Search results for: image features

Authors: Abraham Terán Salcedo, Didier Samayoa Ochoa

Abstract:

This work presents a numerical implementation of a method for estimating the box-counting dimension of self-avoiding curves on a planar space, fractal objects captured on digital images; this method is named fractioning estimator. Classical methods of digital image processing, such as noise filtering, contrast manipulation, and thresholding, among others, are used in order to obtain binary images that are suitable for performing the necessary computations of the fractioning estimator. A user interface is developed for performing the image processing operations and testing the fractioning estimator on different captured images of real-life fractal objects. To analyze the results, the estimations obtained through the fractioning estimator are compared to the results obtained through other methods that are already implemented on different available software for computing and estimating the box-counting dimension.

Keywords: box-counting, digital image processing, fractal dimension, numerical method

Procedia PDF Downloads 75

Authors: Kumar Dron Shrivastav, Ankan Mukherjee Das, Arti Taneja, Harpreet Singh, Priya Ranjan, Rajiv Janardhanan

Abstract:

Cervical cancer is one of the most common cancer among women worldwide which can be cured if detected early. Manual pathology which is typically utilized at present has many limitations. The current gold standard for cervical cancer diagnosis is exhaustive and time-consuming because it relies heavily on the subjective knowledge of the oncopathologists which leads to mis-diagnosis and missed diagnosis resulting false negative and false positive. To reduce time and complexities associated with early diagnosis, we require an interactive diagnostic tool for early detection particularly in developing countries where cervical cancer incidence and related mortality is high. Incorporation of digital pathology in place of manual pathology for cervical cancer screening and diagnosis can increase the precision and strongly reduce the chances of error in a time-specific manner. Thus, we propose a robust and interactive cervical cancer image analysis and diagnostic tool, which can categorically process both histopatholgical and cytopathological images to identify abnormal cells in the least amount of time and settings with minimum resources. Furthermore, incorporation of a set of specific parameters that are typically referred to for identification of abnormal cells with the help of open source software -’R’ is one of the major highlights of the tool. The software has the ability to automatically identify and quantify the morphological features, color intensity, sensitivity and other parameters digitally to differentiate abnormal from normal cells, which may improve and accelerate screening and early diagnosis, ultimately leading to timely treatment of cervical cancer.

Keywords: cervical cancer, early detection, digital Pathology, screening

Procedia PDF Downloads 167

Authors: Ching-Yi Huang, Pi-Fen Cheng, Hui-Zhu Chen, Shi Ting Huang, Heng-Hua Wang

Abstract:

This is a case of oral cancer after extensive resection and modified right lateral neck lymph node dissection followed by reconstruction with a skin flap. The nursing period lasted From September 25 to October 3, 2017, through observation, interview, physical assessment, and medical record review, the author identified the following nursing problems: acute pain, impaired oral mucous membrane, and body image change. During the nursing period, the author provided individual and overall nursing care and established mutual trust through the use of empathy. Author listened and eased the patient's physical indisposition, such as wound pain, we use medications and acupuncture massage to relieve pain. However, for oral mucosa change caused by surgery, provide continuous and complete oral care and oral exercise training to improve oral mucosal healing and restore swallowing function. In the body-image changes, guided him to express his feeling after the body-image change, and enhanced support and from the family, and encouraged him to attend head and neck cancer survivor alliance which allowed the patient to accept the altered body image and reaffirm self-worth. Hopefully, through sharing this nursing experience will help to the nursing care quality of nursing care for oral cancer patients after extensive resection and modified right lateral neck lymph node dissection followed by reconstruction with a skin flap.

Keywords: oral cancer, acute pain, impaired oral mucous membrane, body image change

Procedia PDF Downloads 173

Authors: Lamees Nasser, Yago Diez, Robert Martí, Joan Martí, Ibrahim Sadek

Abstract:

