Search results for: sign language recognition
1385 Automatic Number Plate Recognition System Based on Deep Learning
Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi
Abstract:
In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.
Keywords: Automatic number plate recognition, character segmentation, convolutional neural network, CNN, deep learning, number plate localization.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12591384 Developing a Practice Guideline for Enhancing Communication in Hearing Families with Deaf Children
Authors: Nomataru P. Gontse, Lavanithum Joseph
Abstract:
Deafness coupled with a lack of support and resources in developing countries poses a serious threat to the well- being of children. The mismatch between the needs of persons with disabilities and the resources available to them is a key factor in service provision in resource constrained contexts. Furthermore, deafness in children is the most common childhood sensory disorder in developing countries, and as such seriously affected with regard to resource constraints. This paper discusses the issues and research protocol for a Ph.D. study that aims to develop a practice guideline that is contextually sensitive and includes an interdisciplinary approach that will improve the outcomes of learners and the relationships in hearing households with deaf learners in rural areas of the Eastern Cape, one of the poorest provinces in South Africa. The guideline developed will consider the lived experiences of deaf children and their hearing families on the impact deafness has on their relationships and communication at home. Ethical clearance for the study has been obtained. The methodology is a mixed-methods approach in the form of a survey using questionnaires and semi-structured interviews with deaf learners in primary and high school and their hearing parents to get their perspective on the impact deafness has on their relationships and communication at home. The study is conducted using adolescent learners from Grades 7 to 12 (excluding learners younger than 12 years and older than 21 years). An audiologist, teachers, and support staff will also give their views on how the intervention is currently done and possible suggestions on how management can be done differently. Data collection will be conducted in isiXhosa by the researcher, as isiXhosa is dominant in this region. The interviews will be conducted in South African Sign Language by the sign language interpreter for deaf learners and educational professionals. An expected outcome for this study is the development of recommendations and a practice guideline for deaf children diagnosed late from rural or under-resourced environments. To ensure the implementation of the findings, in the end, professionals will be given feedback on the outcomes of the study so that they can identify areas within their practices that require updated knowledge. The developed guideline is expected to have an impact on the Department of Education policies both regionally and nationally, providing recommendations for a strategic management plan and practice guidelines for this vulnerable and marginalized population. The IsiXhosa specific context could be generalized to other similar contexts.
Keywords: Deafness, family-centred approach, early identification, rural communities.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3501383 Automatic Recognition of an Unknown and Time-Varying Number of Simultaneous Environmental Sound Sources
Authors: S. Ntalampiras, I. Potamitis, N. Fakotakis, S. Kouzoupis
Abstract:
The present work faces the problem of automatic enumeration and recognition of an unknown and time-varying number of environmental sound sources while using a single microphone. The assumption that is made is that the sound recorded is a realization of sound sources belonging to a group of audio classes which is known a-priori. We describe two variations of the same principle which is to calculate the distance between the current unknown audio frame and all possible combinations of the classes that are assumed to span the soundscene. We concentrate on categorizing environmental sound sources, such as birds, insects etc. in the task of monitoring the biodiversity of a specific habitat.
Keywords: automatic recognition of multiple sound sources, enumeration of sound sources, computational ecology.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15441382 Natural Language Database Interface for Selection of Data Using Grammar and Parsing
Authors: N. D. Karande, G. A. Patil
Abstract:
Databases have become ubiquitous. Almost all IT applications are storing into and retrieving information from databases. Retrieving information from the database requires knowledge of technical languages such as Structured Query Language (SQL). However majority of the users who interact with the databases do not have a technical background and are intimidated by the idea of using languages such as SQL. This has led to the development of a few Natural Language Database Interfaces (NLDBIs). A NLDBI allows the user to query the database in a natural language. This paper highlights on architecture of new NLDBI system, its implementation and discusses on results obtained. In most of the typical NLDBI systems the natural language statement is converted into an internal representation based on the syntactic and semantic knowledge of the natural language. This representation is then converted into queries using a representation converter. A natural language query is translated to an equivalent SQL query after processing through various stages. The work has been experimented on primitive database queries with certain constraints.
