Search results for: trees recognition

Authors: Khenfer-Koummich Fatima, Mesbahi Larbi, Hendel Fatiha

Abstract:

This paper presents a recognition system for isolated words like robot commands. It’s carried out by Time Delay Neural Networks; TDNN. To teleoperate a robot for specific tasks as turn, close, etc… In industrial environment and taking into account the noise coming from the machine. The choice of TDNN is based on its generalization in terms of accuracy, in more it acts as a filter that allows the passage of certain desirable frequency characteristics of speech; the goal is to determine the parameters of this filter for making an adaptable system to the variability of speech signal and to noise especially, for this the back propagation technique was used in learning phase. The approach was applied on commands pronounced in two languages separately: The French and Arabic. The results for two test bases of 300 spoken words for each one are 87%, 97.6% in neutral environment and 77.67%, 92.67% when the white Gaussian noisy was added with a SNR of 35 dB.

Keywords: TDNN, neural networks, noise, speech recognition

Procedia PDF Downloads 289

Authors: Emiru Birhane, Tesfay Gidey, Haftu Abrha, Abrha Brhan, Amanuel Zenebe, Girmay Gebresamuel, Florent Noulèkoun

Abstract:

Dracaena ombet and Dobera glabra are two of the most rare and endangered tree species in dryland areas. Unfortunately, their sustainability is being compromised by different anthropogenic and natural factors. However, the impacts of ongoing land use and climate change on the population structure and distribution of the species are less explored. This study was carried out in the grazing lands and hillside areas of the Desa'a dry Afromontane forest, northern Ethiopia, to characterize the population structure of the species and predict the impact of climate change on their potential distributions. In each land-use type, abundance, diameter at breast height, and height of the trees were collected using 70 sampling plots distributed over seven transects spaced one km apart. The geographic coordinates of each individual tree were also recorded. The results showed that the species populations were characterized by low abundance and unstable population structure. The latter was evinced by a lack of seedlings and mature trees. The study also revealed that the total abundance and dendrometric traits of the trees were significantly different between the two land uses. The hillside areas had a denser abundance of bigger and taller trees than the grazing lands. Climate change predictions using the MaxEnt model highlighted that future temperature increases coupled with reduced precipitation would lead to significant reductions in the suitable habitats of the species in northern Ethiopia. The species' suitable habitats were predicted to decline by 48–83% for D. ombet and 35–87% for D. glabra. Hence, to sustain the species populations, different strategies should be adopted, namely the introduction of alternative livelihoods (e.g., gathering NTFP) to reduce the overexploitation of the species for subsistence income and the protection of the current habitats that will remain suitable in the future using community-based exclosures. Additionally, the preservation of the species' seeds in gene banks is crucial to ensure their long-term conservation.

Keywords: grazing lands, hillside areas, land-use change, MaxEnt, range limitation, rare and endangered tree species

Procedia PDF Downloads 96

Authors: Jae-Hyun Choi, Sung-Soo Bae, Sangyoung Yoon, Hong-Ku Yun, Jiyoung Kwahk

Abstract:

This study was conducted to investigate the effect of ocular dominance on recognition performance using a single-lens smart display designed for cycling. A total of 36 bicycle riders who have been cycling consistently were recruited and participated in the experiment. The participants were asked to perform tasks riding a bicycle on a stationary stand for safety reasons. Independent variables of interest include ocular dominance, bike usage, age group, and information layout. Recognition time (i.e., the time required to identify specific information measured with an eye-tracker), error rate (i.e. false answer or failure to identify the information in 5 seconds), and user preference scores were measured and statistical tests were conducted to identify significant results. Recognition time and error ratio showed significant difference by ocular dominance factor, while the preference score did not. Recognition time was faster when the single-lens see-through display on the dominant eye (average 1.12sec) than on the non-dominant eye (average 1.38sec). Error ratio of the information recognition task was significantly lower when the see-through display was worn on the dominant eye (average 4.86%) than on the non-dominant eye (average 14.04%). The interaction effect of ocular dominance and age group was significant with respect to recognition time and error ratio. The recognition time of the users in their 40s was significantly longer than the other age groups when the display was placed on the non-dominant eye, while no difference was observed on the dominant eye. Error ratio also showed the same pattern. Although no difference was observed for the main effect of ocular dominance and bike usage, the interaction effect between the two variables was significant with respect to preference score. Preference score of daily bike users was higher when the display was placed on the dominant eye, whereas participants who use bikes for leisure purposes showed the opposite preference patterns. It was found more effective and efficient to wear a see-through display on the dominant eye than on the non-dominant eye, although user preference was not affected by ocular dominance. It is recommended to wear a see-through display on the dominant eye since it is safer by helping the user recognize the presented information faster and more accurately, even if the user may not notice the difference.