Automated 3D breast ultrasound (ABUS) screening is a novel modality in medical imaging because of its common characteristics shared with other ultrasound modalities in addition to the three orthogonal planes (i.e., axial, sagittal, and coronal) that are useful in analysis of tumors. In the literature, few automatic approaches exist for typical tasks such as segmentation or registration. In this work, we deal with two problems concerning ABUS images: nipple and rib detection. Nipple and ribs are the most visible and salient features in ABUS images. Determining the nipple position plays a key role in some applications for example evaluation of registration results or lesion follow-up. We present a nipple detection algorithm based on color and shape of the nipple, besides an automatic approach to detect the ribs. In point of fact, rib detection is considered as one of the main stages in chest wall segmentation. This approach consists of four steps. First, images are normalized in order to minimize the intensity variability for a given set of regions within the same image or a set of images. Second, the normalized images are smoothed by using anisotropic diffusion filter. Next, the ribs are detected in each slice by analyzing the eigenvalues of the 3D Hessian matrix. Finally, a breast mask and a probability map of regions detected as ribs are used to remove false positives (FP). Qualitative and quantitative evaluation obtained from a total of 22 cases is performed. For all cases, the average and standard deviation of the root mean square error (RMSE) between manually annotated points placed on the rib surface and detected points on rib borders are 15.1188 mm and 14.7184 mm respectively.

Keywords: Automated 3D Breast Ultrasound, Eigenvalues of Hessian matrix, Nipple detection, Rib detection

Procedia PDF Downloads 325

Authors: Hamza A. Al-Sewadi, Akram N. A. Aldakari

Abstract:

Copyright protection and ownership proof of digital multimedia are achieved nowadays by digital watermarking techniques. A text watermarking algorithm for protecting the property rights and ownership judgment of color images is proposed in this paper. Embedding is achieved by inserting texts elements randomly into the color image as noise. The YIQ image processing model is found to be faster than other image processing methods, and hence, it is adopted for the embedding process. An optional choice of encrypting the text watermark before embedding is also suggested (in case required by some applications), where, the text can is encrypted using any enciphering technique adding more difficulty to hackers. Experiments resulted in embedding speed improvement of more than double the speed of other considered systems (such as least significant bit method, and separate color code methods), and a fairly acceptable level of peak signal to noise ratio (PSNR) with low mean square error values for watermarking purposes.

Keywords: steganography, watermarking, time complexity measurements, private keys

Procedia PDF Downloads 134

Authors: Syeda Shawana Mahasan, Muhammad Farooq Akhtar

Abstract:

The objective of this study is to analyze the influence of the green marketing mix strategy and corporate social responsibility (CSR) on the performance of an organization, taking into account the mediating effect of corporate image. The impact of frugal innovation and corporate activism is being examined. The data was gathered from executives at various levels of management, including top, middle, and lower-level managers, from a total of 550 manufacturing enterprises of different sizes, ranging from small to medium to large. The collected replies are processed and analyzed using SMART PLS version 4.0.0.0. The application of PLS-SEM demonstrates that the green marketing mix strategy and corporate social responsibility have a significant impact on organizational performance. Therefore, it is imperative for organizations to effectively adopt environmentally sustainable and socially conscious methods within their operations. The results indicate that the corporate image has a key role in mediating the relationship between the green marketing mix strategy, corporate social responsibility, and organizational performance. This demonstrates the imperative for organizations to actively enhance their favorable reputation among stakeholders. The combination of frugal innovation and corporate activism enhances the connection between corporate image and organizational performance. The current study assists managers in recognizing the significance of these particular constructs in maintaining the long-term performance of the organization.

Keywords: green marketing mix strategy, CSR, corporate image, organizational performance, frugal innovation, corporate activism

Procedia PDF Downloads 23

Authors: Kumar Kanudkuri, A. Sandhya

Abstract:

Typically, in a MRI clinical setting, there are several protocols run, each indicated for a specific anatomy and disease condition. However, these protocols or parameters within them can change over time due to changes to the recommendations by the physician groups or updates in the software or by the availability of new technologies. Most of the time, the changes are performed by the MRI technologist to account for either time, coverage, physiological, or Specific Absorbtion Rate (SAR ) reasons. However, giving properly guidelines to MRI technologist is important so that they do not change the parameters that negatively impact the image quality. Typically a standard American College of Radiology (ACR) MRI phantom is used for Quality Control (QC) in order to guarantee that the primary objectives of MRI are met. The visual evaluation of quality depends on the operator/reviewer and might change amongst operators as well as for the same operator at various times. Therefore, overcoming these constraints is essential for a more impartial evaluation of quality. This makes quantitative estimation of image quality (IQ) metrics for MRI quality control is very important. So in order to solve this problem, we proposed that there is a need for a robust, open-source, and automated MRI image control tool. The Designed and developed an automatic analysis tool for measuring MRI image quality (IQ) metrics like Signal to Noise Ratio (SNR), Signal to Noise Ratio Uniformity (SNRU), Visual Information Fidelity (VIF), Feature Similarity (FSIM), Gray level co-occurrence matrix (GLCM), slice thickness accuracy, slice position accuracy, High contrast spatial resolution) provided good accuracy assessment. A standardized quality report has generated that incorporates metrics that impact diagnostic quality.