Keywords: Natural language database interface, representation converter, syntactic and semantic knowledge
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 26871381 Gender Differences in Spatial Navigation
Authors: Bia Kim, Sewon Lee, Jaesik Lee
Abstract:
This study aims to investigate the gender differences in spatial navigation using the tasks of 2-D matrix navigation and recognition of real driving scene. The results can be summarized as followings. First, female subjects responded faster in 2-D matrix navigation task than male subjects when landmark instructions were provided. Second, in recognition task, male subjects recognized the key elements involved in the past driving scene more accurately than female subjects. In particular, female subjects tended to miss peripheral information. These results suggest the possibility of gender differences in spatial navigation.Keywords: Gender differences, Spatial navigation, 2-D matrixnavigation, Recognition of driving scene.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27231380 Parametric Primitives for Hand Gesture Recognition
Authors: Sanmohan Krüger, Volker Krüger
Abstract:
Imitation learning is considered to be an effective way of teaching humanoid robots and action recognition is the key step to imitation learning. In this paper an online algorithm to recognize parametric actions with object context is presented. Objects are key instruments in understanding an action when there is uncertainty. Ambiguities arising in similar actions can be resolved with objectn context. We classify actions according to the changes they make to the object space. Actions that produce the same state change in the object movement space are classified to belong to the same class. This allow us to define several classes of actions where members of each class are connected with a semantic interpretation.Keywords: Parametric actions, Action primitives, Hand gesture recognition, Imitation learning
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14771379 Improved Dynamic Bayesian Networks Applied to Arabic on Line Characters Recognition
Authors: Redouane Tlemsani, Abdelkader Benyettou
Abstract:
Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology.
This system is a Markovian system, which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting from training data.
Our approach is based on the dynamic Bayesian Networks formalism. The DBNs theory is a Bayesians networks generalization to the dynamic processes. Among our objective, amounts finding better parameters, which represent the links (dependences) between dynamic network variables.
In applications in pattern recognition, one will carry out the fixing of the structure, which obliges us to admit some strong assumptions (for example independence between some variables). Our application will relate to the Arabic isolated characters on line recognition using our laboratory database: NOUN. A neural tester proposed for DBN external optimization.
The DBN scores and DBN mixed are respectively 70.24% and 62.50%, which lets predict their further development; other approaches taking account time were considered and implemented until obtaining a significant recognition rate 94.79%.
Keywords: Arabic on line character recognition, dynamic Bayesian network, pattern recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17621378 Extended Set of DCT-TPLBP and DCT-FPLBP for Face Recognition
Authors: El Mahdi Barrah, Said Safi, Abdessamad Malaoui
Abstract:
In this paper, we describe an application for face recognition. Many studies have used local descriptors to characterize a face, the performance of these local descriptors remain low by global descriptors (working on the entire image). The application of local descriptors (cutting image into blocks) must be able to store both the advantages of global and local methods in the Discrete Cosine Transform (DCT) domain. This system uses neural network techniques. The letter method provides a good compromise between the two approaches in terms of simplifying of calculation and classifying performance. Finally, we compare our results with those obtained from other local and global conventional approaches.Keywords: Face detection, face recognition, discrete cosine transform (DCT), FPLBP, TPLBP, NN.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19621377 The Predictability and Abstractness of Language: A Study in Understanding and Usage of the English Language through Probabilistic Modeling and Frequency
Authors: Revanth Sai Kosaraju, Michael Ramscar, Melody Dye
Abstract:
Accounts of language acquisition differ significantly in their treatment of the role of prediction in language learning. In particular, nativist accounts posit that probabilistic learning about words and word sequences has little to do with how children come to use language. The accuracy of this claim was examined by testing whether distributional probabilities and frequency contributed to how well 3-4 year olds repeat simple word chunks. Corresponding chunks were the same length, expressed similar content, and were all grammatically acceptable, yet the results of the study showed marked differences in performance when overall distributional frequency varied. It was found that a distributional model of language predicted the empirical findings better than a number of other models, replicating earlier findings and showing that children attend to distributional probabilities in an adult corpus. This suggested that language is more prediction-and-error based, rather than on abstract rules which nativist camps suggest.