Keywords: eye tracking, information recognition, ocular dominance, smart headware, wearable device

Procedia PDF Downloads 272

Authors: Shinoy Vengaramkode Bhaskaran, Kaushik Sathupadi, Sandesh Achar

Abstract:

Human locomotion recognition is important in a variety of sectors, such as robotics, security, healthcare, fitness tracking and cloud computing. With the increasing pervasiveness of peripheral devices, particularly Inertial Measurement Units (IMUs) sensors, researchers have attempted to exploit these advancements in order to precisely and efficiently identify and categorize human activities. This research paper introduces a state-of-the-art methodology for the recognition of human locomotion patterns in a cloud environment. The methodology is based on a publicly available benchmark dataset. The investigation implements a denoising and windowing strategy to deal with the unprocessed data. Next, feature extraction is adopted to abstract the main cues from the data. The SelectKBest strategy is used to abstract optimal features from the data. Furthermore, state-of-the-art ML classifiers are used to evaluate the performance of the system, including logistic regression, random forest, gradient boosting and SVM have been investigated to accomplish precise locomotion classification. Finally, a detailed comparative analysis of results is presented to reveal the performance of recognition models.

Keywords: artificial intelligence, cloud computing, IoT, human locomotion, gradient boosting, random forest, neural networks, body-worn sensors

Procedia PDF Downloads 11

Authors: Çiğdem Bakır, Mecit Yüzkat

Abstract:

With the increasing emphasis on water quality worldwide, the search for and expanding the market for new and intelligent monitoring systems has increased. The current method is the laboratory process, where samples are taken from bodies of water, and tests are carried out in laboratories. This method is time-consuming, a waste of manpower, and uneconomical. To solve this problem, we used machine learning methods to detect water pollution in our study. We created decision trees with the Orange3 software we used in our study and tried to determine all the factors that cause water pollution. An automatic prediction model based on water quality was developed by taking many model inputs such as water temperature, pH, transparency, conductivity, dissolved oxygen, and ammonia nitrogen with machine learning methods. The proposed approach consists of three stages: preprocessing of the data used, feature detection, and classification. We tried to determine the success of our study with different accuracy metrics and the results. We presented it comparatively. In addition, we achieved approximately 98% success with the decision tree.

Keywords: decision tree, water quality, water pollution, machine learning

Procedia PDF Downloads 82

Authors: Avyarthana Dey, Naren P. Rao, Arpitha Jacob, Chaitra V. Hiremath, Shivarama Varambally, Ganesan Venkatasubramanian, Rose Dawn Bharath, Bangalore N. Gangadhar

Abstract:

Objective: Impaired facial emotion recognition is widely reported in schizophrenia. Neuropeptide oxytocin is known to modulate brain regions involved in facial emotion recognition, namely amygdala, in healthy volunteers. However, its effect on facial emotion recognition deficits seen in schizophrenia is not well explored. In this study, we examined the effect of intranasal OXT on processing facial emotions and its neural correlates in patients with schizophrenia. Method: 12 male patients (age= 31.08±7.61 years, education= 14.50±2.20 years) participated in this single-blind, counterbalanced functional magnetic resonance imaging (fMRI) study. All participants underwent three fMRI scans; one at baseline, one each after single dose 24IU intranasal OXT and intranasal placebo. The order of administration of OXT and placebo were counterbalanced and subject was blind to the drug administered. Participants performed a facial emotion recognition task presented in a block design with six alternating blocks of faces and shapes. The faces depicted happy, angry or fearful emotions. The images were preprocessed and analyzed using SPM 12. First level contrasts comparing recognition of emotions and shapes were modelled at individual subject level. A group level analysis was performed using the contrasts generated at the first level to compare the effects of intranasal OXT and placebo. The results were thresholded at uncorrected p < 0.001 with a cluster size of 6 voxels. Neuropeptide oxytocin is known to modulate brain regions involved in facial emotion recognition, namely amygdala, in healthy volunteers. Results: Compared to placebo, intranasal OXT attenuated activity in inferior temporal, fusiform and parahippocampal gyri (BA 20), premotor cortex (BA 6), middle frontal gyrus (BA 10) and anterior cingulate gyrus (BA 24) and enhanced activity in the middle occipital gyrus (BA 18), inferior occipital gyrus (BA 19), and superior temporal gyrus (BA 22). There were no significant differences between the conditions on the accuracy scores of emotion recognition between baseline (77.3±18.38), oxytocin (82.63 ± 10.92) or Placebo (76.62 ± 22.67). Conclusion: Our results provide further evidence to the modulatory effect of oxytocin in patients with schizophrenia. Single dose oxytocin resulted in significant changes in activity of brain regions involved in emotion processing. Future studies need to examine the effectiveness of long-term treatment with OXT for emotion recognition deficits in patients with schizophrenia.

Keywords: recognition, functional connectivity, oxytocin, schizophrenia, social cognition

Procedia PDF Downloads 220

Authors: Rabail Shafique Satti, Sidra Ejaz, Madiha Arshad, Marwa Khalid, Sadia Majeed

Abstract:

The paper presents the development of an automated security system to automate the entry of visitors, providing more flexibility of managing their record and securing homes or workplaces. Face recognition is part of this system to authenticate the visitors. A cost effective and SMS based door security module has been developed and integrated with the GSM network and made part of this system to allow communication between system and owner. This system functions in real time as when the visitor’s arrived it will detect and recognizes his face and on the result of face recognition process it will open the door for authorized visitors or notifies and allows the owner’s to take further action in case of unauthorized visitor. The proposed system is developed and it is successfully ensuring security, managing records and operating gate without physical interaction of owner.

