Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Emotion is subjective which convey rich semantics based on an image that induces different emotion based on each individual. A novel method is proposed for emotion classification by using deep learning network with transfer learning method. Transfer learning techniques are the predictive model that reuses the model trained on related predictive problems. The purpose of the proposed work is to classify the emotion perception from images based on visual features. Image augmentation and segmentation is performed to build powerful classifier. The performance of deep convolution neural network (CNN) is improved with transfer learning techniques in large scale Image-Emotion-dataset effectively. The experiments conducted on this dataset and result shows that proposed method achieve promising significant effect on emotion classification with good accuracy and PDA value, when compared with other state-of-art methods. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Department of Software and Systems Engineering

School of Information Technology and Engineering

Vellore Campus

World University root node

International Journal of Speech Technology

Transfer learning techniques for emotion classification on visual features of images in the deep learning network

The virtual touch screen framework (VIRTOS) is intended to exertion in the space, whereas surrounding light environments can change. The VIRTOS consistently displays touch area, when a vast front area (non-foundation, a hand/ shadow) protects and breaks on the catch; the shade of anticipated touch catch is changed quickly with the end goal to recognize the shadow from the hand. Likewise VIRTOS bolsters the slider (scrollbar) in light of these virtual touch-catch instruments. The basic detraction procedure exists is utilized to fragment the frontal area. The reference image meant for each catch is utilized for basic detraction, is ceaselessly refreshed to represent changes in encompassing light. The experiments show that the ease of VIRTOS, is in it needs of two applications: for slide introductions by two virtual catches towards to explore the slides, and further is an activity diversion measured by the virtual slider effective. Maintenance of Virtos is really easy. Among all the benefits of Virtos, the most important thing is that we are using a solar panel and we know that solar energy is a truly renewable energy source. © 2020 IEEE.

Department of Smart Computing

Proceedings of International Conference on Computation, Automation and Knowledge Management, ICCAKM 2020

Augmenting Moving Planar Surfaces and Spatial Control of Interactive Surfaces Application through Virtual Touch Screen (VIRTOS)-A Case Study

Nowadays, deep learning technique becomes the most popular fast-growing machine learning method in an Artificial Neural Network. The Convolution Neural Network (CNN) is one of the deep learning architecture that has been applied in the field of image analysis and image classification. In this paper, we proposed a novel emotion learning model with a deep learning network. The aim of the learning model is to reduce the affective gap, that extracts the objects and background features of an image semantically, such as high-level and low-level features. These extracted features accompanied with few others and it is more effective in emotion prediction model based on visual concepts of image, that leads to better emotion recognition performance. For training and testing, the experiment is conducted on IAPS (International Affective Picture System) dataset, the Artistic Photos, and the Emotion-Image dataset. An experimental result shows that the proposed model combines visual-content and low-level features of the image that provides promising results for Affective Emotion Classification task. © The Author(s) 2020.

International Journal of Electrical Engineering Education

Affective emotion classification using feature vector of image based on visual concepts

Classification of emotion based on the image is a trivial task and hence a challenging issue in Content-Based Image Retrieval (CBIR) technique in the framework called Emotion-Based Image Retrieval (EBIR) system. This paper discusses emotion predication system that automatically predicts the semantic meaning of human emotion and uses visual features in order to ease the process of feature extraction. The emotion-based on the image is the subjectivity which plays a major role in the image retrieval process. The main motivation of this study is to predict the human emotion from an image. In the proposed work, the color, texture and shape are used as feature concepts to predict the semantics of emotion which are related with an image and features extracted by dominant color structure descriptors for color feature extraction, homogeneous texture descriptor(edge histogram) for texture feature extraction and region-based or contour-based descriptor(shape spectrum) for the shape feature extraction. Deep convolution Neural Network (Deep CNN) is used for classification into 6 basic emotion classes like anger, disgust, fear, happiness, sadness, and surprise by using color emotion factors. For training and testing the images, real-time data such as wallpaper, textile, and painting database is used. Experimental results of approach are evaluated and compared with classifier algorithms by using the measures of precision, recall, and accuracy. The prediction system also measures the arousal, valence and dominance value in order to measure the performance of EBIR approach/system. © 2019 JPR Solutions. All rights reserved.