Keywords: Abstractness, child psychology, language acquisition, prediction and error.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20751376 Component-based Segmentation of Words from Handwritten Arabic Text
Authors: Jawad H AlKhateeb, Jianmin Jiang, Jinchang Ren, Stan S Ipson
Abstract:
Efficient preprocessing is very essential for automatic recognition of handwritten documents. In this paper, techniques on segmenting words in handwritten Arabic text are presented. Firstly, connected components (ccs) are extracted, and distances among different components are analyzed. The statistical distribution of this distance is then obtained to determine an optimal threshold for words segmentation. Meanwhile, an improved projection based method is also employed for baseline detection. The proposed method has been successfully tested on IFN/ENIT database consisting of 26459 Arabic words handwritten by 411 different writers, and the results were promising and very encouraging in more accurate detection of the baseline and segmentation of words for further recognition.Keywords: Arabic OCR, off-line recognition, Baseline estimation, Word segmentation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21911375 Indian License Plate Detection and Recognition Using Morphological Operation and Template Matching
Authors: W. Devapriya, C. Nelson Kennedy Babu, T. Srihari
Abstract:
Automatic License plate recognition (ALPR) is a technology which recognizes the registration plate or number plate or License plate of a vehicle. In this paper, an Indian vehicle number plate is mined and the characters are predicted in efficient manner. ALPR involves four major technique i) Pre-processing ii) License Plate Location Identification iii) Individual Character Segmentation iv) Character Recognition. The opening phase, named pre-processing helps to remove noises and enhances the quality of the image using the conception of Morphological Operation and Image subtraction. The second phase, the most puzzling stage ascertain the location of license plate using the protocol Canny Edge detection, dilation and erosion. In the third phase, each characters characterized by Connected Component Approach (CCA) and in the ending phase, each segmented characters are conceptualized using cross correlation template matching- a scheme specifically appropriate for fixed format. Major application of ALPR is Tolling collection, Border Control, Parking, Stolen cars, Enforcement, Access Control, Traffic control. The database consists of 500 car images taken under dissimilar lighting condition is used. The efficiency of the system is 97%. Our future focus is Indian Vehicle License Plate Validation (Whether License plate of a vehicle is as per Road transport and highway standard).
Keywords: Automatic License plate recognition, Character recognition, Number plate Recognition, Template matching, morphological operation, canny edge detection.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23831374 Interactive Shadow Play Animation System
Authors: Bo Wan, Xiu Wen, Lingling An, Xiaoling Ding
Abstract:
The paper describes a Chinese shadow play animation system based on Kinect. Users, without any professional training, can personally manipulate the shadow characters to finish a shadow play performance by their body actions and get a shadow play video through giving the record command to our system if they want. In our system, Kinect is responsible for capturing human movement and voice commands data. Gesture recognition module is used to control the change of the shadow play scenes. After packaging the data from Kinect and the recognition result from gesture recognition module, VRPN transmits them to the server-side. At last, the server-side uses the information to control the motion of shadow characters and video recording. This system not only achieves human-computer interaction, but also realizes the interaction between people. It brings an entertaining experience to users and easy to operate for all ages. Even more important is that the application background of Chinese shadow play embodies the protection of the art of shadow play animation.