Keywords: ACR MRI phantom, MRI image quality metrics, SNRU, VIF, FSIM, GLCM, slice thickness accuracy, slice position accuracy

Procedia PDF Downloads 153

Authors: Zin Mar Lwin

Abstract:

Brain Computer Interface (BCI) Systems have developed for people who suffer from severe motor disabilities and challenging to communicate with their environment. BCI allows them for communication by a non-muscular way. For communication between human and computer, BCI uses a type of signal called Electroencephalogram (EEG) signal which is recorded from the human„s brain by means of an electrode. The electroencephalogram (EEG) signal is an important information source for knowing brain processes for the non-invasive BCI. Translating human‟s thought, it needs to classify acquired EEG signal accurately. This paper proposed a typical EEG signal classification system which experiments the Dataset from “Purdue University.” Independent Component Analysis (ICA) method via EEGLab Tools for removing artifacts which are caused by eye blinks. For features extraction, the Time and Frequency features of non-stationary EEG signals are extracted by Matching Pursuit (MP) algorithm. The classification of one of five mental tasks is performed by Multi_Class Support Vector Machine (SVM). For SVMs, the comparisons have been carried out for both 1-against-1 and 1-against-all methods.

Keywords: BCI, EEG, ICA, SVM

Procedia PDF Downloads 267

Authors: Bushra Zafar, Usman Qamar

Abstract:

Large data sample size and dimensions render the effectiveness of conventional data mining methodologies. A data mining technique are important tools for collection of knowledgeable information from variety of databases and provides supervised learning in the form of classification to design models to describe vital data classes while structure of the classifier is based on class attribute. Classification efficiency and accuracy are often influenced to great extent by noisy and undesirable features in real application data sets. The inherent natures of data set greatly masks its quality analysis and leave us with quite few practical approaches to use. To our knowledge first time, we present a new approach for investigation of structure and quality of datasets by providing a targeted analysis of localization of noisy and irrelevant features of data sets. Machine learning is based primarily on feature selection as pre-processing step which offers us to select few features from number of features as a subset by reducing the space according to certain evaluation criterion. The primary objective of this study is to trim down the scope of the given data sample by searching a small set of important features which may results into good classification performance. For this purpose, a heuristic for wrapper-based feature selection using genetic algorithm and for discriminative feature selection an external classifier are used. Selection of feature based on its number of occurrence in the chosen chromosomes. Sample dataset has been used to demonstrate proposed idea effectively. A proposed method has improved average accuracy of different datasets is about 95%. Experimental results illustrate that proposed algorithm increases the accuracy of prediction of different diseases.

Keywords: data mining, generic algorithm, KNN algorithms, wrapper based feature selection

Procedia PDF Downloads 309

Authors: Wafeek Mohamed Ibrahim Mohamed

Abstract:

In the era of globalization and openness informational. Anyone who thinks about innovation in the earth population in Islam in our contemporary reality, he will find that it is not destined to its civilized extension to last. The purpose of the research is a trial to reach a realistic vision for creative, innovative and intellectual thought for the earth population in Islam as an instrument to Confrontation and observe the changes that have affected in the architecture of the land during different eras. Through knowing the controls of the ruling legitimacy(that served as definitions and laws which formulate its features) and using customs, traditions, and conventions as a telescope for the earth population in Islam, It explained the impact of them on features of creative formation for the architecture of the land in our contemporary reality. The study shows a modern vision to identify innovation in the earth population in Islam. As well as reformulating its mental image and monitoring its changes in Islamic heritage cities. This will be done through a two main branches: firstly, set forth a theory represented in studying creative concepts which formulate the population of the earth in Islam. Such as initiative and responsibility for reviving the dead land, the lane [alley] as formation unit and social solidarity,… Etc.. The second branch is preparing a practical, critical vision for innovative conceptual thought for the architecture of the land of Islam, through studying the development of a traditional Islamic city., The conceptual thought of making the birth festival ["Al-Refaee"] and its emulation for governing roles in the traditional city building. The research concludes The necessity of forming the suggested a creative vision for identifying how to re-form the conceptual for our contemporary population of the earth. It poses an important question which is how to return to creativity in the architecture of the land of Islam in our built environments.