Keywords: SMS, e-mail, GSM modem, authenticate, face recognition, authorized

Procedia PDF Downloads 789

Authors: Dong Seop Lee, Byung Sik Kim

Abstract:

In the 4th Industrial Revolution, various intelligent technologies have been developed in many fields. These artificial intelligence technologies are applied in various services, including disaster management. Disaster information management does not just support disaster work, but it is also the foundation of smart disaster management. Furthermore, it gets historical disaster information using artificial intelligence technology. Disaster information is one of important elements of entire disaster cycle. Disaster information management refers to the act of managing and processing electronic data about disaster cycle from its’ occurrence to progress, response, and plan. However, information about status control, response, recovery from natural and social disaster events, etc. is mainly managed in the structured and unstructured form of reports. Those exist as handouts or hard-copies of reports. Such unstructured form of data is often lost or destroyed due to inefficient management. It is necessary to manage unstructured data for disaster information. In this paper, the Optical Character Recognition approach is used to convert handout, hard-copies, images or reports, which is printed or generated by scanners, etc. into electronic documents. Following that, the converted disaster data is organized into the disaster code system as disaster information. Those data are stored in the disaster database system. Gathering and creating disaster information based on Optical Character Recognition for unstructured data is important element as realm of the smart disaster management. In this paper, Korean characters were improved to over 90% character recognition rate by using upgraded OCR. In the case of character recognition, the recognition rate depends on the fonts, size, and special symbols of character. We improved it through the machine learning algorithm. These converted structured data is managed in a standardized disaster information form connected with the disaster code system. The disaster code system is covered that the structured information is stored and retrieve on entire disaster cycle such as historical disaster progress, damages, response, and recovery. The expected effect of this research will be able to apply it to smart disaster management and decision making by combining artificial intelligence technologies and historical big data.

Keywords: disaster information management, unstructured data, optical character recognition, machine learning

Procedia PDF Downloads 129

Authors: Micheal Olaolu Arowolo, Muhammad Azam, Fei He, Mihail Popescu, Dong Xu

Abstract:

As the quantity of biological articles rises, so does the number of biological route figures. Each route figure shows gene names and relationships. Annotating pathway diagrams manually is time-consuming. Advanced image understanding models could speed up curation, but they must be more precise. There is rich information in biological pathway figures. The first step to performing image understanding of these figures is to recognize gene names automatically. Classical optical character recognition methods have been employed for gene name recognition, but they are not optimized for literature mining data. This study devised a method to recognize an image bounding box of gene name as a photo using deep Siamese neural network models to outperform the existing methods using ResNet, DenseNet and Inception architectures, the results obtained about 84% accuracy.

Keywords: biological pathway, gene identification, object detection, Siamese network

Procedia PDF Downloads 292

Authors: Titinan Pothong, Prasit Wangpakapattanawong, Stephen Elliott

Abstract:

Shifting cultivation is an indigenous agricultural practice among upland people and has long been one of the major land-use systems in Southeast Asia. As a result, fallows and secondary forests have come to cover a large part of the region. However, they are increasingly being replaced by monocultures, such as corn cultivation. This is believed to be a main driver of deforestation and forest degradation, and one of the reasons behind the recurring winter smog crisis in Thailand and around Southeast Asia. Accurate biomass estimation of trees is important to quantify valuable carbon stocks and changes to these stocks in case of land use change. However, presently, Thailand lacks proper tools and optimal equations to quantify its carbon stocks, especially for secondary evergreen forests, including fallow areas after shifting cultivation and smaller trees with a diameter at breast height (DBH) of less than 5 cm. Developing new allometric equations to estimate biomass is urgently needed to accurately estimate and manage carbon storage in tropical secondary forests. This study established new equations using a destructive method at three study sites: approximately 50-year-old secondary forest, 4-year-old fallow, and 7-year-old fallow. Tree biomass was collected by harvesting 136 individual trees (including coppiced trees) from 23 species, with a DBH ranging from 1 to 31 cm. Oven-dried samples were sent for carbon analysis. Wood density was calculated from disk samples and samples collected with an increment borer from 79 species, including 35 species currently missing from the Global Wood Densities database. Several models were developed, showing that aboveground biomass (AGB) was strongly related to DBH, height (H), and wood density (WD). Including WD in the model was found to improve the accuracy of the AGB estimation. This study provides insights for reforestation management, and can be used to prepare baseline data for Thailand’s carbon stocks for the REDD+ and other carbon trading schemes. These may provide monetary incentives to stop illegal logging and deforestation for monoculture.