Keywords: Gesture recognition, Kinect, shadow play animation, VRPN.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 26881373 SIFT Accordion: A Space-Time Descriptor Applied to Human Action Recognition
Authors: Olfa.Ben Ahmed, Mahmoud. Mejdoub, Chokri. Ben Amar
Abstract:
Recognizing human action from videos is an active field of research in computer vision and pattern recognition. Human activity recognition has many potential applications such as video surveillance, human machine interaction, sport videos retrieval and robot navigation. Actually, local descriptors and bag of visuals words models achieve state-of-the-art performance for human action recognition. The main challenge in features description is how to represent efficiently the local motion information. Most of the previous works focus on the extension of 2D local descriptors on 3D ones to describe local information around every interest point. In this paper, we propose a new spatio-temporal descriptor based on a spacetime description of moving points. Our description is focused on an Accordion representation of video which is well-suited to recognize human action from 2D local descriptors without the need to 3D extensions. We use the bag of words approach to represent videos. We quantify 2D local descriptor describing both temporal and spatial features with a good compromise between computational complexity and action recognition rates. We have reached impressive results on publicly available action data setKeywords: Accordion, Bag of Features, Human action, Motion, Moving point, Space-Time Descriptor, SIFT, Video.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20961372 Comparison of MFCC and Cepstral Coefficients as a Feature Set for PCG Biometric Systems
Authors: Justin Leo Cheang Loong, Khazaimatol S Subari, Muhammad Kamil Abdullah, Nurul Nadia Ahmad, RosliBesar
Abstract:
Heart sound is an acoustic signal and many techniques used nowadays for human recognition tasks borrow speech recognition techniques. One popular choice for feature extraction of accoustic signals is the Mel Frequency Cepstral Coefficients (MFCC) which maps the signal onto a non-linear Mel-Scale that mimics the human hearing. However the Mel-Scale is almost linear in the frequency region of heart sounds and thus should produce similar results with the standard cepstral coefficients (CC). In this paper, MFCC is investigated to see if it produces superior results for PCG based human identification system compared to CC. Results show that the MFCC system is still superior to CC despite linear filter-banks in the lower frequency range, giving up to 95% correct recognition rate for MFCC and 90% for CC. Further experiments show that the high recognition rate is due to the implementation of filter-banks and not from Mel-Scaling.Keywords: Biometric, Phonocardiogram, Cepstral Coefficients, Mel Frequency
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 35361371 ADABeV: Automatic Detection of Abnormal Behavior in Video-surveillance
Authors: Nour Charara, Iman Jarkass, Maria Sokhn, Elena Mugellini, Omar Abou Khaled
Abstract:
Intelligent Video-Surveillance (IVS) systems are being more and more popular in security applications. The analysis and recognition of abnormal behaviours in a video sequence has gradually drawn the attention in the field of IVS, since it allows filtering out a large number of useless information, which guarantees the high efficiency in the security protection, and save a lot of human and material resources. We present in this paper ADABeV, an intelligent video-surveillance framework for event recognition in crowded scene to detect the abnormal human behaviour. This framework is attended to be able to achieve real-time alarming, reducing the lags in traditional monitoring systems. This architecture proposal addresses four main challenges: behaviour understanding in crowded scenes, hard lighting conditions, multiple input kinds of sensors and contextual-based adaptability to recognize the active context of the scene.Keywords: Behavior recognition, Crowded scene, Data fusion, Pattern recognition, Video-surveillance
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 36201370 Object Recognition in Color Images by the Self Configuring System MEMORI
Authors: Michela Lecca
Abstract:
System MEMORI automatically detects and recognizes rotated and/or rescaled versions of the objects of a database within digital color images with cluttered background. This task is accomplished by means of a region grouping algorithm guided by heuristic rules, whose parameters concern some geometrical properties and the recognition score of the database objects. This paper focuses on the strategies implemented in MEMORI for the estimation of the heuristic rule parameters. This estimation, being automatic, makes the system a self configuring and highly user-friendly tool.Keywords: Automatic Object Recognition, Clustering, Contentbased Image Retrieval System, Image Segmentation, Region Adjacency Graph, Region Grouping.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 11881369 Learning to Recognize Faces by Local Feature Design and Selection
Authors: Yanwei Pang, Lei Zhang, Zhengkai Liu
Abstract:
Studies in neuroscience suggest that both global and local feature information are crucial for perception and recognition of faces. It is widely believed that local feature is less sensitive to variations caused by illumination, expression and illumination. In this paper, we target at designing and learning local features for face recognition. We designed three types of local features. They are semi-global feature, local patch feature and tangent shape feature. The designing of semi-global feature aims at taking advantage of global-like feature and meanwhile avoiding suppressing AdaBoost algorithm in boosting weak classifies established from small local patches. The designing of local patch feature targets at automatically selecting discriminative features, and is thus different with traditional ways, in which local patches are usually selected manually to cover the salient facial components. Also, shape feature is considered in this paper for frontal view face recognition. These features are selected and combined under the framework of boosting algorithm and cascade structure. The experimental results demonstrate that the proposed approach outperforms the standard eigenface method and Bayesian method. Moreover, the selected local features and observations in the experiments are enlightening to researches in local feature design in face recognition.Keywords: Face recognition, local feature, AdaBoost, subspace analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15801368 Dynamic Threshold Adjustment Approach For Neural Networks
Authors: Hamza A. Ali, Waleed A. J. Rasheed
Abstract:
The use of neural networks for recognition application is generally constrained by their inherent parameters inflexibility after the training phase. This means no adaptation is accommodated for input variations that have any influence on the network parameters. Attempts were made in this work to design a neural network that includes an additional mechanism that adjusts the threshold values according to the input pattern variations. The new approach is based on splitting the whole network into two subnets; main traditional net and a supportive net. The first deals with the required output of trained patterns with predefined settings, while the second tolerates output generation dynamically with tuning capability for any newly applied input. This tuning comes in the form of an adjustment to the threshold values. Two levels of supportive net were studied; one implements an extended additional layer with adjustable neuronal threshold setting mechanism, while the second implements an auxiliary net with traditional architecture performs dynamic adjustment to the threshold value of the main net that is constructed in dual-layer architecture. Experiment results and analysis of the proposed designs have given quite satisfactory conducts. The supportive layer approach achieved over 90% recognition rate, while the multiple network technique shows more effective and acceptable level of recognition. However, this is achieved at the price of network complexity and computation time. Recognition generalization may be also improved by accommodating capabilities involving all the innate structures in conjugation with Intelligence abilities with the needs of further advanced learning phases.
Keywords: Classification, Recognition, Neural Networks, Pattern Recognition, Generalization.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16151367 View-Point Insensitive Human Pose Recognition using Neural Network
Authors: Sanghyeok Oh, Yunli Lee, Kwangjin Hong, Kirak Kim, Keechul Jung
Abstract:
This paper proposes view-point insensitive human pose recognition system using neural network. Recognition system consists of silhouette image capturing module, data driven database, and neural network. The advantages of our system are first, it is possible to capture multiple view-point silhouette images of 3D human model automatically. This automatic capture module is helpful to reduce time consuming task of database construction. Second, we develop huge feature database to offer view-point insensitivity at pose recognition. Third, we use neural network to recognize human pose from multiple-view because every pose from each model have similar feature patterns, even though each model has different appearance and view-point. To construct database, we need to create 3D human model using 3D manipulate tools. Contour shape is used to convert silhouette image to feature vector of 12 degree. This extraction task is processed semi-automatically, which benefits in that capturing images and converting to silhouette images from the real capturing environment is needless. We demonstrate the effectiveness of our approach with experiments on virtual environment.Keywords: Computer vision, neural network, pose recognition, view-point insensitive.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13161366 Pre-Analysis of Printed Circuit Boards Based On Multispectral Imaging for Vision Based Recognition of Electronics Waste
Authors: Florian Kleber, Martin Kampel
Abstract:
The increasing demand of gallium, indium and rare-earth elements for the production of electronics, e.g. solid state-lighting, photovoltaics, integrated circuits, and liquid crystal displays, will exceed the world-wide supply according to current forecasts. Recycling systems to reclaim these materials are not yet in place, which challenges the sustainability of these technologies. This paper proposes a multispectral imaging system as a basis for a vision based recognition system for valuable components of electronics waste. Multispectral images intend to enhance the contrast of images of printed circuit boards (single components, as well as labels) for further analysis, such as optical character recognition and entire printed circuit board recognition. The results show, that a higher contrast is achieved in the near infrared compared to ultraviolett and visible light.