Keywords: innovation and creation, architecture, the land in Islam, criticism of design

Procedia PDF Downloads 452

Authors: R. K. Chaurasiya, N. D. Londhe, S. Ghosh

Abstract:

The study of the electrical signals produced by neural activities of human brain is called Electroencephalography. In this paper, we propose an automatic and efficient EEG signal classification approach. The proposed approach is used to classify the EEG signal into two classes: epileptic seizure or not. In the proposed approach, we start with extracting the features by applying Discrete Wavelet Transform (DWT) in order to decompose the EEG signals into sub-bands. These features, extracted from details and approximation coefficients of DWT sub-bands, are used as input to Principal Component Analysis (PCA). The classification is based on reducing the feature dimension using PCA and deriving the support-vectors using Support Vector Machine (SVM). The experimental are performed on real and standard dataset. A very high level of classification accuracy is obtained in the result of classification.

Keywords: discrete wavelet transform, electroencephalogram, pattern recognition, principal component analysis, support vector machine

Procedia PDF Downloads 624

Authors: Hassan Sabo

Abstract:

Language is a system of conventionally spoken, manual and written symbols by human beings that members of a certain social group and participants in its culture express themselves. Communication, expression of identity and imaginative expression are among the functions of language. Dialect is a form of language, or a regional variety of language that is spoken in a particular geographical setting by a particular group of people. Hausa is one of the major languages in Africa, in terms of large number of people for whom it is the first language. Hausa is one of the western Chadic groups of languages. It constitutes one of the five or six branches of Afro-Asiatic family. The predominant Hausa speakers are in Nigeria and they live in different geographical locations which resulted to variety of dialects within the Hausa language apart of the standard Hausa language, the Hausa language has a variety of dialect that distinguish from one another by such features as phonology, grammar and vocabulary. This study intends to examine such features that serve as means of identification among Hausa speakers who are set off from others, geographically or socially.

Keywords: dialect, features, geographical location, Hausa language

Procedia PDF Downloads 184

Authors: Rishabh Beri, Sahil Shah

Abstract:

We have applied a range of filters and processing in order to extract out the various features of the football game, like the field lines of a football field. Another important aspect was the detection of the players in the field and tagging them according to their teams distinguished by their jersey colours. This extracted information combined about the players and field helped us to create a virtual field that consists of the playing field and the players mapped to their locations in it.

Keywords: Detect, Football, Players, Virtual

Procedia PDF Downloads 318

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinie

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. That is why the need for automation of this task is urgent. A lot of studies have investigated the subject using different standard image processing descriptors and sometimes hand-crafted ones.In this work, we make a comparative study between classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN, Autoencoders, Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches

Keywords: pollens identification, features extraction, pollens classification, automated palynology

Procedia PDF Downloads 124

Authors: Timothy E. Frank, Josh R. Aldred, Sophie B. Boulware, Michelle K. Cabonce, Justin H. White

Abstract:

Materials degrade at different rates in different environments depending on factors such as temperature, aridity, salinity, and solar radiation. Therefore, predicting asset longevity depends, in part, on the environmental conditions to which the asset is exposed. Heating, ventilation, and air conditioning (HVAC) systems are critical to building operations yet are responsible for a significant proportion of their energy consumption. HVAC energy use increases substantially with slight operational inefficiencies. Understanding the environmental influences on HVAC degradation in detail will inform maintenance schedules and capital investment, reduce energy use, and increase lifecycle management efficiency. HVAC inspection records spanning 14 years from 21 locations across the United States were compiled and associated with the climate conditions to which they were exposed. Three environmental features were explored in this study: average high temperature, average low temperature, and annual precipitation, as well as four non-environmental features. Initial insights showed no correlations between individual features and the rate of HVAC component degradation. Using neighborhood component analysis, however, the most critical features related to degradation were identified. Two models were considered, and results varied between them. However, longitude and latitude emerged as potentially the best predictors of average HVAC component degradation. Further research is needed to evaluate additional environmental features, increase the resolution of the environmental data, and develop more robust models to achieve more conclusive results.