Keywords: aboveground biomass, allometric equation, carbon stock, secondary forest

Procedia PDF Downloads 284

Authors: Muhammad Tayyab, Saba Saira

Abstract:

It is an established fact that organizations across the globe consider employees as their assets and try to advance their well-being. However, the local firms of developing countries are mostly profit oriented and do not have much concern about their employees’ engagement or commitment. Like other developing countries, the local organizations of Pakistan are also less concerned about the well-being of their employees. Especially public sector organizations lack concern regarding engagement, satisfaction or commitment of the employees. Therefore, this study aimed at investigating the impact of job recognition and job motivation on organizational commitment in the mediation role of employee engagement. The data were collected from land record officers of board of revenue, Punjab, Pakistan. Structured questionnaire was used to collect data through physically visiting land record officers and also through the internet. A total of 318 land record officers’ responses were finalized to perform data analysis. The data were analyzed through confirmatory factor analysis and structural equation modeling technique. The findings revealed that job recognition and job motivation have direct as well as indirect positive and significant impact on organizational commitment. The limitations, practical implications and future research indications are also explained.

Keywords: job motivation, job recognition, employee engagement, employee commitment, public sector, land record officers

Procedia PDF Downloads 132

Authors: Ashwinder K. Dhaliwal, G. P. S. Dhillon

Abstract:

Eucalyptus is one of the most important forest tree species that can tolerate and grow well on degraded and unfertile soils which are not suitable for other tree species. Besides this, these trees have a short rotation and good economic value. However, the gall inducing wasp Leptocybe invasa Fisher and La Salle has been reported from many countries throughout the world. The spread of L. invasa is of huge economic concern as more than 20,000 ha of young Eucalyptus trees have already been affected in southern states of India. The host plant resistance being the first line of defense against insect pests demands the screening of different germplasm source against L. invasa. Keeping this in view, fourteen different clones of Eucalyptus spp. were evaluated for their susceptibility to L. invasa from a replicated clonal trial planted at Punjab Agricultural University, Ludhiana. The degree of gall infestation was recorded from three plants of each clone in each replication. Three branches selected from the lower, middle and upper canopy of the trees were selected for recording the total number of galls induced by L. invasa. The statistical analysis was done as per the procedure laid down for completely randomised block design (CRBD), analysis of variance (ANOVA), critical difference (CD) and variance components using Proc GLM (SAS software 9.3, SAS Institute Ltd. U.S.A). All possible treatment means were compared with Duncan’s multiple range test (DMRT) at 1 % probability level. The results showed that the clones C-9, C-45 and C-42 were completely free from the infestation of L. invasa. However, there was minor infestation of L. invasa on C-2135, C-413, C-407, C-35, C-72 and C-37 clones. The clone C-6 was severely infested by L. invasa followed by C-11, C-12, F-316 and C-25 clones. The information generated by this study will be helpful for future breeding and use in afforestation programmes.

Keywords: eucalyptus clones, gall wasp, Leptocybe invasa, screening, susceptibility

Procedia PDF Downloads 221

Authors: Miguel Mellado, Cecilia Zapata

Abstract:

Goats can be exploited in harsh environments due to their capacity to adjust to limited quantity and quality forage sources. In these environments, leguminous trees can be used as supplementary feeds as foliage and fruits of these trees can contribute to maintain or improve production efficiency in ruminants. The objective of this study was to determine the nutritional value of three leguminous trees heavily selected by goats in a xerophyllous shrubland. Chemical composition and in vitro dry matter disappearance (IVDMD) of leaves and pods from leucaena (Leucaena leucocephala), mesquite (Prosopis laevigata) and huisache (Acacia farnesiana) is presented. Crude protein (CP) ranged from 17.3% for leaves of huisache to 21.9% for leucaena. The neutral detergent fiber (NDF) content ranged from 39.0 to 40.3 with no difference among fodder threes. Across tree species, mean IVDMD was 61.6% for pods and 52.2% for leaves. IVDMD for leaves was highest (P < 0.01) for leucaena (54.9%) and lowest for huisache (47.3%). Condensed tannins in an acetonic extract were highest for leaves of huisache (45.3 mg CE/g DM) and lowest for mesquite (25.9 mg CE/g DM). Pods and leaves of huisache presented the highest number of secondary metabolites, mainly related to hydrobenzoic acid and flavonols; leucaena and mesquite presented mainly flavonols and anthocyanins. It was concluded that leaves and pods of leucaena, mesquite and huisache constitute valuable forages for ruminant livestock due to its low fiber, high CP levels, moderate in vitro fermentation characteristics and high mineral content. Keywords: Fodder tree; ruminants; secondary metabolites; minerals; tannins

Keywords: fodder tree, ruminants, secondary metabolites, minerals, tannins

Procedia PDF Downloads 145

Authors: M. Draman, S. Z. Muhamad Yassin, M. S. Alias, Z. Lambak, M. I. Zulkifli, S. N. Padhi, K. N. Baharim, F. Maskuriy, A. I. A. Rahim

Abstract:

The performance of Malay automatic speech recognition (ASR) system for the call centre environment is presented. The system utilizes Kaldi toolkit as the platform to the entire library and algorithm used in performing the ASR task. The acoustic model implemented in this system uses a deep neural network (DNN) method to model the acoustic signal and the standard (n-gram) model for language modelling. With 80 hours of training data from the call centre recordings, the ASR system can achieve 72% of accuracy that corresponds to 28% of word error rate (WER). The testing was done using 20 hours of audio data. Despite the implementation of DNN, the system shows a low accuracy owing to the varieties of noises, accent and dialect that typically occurs in Malaysian call centre environment. This significant variation of speakers is reflected by the large standard deviation of the average word error rate (WERav) (i.e., ~ 10%). It is observed that the lowest WER (13.8%) was obtained from recording sample with a standard Malay dialect (central Malaysia) of native speaker as compared to 49% of the sample with the highest WER that contains conversation of the speaker that uses non-standard Malay dialect.

Keywords: conversational speech recognition, deep neural network, Malay language, speech recognition

Procedia PDF Downloads 322

Authors: Hui Wei, Zheng Dong

Abstract:

Object recognition has long been a challenging task in computer vision. Yet the human brain, with the ability to rapidly and accurately recognize visual stimuli, manages this task effortlessly. In the past decades, advances in neuroscience have revealed some neural mechanisms underlying visual processing. In this paper, we present a novel model inspired by the visual pathway in primate brains. This multi-layer neural network model imitates the hierarchical convergent processing mechanism in the visual pathway. We show that local image features generated by this model exhibit robust discrimination and even better generalization ability compared with some existing image descriptors. We also demonstrate the application of this model in an object recognition task on image data sets. The result provides strong support for the potential of this model.

Keywords: biological model, feature extraction, multi-layer neural network, object recognition

Procedia PDF Downloads 542

Authors: Babatunde Olumide Olawale, Oyebode Olumide Oyediran

Abstract:

The security safe is a place or building where classified document and precious items are kept. To prevent unauthorised persons from gaining access to this safe a lot of technologies had been used. But frequent reports of an unauthorised person gaining access into security safes with the aim of removing document and items from the safes are pointers to the fact that there is still security gap in the recent technologies used as access control for the security safe. In this paper we try to solve this problem by developing a multimodal biometric system for physical access control into a security safe using face and voice recognition. The safe is accessed by the combination of face and speech pattern recognition and also in that sequential order. User authentication is achieved through the use of camera/sensor unit and a microphone unit both attached to the door of the safe. The user face was captured by the camera/sensor while the speech was captured by the use of the microphone unit. The Scale Invariance Feature Transform (SIFT) algorithm was used to train images to form templates for the face recognition system while the Mel-Frequency Cepitral Coefficients (MFCC) algorithm was used to train the speech recognition system to recognise authorise user’s speech. Both algorithms were hosted in two separate web based servers and for automatic analysis of our work; our developed system was simulated in a MATLAB environment. The results obtained shows that the developed system was able to give access to authorise users while declining unauthorised person access to the security safe.

Keywords: access control, multimodal biometrics, pattern recognition, security safe

Procedia PDF Downloads 335

Authors: Brahim-Fares Zaidi, Malika Boudraa, Sid-Ahmed Selouani

Abstract:

Our work aims to improve our Automatic Recognition System for Dysarthria Speech (ARSDS) based on the Hidden Models of Markov (HMM) and the Hidden Markov Model Toolkit (HTK) to help people who are sick. With pronunciation problems, we applied two techniques of speech parameterization based on Mel Frequency Cepstral Coefficients (MFCC's) and Perceptual Linear Prediction (PLP's) and concatenated them with JITTER and SHIMMER coefficients in order to increase the recognition rate of a dysarthria speech. For our tests, we used the NEMOURS database that represents speakers with dysarthria and normal speakers.

Keywords: hidden Markov model toolkit (HTK), hidden models of Markov (HMM), Mel-frequency cepstral coefficients (MFCC), perceptual linear prediction (PLP’s)

Procedia PDF Downloads 161

Authors: Nur Nadhirah Rusyda Rosnan, Nursuhaili Najwa Masrol, Nurul Fatiha MD Nor, Mohammad Zafrullah Mohammad Salim, Sim Choon Cheak

Abstract:

Accurate inventories of oil palm planted areas are crucial for plantation management as this would impact the overall economy and production of oil. One of the technological advancements in the oil palm industry is semi-automated palm counting, which is replacing conventional manual palm counting via digitizing aerial imagery. Most of the semi-automated palm counting method that has been developed was limited to mature palms due to their ideal canopy size represented by satellite image. Therefore, immature palms were often left out since the size of the canopy is barely visible from satellite images. In this paper, an approach using a morphological filter and high-resolution satellite image is proposed to detect immature palm trees. This approach makes it possible to count the number of immature oil palm trees. The method begins with an erosion filter with an appropriate window size of 3m onto the high-resolution satellite image. The eroded image was further segmented using watershed segmentation to delineate immature palm tree regions. Then, local minimum detection was used because it is hypothesized that immature oil palm trees are located at the local minimum within an oil palm field setting in a grayscale image. The detection points generated from the local minimum are displaced to the center of the immature oil palm region and thinned. Only one detection point is left that represents a tree. The performance of the proposed method was evaluated on three subsets with slopes ranging from 0 to 20° and different planting designs, i.e., straight and terrace. The proposed method was able to achieve up to more than 90% accuracy when compared with the ground truth, with an overall F-measure score of up to 0.91.