Keywords: Electronic Waste, Recycling, Multispectral Imaging, Printed Circuit Boards, Rare-Earth Elements.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 26641365 Two Concurrent Convolution Neural Networks TC*CNN Model for Face Recognition Using Edge
Authors: T. Alghamdi, G. Alaghband
Abstract:
In this paper we develop a model that couples Two Concurrent Convolution Neural Network with different filters (TC*CNN) for face recognition and compare its performance to an existing sequential CNN (base model). We also test and compare the quality and performance of the models on three datasets with various levels of complexity (easy, moderate, and difficult) and show that for the most complex datasets, edges will produce the most accurate and efficient results. We further show that in such cases while Support Vector Machine (SVM) models are fast, they do not produce accurate results.
Keywords: Convolution neural network, edges, face recognition, support vector machine.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7101364 Turkic - Indian Lexical Parallels in the Framework of the Nostratic Language's Macrofamily
Authors: Z. E. Iskakova, B. S. Bokuleva, B. N. Zhubatova, U. T. Alzhanbayeva
Abstract:
From ancient times Turkic languages have been in contact with numerous representatives of different language families. The article discusses the Turkic - Indian language contact and were shown promise and necessity of this trend for the Turkic linguistics, were given Turkic - Indian lexical parallels in the framework of the nostratic language's macro family. The research work has done on the base of lexical parallels (LP) -of Turkic (which belong to the Altaic family of languages) and Indian (including Dravidian and Indo-Aryan languages).Keywords: Language communications, lexical parallels, Nostratic languages, Turkic languages.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22111363 Effective Stacking of Deep Neural Models for Automated Object Recognition in Retail Stores
Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay
Abstract:
Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.
Keywords: Retail stores, Faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5521362 Face Detection using Gabor Wavelets and Neural Networks
Authors: Hossein Sahoolizadeh, Davood Sarikhanimoghadam, Hamid Dehghani
Abstract:
This paper proposes new hybrid approaches for face recognition. Gabor wavelets representation of face images is an effective approach for both facial action recognition and face identification. Perform dimensionality reduction and linear discriminate analysis on the down sampled Gabor wavelet faces can increase the discriminate ability. Nearest feature space is extended to various similarity measures. In our experiments, proposed Gabor wavelet faces combined with extended neural net feature space classifier shows very good performance, which can achieve 93 % maximum correct recognition rate on ORL data set without any preprocessing step.Keywords: Face detection, Neural Networks, Multi-layer Perceptron, Gabor wavelets.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21481361 A Study on Algorithm Fusion for Recognition and Tracking of Moving Robot
Authors: Jungho Choi, Youngwan Cho
Abstract:
This paper presents an algorithm for the recognition and tracking of moving objects, 1/10 scale model car is used to verify performance of the algorithm. Presented algorithm for the recognition and tracking of moving objects in the paper is as follows. SURF algorithm is merged with Lucas-Kanade algorithm. SURF algorithm has strong performance on contrast, size, rotation changes and it recognizes objects but it is slow due to many computational complexities. Processing speed of Lucas-Kanade algorithm is fast but the recognition of objects is impossible. Its optical flow compares the previous and current frames so that can track the movement of a pixel. The fusion algorithm is created in order to solve problems which occurred using the Kalman Filter to estimate the position and the accumulated error compensation algorithm was implemented. Kalman filter is used to create presented algorithm to complement problems that is occurred when fusion two algorithms. Kalman filter is used to estimate next location, compensate for the accumulated error. The resolution of the camera (Vision Sensor) is fixed to be 640x480. To verify the performance of the fusion algorithm, test is compared to SURF algorithm under three situations, driving straight, curve, and recognizing cars behind the obstacles. Situation similar to the actual is possible using a model vehicle. Proposed fusion algorithm showed superior performance and accuracy than the existing object recognition and tracking algorithms. We will improve the performance of the algorithm, so that you can experiment with the images of the actual road environment.Keywords: SURF, Optical Flow Lucas-Kanade, Kalman Filter, object recognition, object tracking.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22781360 On a Theoretical Framework for Language Learning Apps Evaluation
Authors: Juan Manuel Real-Espinosa
Abstract:
This paper addresses the first step to evaluate language learning apps: what theoretical framework to adopt when designing the app evaluation framework. The answer is not just one, since there are several options that could be proposed. However, the question to be clarified is to what extent the learning design of apps is based on a specific learning approach, or on the contrary, on a fusion of elements from several theoretical proposals and paradigms, such as m-learning, Mobile Assisted Language Learning and a number of theories about language acquisition. The present study suggests that the reality is closer to the second assumption. This implies that the theoretical framework against which the learning design of the apps should be evaluated, must also be a hybrid theoretical framework, which integrates evaluation criteria from the different theories involved in language learning through mobile applications.