Keywords: climate, degradation, HVAC, neighborhood component analysis

Procedia PDF Downloads 415

Authors: Bin Liu

Abstract:

Protein remote homology detection and fold recognition are two most important tasks in protein sequence analysis, which is critical for protein structure and function studies. In this study, we combined the profile-based features with various string kernels, and constructed several computational predictors for protein remote homology detection and fold recognition. Experimental results on two widely used benchmark datasets showed that these methods outperformed the competing methods, indicating that these predictors are useful computational tools for protein sequence analysis. By analyzing the discriminative features of the training models, some interesting patterns were discovered, reflecting the characteristics of protein superfamilies and folds, which are important for the researchers who are interested in finding the patterns of protein folds.

Keywords: protein remote homology detection, protein fold recognition, profile-based features, Support Vector Machines (SVMs)

Procedia PDF Downloads 151

Authors: Mohammad Esmaeilpour

Abstract:

One of the important open problems in the field of medical image processing is detection and quantification of small changes. In this poster, we try to investigate that, how the algebraic decomposition techniques can be used for semiautomatically detecting and quantifying subtle changes in Magnetic Resonance (MR) neuroimaging volumes. We mostly focus on the low-rank values of the matrices achieved from decomposing MR image pairs during a period of time. Besides, a skillful neuroradiologist will help the algorithm to distinguish between noises and small changes.

Keywords: magnetic resonance neuroimaging, subtle change detection and quantification, algebraic decomposition, basis functions

Procedia PDF Downloads 462

Authors: Eliza. E. Camaso, Guiller. B. Damian, Miguelito. F. Isip, Ronaldo T. Alberto

Abstract:

Land-cover maps were important for many scientific, ecological and land management purposes and during the last decades, rapid decrease of soil fertility was observed to be due to land use practices such as rice cultivation. High-precision land-cover maps are not yet available in the area which is important in an economy management. To assure   accurate mapping of land cover to provide information, remote sensing is a very suitable tool to carry out this task and automatic land use and cover detection. The study did not only provide high precision land cover maps but it also provides estimates of rice production area that had undergone chemical degradation due to fertility decline. Land-cover were delineated and classified into pre-defined classes to achieve proper detection features. After generation of Land-cover map, of high intensity of rice cultivation, soil fertility degradation assessment in rice production area due to fertility decline was created to assess the impact of soils used in agricultural production. Using Simple spatial analysis functions and ArcGIS, the Land-cover map of Municipality of Quezon in Nueva Ecija, Philippines was overlaid to the fertility decline maps from Land Degradation Assessment Philippines- Bureau of Soils and Water Management (LADA-Philippines-BSWM) to determine the area of rice crops that were most likely where nitrogen, phosphorus, zinc and sulfur deficiencies were induced by high dosage of urea and imbalance N:P fertilization. The result found out that 80.00 % of fallow and 99.81% of rice production area has high soil fertility decline.

Keywords: aerial image, landcover, LiDAR, soil fertility degradation

Procedia PDF Downloads 246

Authors: Mohammad A. U. Khan, Tariq M. Khan, Yinan Kong

Abstract:

Fingerprint image enhancement is one of the most important step in an automatic fingerprint identification recognition (AFIS) system which directly affects the overall efficiency of AFIS. The conventional fingerprint enhancement like Gabor and Anisotropic filters do fill the gaps in ridge lines but they fail to tackle scar lines. To deal with this problem we are proposing a method for enhancing the ridges and valleys with scar so that true minutia points can be extracted with accuracy. Our results have shown an improved performance in terms of enhancement.

Keywords: fingerprint image enhancement, removing noise, coherence, enhanced diffusion

Procedia PDF Downloads 504

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 116

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular diseases caused by hypertension are extremely threatening to human health, and early diagnosis of hypertension can save a large number of lives. Traditional hypertension detection methods require special equipment and are difficult to detect continuous blood pressure changes. In this regard, this paper first analyzes the principle of heart rate variability (HRV) and introduces sliding window and power spectral density (PSD) to analyze the time domain features and frequency domain features of HRV, and secondly, designs an HRV-based hypertension prediction network by combining Resnet, attention mechanism, and multilayer perceptron, which extracts the frequency domain through the improved ResNet18 features through a modified ResNet18, its fusion with time-domain features through an attention mechanism, and the auxiliary prediction of hypertension through a multilayer perceptron. Finally, the network was trained and tested using the publicly available SHAREE dataset on PhysioNet, and the test results showed that this network achieved 92.06% prediction accuracy for hypertension and outperformed K Near Neighbor(KNN), Bayes, Logistic, and traditional Convolutional Neural Network(CNN) models in prediction performance.