Keywords: immature palm count, oil palm, precision agriculture, remote sensing

Procedia PDF Downloads 76

Authors: Mumtaz Begum Mustafa, Siti Salwah Salim, Feizal Dani Rahman

Abstract:

Recently, Automatic Speech Recognition (ASR) systems were used to assist children in language acquisition as it has the ability to detect human speech signal. Despite the benefits offered by the ASR system, there is a lack of ASR systems for Malay-speaking children. One of the contributing factors for this is the lack of continuous speech database for the target users. Though cross-lingual adaptation is a common solution for developing ASR systems for under-resourced language, it is not viable for children as there are very limited speech databases as a source model. In this research, we propose a two-stage adaptation for the development of ASR system for Malay-speaking children using a very limited database. The two stage adaptation comprises the cross-lingual adaptation (first stage) and cross-age adaptation. For the first stage, a well-known speech database that is phonetically rich and balanced, is adapted to the medium-sized Malay adults using supervised MLLR. The second stage adaptation uses the speech acoustic model generated from the first adaptation, and the target database is a small-sized database of the target users. We have measured the performance of the proposed technique using word error rate, and then compare them with the conventional benchmark adaptation. The two stage adaptation proposed in this research has better recognition accuracy as compared to the benchmark adaptation in recognizing children’s speech.

Keywords: Automatic Speech Recognition System, children speech, adaptation, Malay

Procedia PDF Downloads 397

Authors: Marie Alaghband, Niloofar Yousefi, Ivan Garibay

Abstract:

Facial expressions are important parts of both gesture and sign language recognition systems. Despite the recent advances in both fields, annotated facial expression datasets in the context of sign language are still scarce resources. In this manuscript, we introduce an annotated sequenced facial expression dataset in the context of sign language, comprising over 3000 facial images extracted from the daily news and weather forecast of the public tv-station PHOENIX. Unlike the majority of currently existing facial expression datasets, FePh provides sequenced semi-blurry facial images with different head poses, orientations, and movements. In addition, in the majority of images, identities are mouthing the words, which makes the data more challenging. To annotate this dataset we consider primary, secondary, and tertiary dyads of seven basic emotions of "sad", "surprise", "fear", "angry", "neutral", "disgust", and "happy". We also considered the "None" class if the image’s facial expression could not be described by any of the aforementioned emotions. Although we provide FePh as a facial expression dataset of signers in sign language, it has a wider application in gesture recognition and Human Computer Interaction (HCI) systems.

Keywords: annotated facial expression dataset, gesture recognition, sequenced facial expression dataset, sign language recognition

Procedia PDF Downloads 159

Authors: Thein Thein, Kalyar Myo San

Abstract:

Lip reading system is one of the different supportive technologies for hearing impaired, or elderly people or non-native speakers. For normal hearing persons in noisy environments or in conditions where the audio signal is not available, lip reading techniques can be used to increase their understanding of spoken language. Hearing impaired persons have used lip reading techniques as important tools to find out what was said by other people without hearing voice. Thus, visual speech information is important and become active research area. Using visual information from lip movements can improve the accuracy and robustness of a speech recognition system and the need for lip reading system is ever increasing for every language. However, the recognition of lip movement is a difficult task because of the region of interest (ROI) is nonlinear and noisy. Therefore, this paper proposes method to detect the accurate lips shape and to localize lip movement towards automatic lip tracking by using the combination of Otsu global thresholding technique and Moore Neighborhood Tracing Algorithm. Proposed method shows how accurate lip localization and tracking which is useful for speech recognition. In this work of study and experiments will be carried out the automatic lip localizing the lip shape for Myanmar consonants using the only visual information from lip movements which is useful for visual speech of Myanmar languages.

Keywords: lip reading, lip localization, lip tracking, Moore neighborhood tracing algorithm

Procedia PDF Downloads 352

Authors: M. L. Anitha, K. A. Radhakrishna Rao

Abstract:

With the advent of modern computing technology, there is an increased demand for developing recognition systems that have the capability of verifying the identity of individuals. Recognition systems are required by several civilian and commercial applications for providing access to secured resources. Traditional recognition systems which are based on physical identities are not sufficiently reliable to satisfy the security requirements due to the use of several advances of forgery and identity impersonation methods. Recognizing individuals based on his/her unique physiological characteristics known as biometric traits is a reliable technique, since these traits are not transferable and they cannot be stolen or lost. Since the performance of biometric based recognition system depends on the particular trait that is utilized, the present work proposes a fusion approach which combines Inner knuckle print (IKP) trait of the middle, ring and index fingers with the geometrical features of hand. The hand image captured from a digital camera is preprocessed to find finger IKP as region of interest (ROI) and hand geometry features. Geometrical features are represented as the distances between different key points and IKP features are extracted by applying local binary pattern descriptor on the IKP ROI. The decision level AND fusion was adopted, which has shown improvement in performance of the combined scheme. The proposed approach is tested on the database collected at our institute. Proposed approach is of significance since both hand geometry and IKP features can be extracted from the palm region of the hand. The fusion of these features yields a false acceptance rate of 0.75%, false rejection rate of 0.86% for verification tests conducted, which is less when compared to the results obtained using individual traits. The results obtained confirm the usefulness of proposed approach and suitability of the selected features for developing biometric based recognition system based on features from palmar region of hand.

Keywords: biometrics, hand geometry features, inner knuckle print, recognition

Procedia PDF Downloads 220

Authors: María de los Ángeles Cerda González, Itzel Arriaga Hurtado, Pascacio José Martínez Pichardo

Abstract:

In México, the recognition of refugee condition is a fundamental right which, as host State, has the obligation of respect, protect, and fulfill to the foreigners – where we can find the figure of immigrants in irregular situation-, that cannot return to their country of origin for humanitarian reasons. The recognition of the refugee condition as a fundamental right in the Mexican law system proceeds under these situations: 1. The immigrant applies for the refugee condition, even without the necessary proving elements to accredit the humanitarian character of his departure from his country of origin. 2. The immigrant does not apply for the recognition of refugee because he does not know he has the right to, even if he has the profile to apply for. 3. The immigrant who applies fulfills the requirements of the administrative procedure and has access to the refugee recognition. Of the three situations above, only the last one is contemplated for the national indexes of the status refugee; and the first two prove the inefficiency of the governmental system viewed from its lack of sensibility consequence of the no education in human rights matter and which results in the legal vulnerability of the immigrants in irregular situation because they do not have access to the procuration and administration of justice. In the aim of determining the causes and consequences of the no recognition of the refugee status, this investigation was structured from a systemic analysis which objective is to show the advances in Central American humanitarian emergency investigation, the Mexican States actions to protect, respect and fulfil the fundamental right of refugee of immigrants in irregular situation and the social and legal vulnerabilities suffered by Central Americans in Mexico. Therefore, to achieve the deduction of the legal nature of the humanitarian emergency from the Human Rights as a branch of the International Public Law, a conceptual framework is structured using the inductive deductive method. The problem statement is made from a legal framework to approach a theoretical scheme under the theory of social systems, from the analysis of the lack of communication of the governmental and normative subsystems of the Mexican legal system relative to the process undertaken by the Central American immigrants to achieve the recognition of the refugee status as a human right. Accordingly, is determined that fulfilling the obligations of the State referent to grant the right of the recognition of the refugee condition, would mean a guideline for a new stage in Mexican Law, because it would enlarge the constitutional benefits to everyone whose right to the recognition of refugee has been denied an as consequence, a great advance in human rights matter would be achieved.

Keywords: central American immigrants in irregular situation, humanitarian emergency, human rights, refugee

Procedia PDF Downloads 289

Authors: Harshit Mittal, Neeraj Garg

Abstract:

Hand symbol recognition is a pivotal component in the domain of computer vision, with far-reaching applications spanning sign language interpretation, human-computer interaction, and accessibility. This research paper discusses the approach with the integration of the Canny Edge algorithm and convolutional neural network. The significance of this study lies in its potential to enhance communication and accessibility for individuals with hearing impairments or those engaged in gesture-based interactions with technology. In the experiment mentioned, the data is manually collected by the authors from the webcam using Python codes, to increase the dataset augmentation, is applied to original images, which makes the model more compatible and advanced. Further, the dataset of about 6000 coloured images distributed equally in 5 classes (i.e., 1, 2, 3, 4, 5) are pre-processed first to gray images and then by the Canny Edge algorithm with threshold 1 and 2 as 150 each. After successful data building, this data is trained on the Convolutional Neural Network model, giving accuracy: 0.97834, precision: 0.97841, recall: 0.9783, and F1 score: 0.97832. For user purposes, a block of codes is built in Python to enable a window for hand symbol recognition. This research, at its core, seeks to advance the field of computer vision by providing an advanced perspective on hand sign recognition. By leveraging the capabilities of the Canny Edge algorithm and convolutional neural network, this study contributes to the ongoing efforts to create more accurate, efficient, and accessible solutions for individuals with diverse communication needs.