Keywords: Action-oriented approach, apps evaluation, mobile-assisted language learning, post-method pedagogy.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5321359 Object Detection Based on Plane Segmentation and Features Matching for a Service Robot
Authors: António J. R. Neves, Rui Garcia, Paulo Dias, Alina Trifan
Abstract:
With the aging of the world population and the continuous growth in technology, service robots are more and more explored nowadays as alternatives to healthcare givers or personal assistants for the elderly or disabled people. Any service robot should be capable of interacting with the human companion, receive commands, navigate through the environment, either known or unknown, and recognize objects. This paper proposes an approach for object recognition based on the use of depth information and color images for a service robot. We present a study on two of the most used methods for object detection, where 3D data is used to detect the position of objects to classify that are found on horizontal surfaces. Since most of the objects of interest accessible for service robots are on these surfaces, the proposed 3D segmentation reduces the processing time and simplifies the scene for object recognition. The first approach for object recognition is based on color histograms, while the second is based on the use of the SIFT and SURF feature descriptors. We present comparative experimental results obtained with a real service robot.Keywords: Service Robot, Object Recognition, 3D Sensors, Plane Segmentation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16571358 Greek Compounds: A Challenging Case for the Parsing Techniques of PC-KIMMO v.2
Authors: Angela Ralli, Eleni Galiotou
Abstract:
In this paper we describe the recognition process of Greek compound words using the PC-KIMMO software. We try to show certain limitations of the system with respect to the principles of compound formation in Greek. Moreover, we discuss the computational processing of phenomena such as stress and syllabification which are indispensable for the analysis of such constructions and we try to propose linguistically-acceptable solutions within the particular system.
Keywords: Morpho-phonological parsing, compound words, two-level morphology, natural language processing.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15921357 Interfacing C and TMS320C6713 Assembly Language (Part-I)
Authors: Abdullah A. Wardak
Abstract:
This paper describes an interfacing of C and the TMS320C6713 assembly language which is crucially important for many real-time applications. Similarly, interfacing of C with the assembly language of a conventional microprocessor such as MC68000 is presented for comparison. However, it should be noted that the way the C compiler passes arguments among various functions in the TMS320C6713-based environment is totally different from the way the C compiler passes arguments in a conventional microprocessor such as MC68000. Therefore, it is very important for a user of the TMS320C6713-based system to properly understand and follow the register conventions when interfacing C with the TMS320C6713 assembly language subroutine. It should be also noted that in some cases (examples 6-9) the endian-mode of the board needs to be taken into consideration. In this paper, one method is presented in great detail. Other methods will be presented in the future.Keywords: Assembly language, high level language, interfacing, stack, arguments.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25051356 Choosing an Ontology Language
Authors: Anna V. Zhdanova, Uwe Keller
Abstract:
We summarize information that facilitates choosing an ontology language for knowledge intensive applications. This paper is a short version of the ontology language state-of-the-art and evolution analysis carried out for choosing an ontology language in the IST Esperonto project. At first, we analyze changes and evolution that took place in the filed of Semantic Web languages during the last years, in particular, around the ontology languages of the RDF/S and OWL family. Second, we present current trends in development of Semantic Web languages, in particular, rule support extensions for Semantic Web languages and emerging ontology languages such as WSMO languages.Keywords: OWL, RDF/S, Semantic Web Languages, WSML
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1737