Keywords: feature extraction, heart rate variability, hypertension, residual networks

Procedia PDF Downloads 89

Authors: Thomas Louis, Irina Primac, Florent Morfoisse, Tania Durre, Silvia Blacher, Agnes Noel

Abstract:

In vitro and in vivo lymphangiogenesis assays are essential for the identification of potential lymphangiogenic agents and the screening of pharmacological inhibitors. In the present study, we analyse three biological models: in vitro lymphatic endothelial cell spheroids, in vivo ear sponge assay, and in vivo lymph node colonisation by tumour cells. These assays provide suitable 3D models to test pro- and anti-lymphangiogenic factors or drugs. 3D images were acquired by confocal laser scanning and light sheet fluorescence microscopy. Virtual scan microscopy followed by 3D reconstruction by image aligning methods was also used to obtain 3D images of whole large sponge and ganglion samples. 3D reconstruction, image segmentation, skeletonisation, and other image processing algorithms are described. Fixed and time-lapse imaging techniques are used to analyse lymphatic endothelial cell spheroids behaviour. The study of cell spatial distribution in spheroid models enables to detect interactions between cells and to identify invasion hierarchy and guidance patterns. Global measurements such as volume, length, and density of lymphatic vessels are measured in both in vivo models. Branching density and tortuosity evaluation are also proposed to determine structure complexity. Those properties combined with vessel spatial distribution are evaluated in order to determine lymphangiogenesis extent. Lymphatic endothelial cell invasion and lymphangiogenesis were evaluated under various experimental conditions. The comparison of these conditions enables to identify lymphangiogenic agents and to better comprehend their roles in the lymphangiogenesis process. The proposed methodology is validated by its application on the three presented models.

Keywords: 3D image segmentation, 3D image skeletonisation, cell invasion, confocal microscopy, ear sponges, light sheet microscopy, lymph nodes, lymphangiogenesis, spheroids

Procedia PDF Downloads 363

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 80

Authors: Natascha C. D'Amico, Enzo Grossi, Giovanni Valbusa, Ala Malasevschi, Gianpiero Cardone, Sergio Papa

Abstract:

Purpose: To characterize, through a radiomic approach, the nature of areas classified PI-RADS (Prostate Imaging Reporting and Data System) 3/5, recognized in multiparametric prostate magnetic resonance with T2-weighted (T2w), diffusion and perfusion sequences with paramagnetic contrast. Methods and Materials: 24 cases undergoing multiparametric prostate MR and biopsy were admitted to this pilot study. Clinical outcome of the PI-RADS 3/5 was found through biopsy, finding 8 malignant tumours. The analysed images were acquired with a Philips achieva 1.5T machine with a CE- T2-weighted sequence in the axial plane. Semi-automatic tumour segmentation was carried out on MR images using 3DSlicer image analysis software. 45 shape-based, intensity-based and texture-based features were extracted and represented the input for preprocessing. An evolutionary algorithm (a TWIST system based on KNN algorithm) was used to subdivide the dataset into training and testing set and select features yielding the maximal amount of information. After this pre-processing 20 input variables were selected and different machine learning systems were used to develop a predictive model based on a training testing crossover procedure. Results: The best machine learning system (three-layers feed-forward neural network) obtained a global accuracy of 90% ( 80 % sensitivity and 100% specificity ) with a ROC of 0.82. Conclusion: Machine learning systems coupled with radiomics show a promising potential in distinguishing benign from malign tumours in PI-RADS 3/5 areas.

Keywords: machine learning, MR prostate, PI-Rads 3, radiomics

Procedia PDF Downloads 179

Authors: Nengi A. H. Ejiobih

Abstract:

Conflict is one of the defining features of human societies. Often, the use or misuse of language in interaction is the genesis of conflict. As such, it is expected that when people use language they do so in socially determined ways and with almost predictable social effects. The objective of this paper was to examine the interest at work as manifested in language choice and collocations in conflict discourse. It also scrutinized the implications of linguistic features in conflict discourse as it concerns ideology and power relations in political discourse in Nigeria. The methodology used for this paper is an approach from Critical discourse analysis because of its multidisciplinary model of analysis, linguistic features and its implications were analysed. The datum used is a text from the Sunday Sun Newspaper in Nigeria, West Africa titled Akunyili Memo: State of the Nation. Some of the findings include; different ideologies are inherent in conflict discourse, there is the presence of power relations being produced, exercised, maintained and produced throughout the discourse and the use of pronouns in conflict discourse is valuable because it is used to initiate and maintain relationships in social context. This paper has provided evidence that, taking into consideration the nature of the social actions and the way these activities are translated into languages, the meanings people convey by their words are identified by their immediate social, political and historical conditions.