Keywords: hand symbol recognition, computer vision, Canny edge algorithm, convolutional neural network

Procedia PDF Downloads 64

Authors: Tomasz Sapiński, Dorota Kamińska, Adam Pelikant, Egils Avots, Cagri Ozcinar, Gholamreza Anbarjafari

Abstract:

People express emotions through different modalities. Integration of verbal and non-verbal communication channels creates a system in which the message is easier to understand. Expanding the focus to several expression forms can facilitate research on emotion recognition as well as human-machine interaction. In this article, the authors present a Polish emotional database composed of three modalities: facial expressions, body movement and gestures, and speech. The corpora contains recordings registered in studio conditions, acted out by 16 professional actors (8 male and 8 female). The data is labeled with six basic emotions categories, according to Ekman’s emotion categories. To check the quality of performance, all recordings are evaluated by experts and volunteers. The database is available to academic community and might be useful in the study on audio-visual emotion recognition.

Keywords: body movement, emotion recognition, emotional corpus, facial expressions, gestures, multimodal database, speech

Procedia PDF Downloads 349

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: classification, singing, spectral analysis, vocal emission, vocal register

Procedia PDF Downloads 304

Authors: Narges Farokhshad, Milad Molazadeh, Saman Jamalabbasi, Hamed Babaei Giglou, Saeed Bibak

Abstract:

The Persian language is an inflectional subject-object-verb language. This fact makes Persian a more uncertain language. However, using techniques such as Zero-Width Non-Joiner (ZWNJ) recognition, punctuation restoration, and Persian Ezafe construction will lead us to a more understandable and precise language. In most of the works in Persian, these techniques are addressed individually. Despite that, we believe that for text refinement in Persian, all of these tasks are necessary. In this work, we proposed a ViraPart framework that uses embedded ParsBERT in its core for text clarifications. First, used the BERT variant for Persian followed by a classifier layer for classification procedures. Next, we combined models outputs to output cleartext. In the end, the proposed model for ZWNJ recognition, punctuation restoration, and Persian Ezafe construction performs the averaged F1 macro scores of 96.90%, 92.13%, and 98.50%, respectively. Experimental results show that our proposed approach is very effective in text refinement for the Persian language.

Keywords: Persian Ezafe, punctuation, ZWNJ, NLP, ParsBERT, transformers

Procedia PDF Downloads 216

Authors: Shaode Yu, Jiajian Meng, Bing Zhu, Hang Yu, Qiurui Sun

Abstract:

Speech emotion recognition (SER) is for recognizing human subjective emotions through audio data in-depth analysis. From speech audios, how to comprehensively extract emotional information and how to effectively fuse extracted features remain challenging. This paper presents a dual-stream SER framework that embraces both full training and transfer learning of different networks for thorough feature encoding. Besides, a plug-and-play cross-attention fusion (CAF) module is implemented for the valid integration of the dual-stream encoder output. The effectiveness of the proposed CAF module is compared to the other three fusion modules (feature summation, feature concatenation, and feature-wise linear modulation) on two databases (RAVDESS and IEMO-CAP) using different dual-stream encoders (full training network, DPCNN or TextRCNN; transfer learning network, HuBERT or Wav2Vec2). Experimental results suggest that the CAF module can effectively reconcile conflicts between features from different encoders and outperform the other three feature fusion modules on the SER task. In the future, the plug-and-play CAF module can be extended for multi-branch feature fusion, and the dual-stream SER framework can be widened for multi-stream data representation to improve the recognition performance and generalization capacity.

Keywords: speech emotion recognition, cross-attention fusion, dual-stream, pre-trained

Procedia PDF Downloads 75

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Hami-Ziniman Revital, Ashwall Rachelly

Abstract:

The conflict resolution realm has developed tremendously during the last half-decade. Three main approaches should be mentioned: an Alternative Dispute Resolution (ADR) suggesting processes such as Arbitration or Interests-based Negotiation was developed as an answer to obligations and rights-based conflicts. The Pragmatic mediation approach focuses on the gap between interests and needs of disputants. The Transformative mediation approach focusses on relations and suits identity-based conflicts. In the current study, we examine the conflictual relations between religious and non-religious Jews in Israel and the impact of three transformative mechanisms: Inter-group recognition, In-group empowerment and Value-based reframing on the relations between the participants. The research was conducted during four facilitated joint mediation classes. A unique finding was found. Using both transformative mechanisms and the Contact Hypothesis criteria, we identify transformation in participants’ relations and a considerable change from anger, alienation, and suspiciousness to an increased understanding, affection and interpersonal concern towards the out-group members. Intergroup Recognition, In-group empowerment, and Values-based reframing were the skills discovered as the main enablers of the change in the relations and the research participants’ fostered mutual recognition of the out-group values and identity-based issues. We conclude this transformation was possible due to a constant intergroup contact, based on the Contact Hypothesis criteria. In addition, as Interests-based mediation uses “Reframing” as a skill to acknowledge both mutual and opposite needs of the disputants, we suggest the use of “Value-based Reframing” in intergroup identity-based conflicts, as a skill contributes to the empowerment and the recognition of both mutual and different out-group values. We offer to implement those insights and skills to assist conflict resolution facilitators in various intergroup identity-based conflicts resolution efforts and to establish further research and knowledge.

Keywords: empowerment, identity-based conflict, intergroup recognition, intergroup relations, mediation skills, multi-cultural society, reframing, value-based recognition

Procedia PDF Downloads 342