Test Engineering and Management

A semantic classification of images by predicting emotional concepts from visual features

Semantic based video/image retrieval is a most critical issue in the multimedia search enginerelated research. Multimedia content annotation improves the accuracy of semantic based content retrieval system where multimedia content annotation can be done in two ways: One is content based annotation and another is context based annotation. The content based annotation of images and videos consist of both low level and high level features which would be derived from the detailed pixel intensity information of images whereas context information would provide the semantic details about the images/videos. In this analysis work, discussion about the various techniques used to retrieve the multimedia content from the web engines with the semantic knowledge awareness is provided. The various research methods that intend to perform the annotation on multimedia contents is discussed in detailed. And also, this analysis work provides the discussion about the techniques in terms of their merits and demerits. Finally this work also provides the numerical evaluation of eachtechnique based on their accuracy in the videoretrieval outcome. The overall evaluation of the surveyed methodologies is performed and provides discussion about the outcome obtained from each technique. © BEIESP.

International Journal of Innovative Technology and Exploring Engineering

A comprehensive survey on various semantic based video/image retrieval techniques

Data mining techniques play a major role in healthcare centers to solve large volume of datasets. For diabetes patients if the blood glucose level diverges from typical range leads to serious complications. So, they must be monitored regularly to determine any critical variations. Implementing a predictive model for monitoring the glucose level would enable the patients to take preventive measures. This paper describes a solution for early detection of diabetes by applying various data mining techniques to generate informative structures to train on specific data. The main goal of the research is to generate clear and understandable pattern description in order to extract data knowledge and information stored in the dataset. We investigate the relative performance of various classifiers such as Naive Bayes, SMO-Support Vector Machine (SVM), Decision Tree, and also Neural Network (multilayer perceptron) for our purpose. The ensemble data mining approaches have been improved by classification algorithm. The experimental result shows that Naive Bayes algorithm shows better accuracy of 83.5% by splitting techniques (ST), when the data sets is reduced by 70–30 ratio percentage. By cross-validation (CV) decision tree shows better result 78.3% when compared with other classifiers. The experiment is performed on diabetes dataset at UCI repository in Weka tool. The study shows the potential of ensemble predictive model for predicting instance of diabetes using UCI repository diabetes data. The results are compared among various classifiers and accuracy of test results is measured. © 2019, Springer Nature Singapore Pte Ltd.

Department of Information Technology

Advances in Intelligent Systems and Computing Advances in Big Data and Cloud Computing

Comparative Study of Classification Algorithm for Diabetics Data

Confront acknowledgment framework is one of the biometrics strategies that are utilized as a part of assortment of uses utilizing the picture handling systems. Confront acknowledgment framework is produced utilizing the Mat lab condition with the systems took after by main segment investigation and the straight discriminant examination. The execution is measured utilizing the time rate, remove rate, pixel values and the element separated determination rate. The ideal acknowledgment is executed when the time traverse around half and the separation rate around the 90 %. What’s more, on account of pixel and determination, when the pixel qualities are expanding then the determination calculate ought to likewise be an expanding request. On the off chance that the removed element contains more pixels then the determination element is progressively that identifies with the quality in separating the element. The execution is measured utilizing the two distinctive programming metric techniques to be specific spearmen and Pearson metric. At that point the general measure is characterized by picking up with the two metric strategies. The execution is plotted utilizing the diagram to foresee the rate of time and extricated include. © 2017, Institute of Advanced Scientific Research, Inc. All rights reserved.

Journal of Advanced Research in Dynamical and Control Systems

Similarity based face identification using metrics analysis

This case study reviews the procedural modeling methodology to reconstruct 3D buildings when given a single facade 2D image view and their corresponding footprint. This is an algorithmic approach when compared with existing software tools that are used for mass 3D building model generation like CityEngine. Procedural modeling framework accepts the best production rule given a particular alignment of footprint. We have evaluated the framework using modeling experiments by taking real building footprint data and 2D photographs. We have proved the reliability of procedural modeling framework from the results of user satisfaction survey. The Cronbach's alpha value of 0.86 suggests that the results are statistically significant. © IAEME Publication.