Keywords: conflicts, discourse, language, linguistic features, social context

Procedia PDF Downloads 464

Authors: Nabilah Ibrahim, Khaliza Musa

Abstract:

The increment thickness of intima-media thickness (IMT) which involves the changes of diameter of the carotid artery is one of the early symptoms of the atherosclerosis lesion. The manual measurement of arterial diameter is time consuming and lack of reproducibility. Thus, this study reports the automatic approach to find the arterial diameter behavior for different gender, and body mass index (BMI) categories, focus on tracked region. BMI category is divided into underweight, normal, and overweight categories. Canny edge detection is employed to the B-mode image to extract the important information to be deal as the carotid wall boundary. The result shows the significant difference of arterial diameter between male and female groups which is 2.5% difference. In addition, the significant result of differences of arterial diameter for BMI category is the decreasing of arterial diameter proportional to the BMI.

Keywords: B-mode Ultrasound Image, carotid artery diameter, canny edge detection, body mass index

Procedia PDF Downloads 434

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 186

Authors: Lakshay Kharbanda, Aabhas Chauhan

Abstract:

In this paper, an application of Normalized Compression Distance (NCD) to detect notable scene alterations occurring in videos is presented. Several research groups have been developing methods to perform image classification using NCD, a computable approximation to Normalized Information Distance (NID) by studying the degree of similarity in images. The timeframes where significant aberrations between the frames of a video have occurred have been identified by obtaining a threshold NCD value, using two compressors: LZMA and BZIP2 and defining scene alterations using Pixel Difference Percentage metrics.

Keywords: image compression, Kolmogorov complexity, normalized compression distance, root mean square error

Procedia PDF Downloads 333

Authors: M. Ibrahim Ali, M. El Dawi, M. A. Mohamed Ali

Abstract:

In this study, the use of magnetic gradient survey, and the geoelectrical ground methods used together to explore archaeological features in Nuri’s pyramids area. Research methods used and the procedures and methodologies have taken full right during the study. The magnetic survey method was used to search for archaeological features using (Geoscan Fluxgate Gradiometer (FM36)). The study area was divided into a number of squares (networks) exactly equal (20 * 20 meters). These squares were collected at the end of the study to give a major network for each region. Networks also divided to take the sample using nets typically equal to (0.25 * 0.50 meter), in order to give a more specific archaeological features with some small bipolar anomalies that caused by buildings built from fired bricks. This definition is important to monitor many of the archaeological features such as rooms and others. This main network gives us an integrated map displayed for easy presentation, and it also allows for all the operations required using (Geoscan Geoplot software). The parallel traverse is the main way to take readings of the magnetic survey, to get out the high-quality data. The study area is very rich in old buildings that vary from small to very large. According to the proportion of the sand dunes and the loose soil, most of these buildings are not visible from the surface. Because of the proportion of the sandy dry soil, there is no connection between the ground surface and the electrodes. We tried to get electrical readings by adding salty water to the soil, but, unfortunately, we failed to confirm the magnetic readings with electrical readings as previously planned.

Keywords: archaeological features, independent grids, magnetic gradient, Nuri pyramid

Procedia PDF Downloads 474

Authors: Mayank Raj, V. G. Narendra

Abstract:

Ever since the DARPA challenge on autonomous vehicles in 2005, there has been a lot of buzz about ‘Autonomous Vehicles’ amongst the major tech giants such as Google, Uber, and Tesla. Numerous approaches have been adopted to solve this problem, which can have a long-lasting impact on mankind. In this paper, we have used Deep Learning techniques and TensorFlow framework with the goal of building a neural network model to predict (speed, acceleration, steering angle, and brake) features needed for navigation of autonomous vehicles. The Deep Neural Network has been trained on images and sensor data obtained from the comma.ai dataset. A heatmap was used to check for correlation among the features, and finally, four important features were selected. This was a multivariate regression problem. The final model had five convolutional layers, followed by five dense layers. Finally, the calculated values were tested against the labeled data, where the mean squared error was used as a performance metric.

Keywords: autonomous vehicles, deep learning, computer vision, artificial intelligence

Procedia PDF Downloads 149