Dr. K K Goyal

Followers

Following

Co-author

Public Views

Interests

Uploads

Papers by Dr. K K Goyal

Implementation of Improved NK Protocol using MATLAB

proposed an authentication of the user from the remote autonomous object. In 2005 Yang et al poin... more proposed an authentication of the user from the remote autonomous object. In 2005 Yang et al pointed out that Novikov and Kiselev scheme is insecure against the man-in-middle attack. In 2009, Goyal and Bhardwaj[12], proposed that Novikov-Kiselev scheme is insecure against a reflection attack and also proposed an improvement in this scheme. In this paper, we propose the implementation of the improved NK protocol using MATLAB.

Download

Facial Expression Recognition Using Expression Generative Adversarial Network and Attention CNN

by Dr. K K Goyal and Gyanendra Tiwary

International Journal of Intelligent Systems and Applications in Engineering, 2023

Facial Expressions are quite personalized and may look different for different individuals. Where... more Facial Expressions are quite personalized and may look different for different individuals. Whereas there are certain facial muscles which shows some common features for certain human expressions across the cultures and facial shapes. Convolution Neural Network have shown tremendous success in Facial Expression Recognition task. In recent past many researchers have proposed multiple models with manageable size solution to Facial Expression Recognition task. In the current work, we have considered shape, complexion and other identity related information separate from certain specified muscle movements which are specific for emotion recognition. This is done by a novel Emotion-Generative Adversarial Network. This saves a lot of effort and simplifies the Facial Expression Recognition process. We then apply Scale Invariant Feature Transformation and vola john's face extraction method for pre-processing and face image extraction from background. This enables us to train our model accurately irrespective of scale, orientation, illumination etc and with very less training samples accurately. We feed the feature extracted facial image to an attention-based Convolutional Neural Network. This will ensure more emphasis on critical areas for expression recognition of facial image. Finally, we have used Local Binary Pattern for classification of the input image to a particular emotion class. We have tested our model on CK+, OULU-Casia and FER-2013 datasets and it is at par with performance of all major state-of-art models. Proposed model may be utilized by various automated interactive systems, such as robot to human communication, automated customer care systems etc. The proposed work may also be quite useful for observing reaction of viewers to a particular advertisement or article automatically and use this information for various purposes like user's interest, product feedback etc.

Download

Enhancing Discriminative Power in Facial Recognition Systems through Crucial Facial Region Analysis

Journal of Electrical Systems ISSN:1112-5209, 2024

For a variety of reasons, including differences in illumination, position, and occlusions, facial... more For a variety of reasons, including differences in illumination, position, and occlusions, facial recognition systems are becoming increasingly ubiquitous in a variety of applications; nonetheless, they frequently fail to achieve high discriminative power. This article presents a unique way to improve the discriminative power of face recognition systems by analysing critical facial areas, notably the eyes, nose, and mouth. The purpose of this approach is to raise the sensitivity of facial recognition systems. We hope that by concentrating on these two critical areas, we will be able to enhance feature extraction and representation, which will ultimately result in recognition that is more accurate and dependable. For the purpose of properly isolating and analysing these key regions, our methodology incorporates complex machine learning and deep learning techniques, as well as attention processes. Enhanced capability to discriminate between individuals is achieved by the utilization of a hybrid feature extraction approach that combines geometric and appearance-based information. Our methodology has been shown to be effective through the use of experimental assessments on benchmark datasets such as FER2013, CK+, and JAFFE. With regard to identification accuracy, precision, recall, and F1 score, the suggested system makes considerable improvements in comparison to the systems that are currently in use. According to these findings, facial area analysis could be able to significantly improve the performance of face recognition systems, hence making them more reliable and adaptable to situations that occur in the real world. When it comes to boosting the overall discriminative capacity of recognition systems, our work not only contributes to the advancement of the area of facial recognition but also brings to light the significance of focused feature analysis. In subsequent study, the integration of this method with real-time video processing will be investigated, along with the implications that this integration has for applications in the fields of healthcare and security.

format_quoteThe new system achieved considerable improvements in identification metrics like precision, recall, and F1 score over existing systems.format_quote

Download

Explore the Integration of Multimodal Inputs with Facial Expressions for More Comprehensive Emotion Recognition

Communications on Applied Nonlinear Analysis ISSN: 1074-133X, 2024

With improvements in multimodal data integration, which uses voice, text, and visual cues to corr... more With improvements in multimodal data integration, which uses voice, text, and visual cues to correctly guess emotional states, emotion recognition has come a long way. In this study, we examine how adding facial expressions to speech and text sources can make emotion recognition systems more accurate and detailed. Including facial signals is vital since it includes a visual component that makes a difference us get it feelings more profoundly, complementing what able to learn from tuning in and perusing. In this think about, we utilize profound learning methods, particularly Convolutional Neural Systems (CNNs) and Repetitive Neural Systems (RNNs), to way better handle and combine multi-dimensional information. A. CNNs are exceptionally great at sifting spatial features from facial expressions. B. Identifying little changes within the way facial muscles move that show diverse feelings. At the same time, RNNs handle grouping information from composed sources, capturing semantic setting and etymological nuances that offer assistance individuals express their sentiments. In this strategy, the multimodal information is preprocessed to coordinate spatial highlights and synchronize transient angles, guaranteeing information consistency over all modalities. Feature extraction procedures are utilized to extricate important designs from each media. Usually taken after by a combination handle that works in couple to create the data more valuable. The objective of this combination prepare is to evacuate superfluous information and make the assumption classification show more versatile to the clamor and variety that comes with real-world information. Measures utilized for assessment incorporate precision, exactness, review and F1 score. These are compared against well-known assumption datasets such as AffectNet and IEMOCAP. This ponder explores how well multimodal integration works. We conclude that compared with unimodal strategies, multimodal integration is more precise and solid in capturing complex enthusiastic reactions, and can be utilized in numerous real-world spaces, such as healthcare, human-computer interaction (MCI), and emotional computing. Accurate emotion tracking helps doctors diagnose mental health problems and keep an eye on patients, which makes healing treatments based on emotional states more effective.

Download

Compare the Accuracy and Efficiency of Different Machine Learning Algorithms in Recognizing Facial Expressions

The Indian Journal of Technical Education, ISSN 0971-3034, 2024

Facial expression recognition (FER) is an essential task in computer vision that has a wide range... more Facial expression recognition (FER) is an essential task in computer vision that has a wide range of applications, including human-computer interaction and affective computing. This study involved a thorough analysis to compare the precision and effectiveness of different machine learning algorithms in identifying facial expressions. The analysis was conducted using a dataset specifically designed for facial expressions. The objective was to determine the most efficient algorithm for precisely categorizing various facial expressions depicted in still images. In order to accomplish this goal, we examined six well-known machine learning algorithms: Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Decision Trees, and Gradient Boosting Machines (GBM). The evaluation of these algorithms was conducted using various performance metrics, such as accuracy, precision, recall, and F1 score. The dataset utilized in this investigation consisted of a varied collection of facial expressions captured in still images, encompassing a range of emotions including happiness, sadness, anger, surprise, fear, and disgust. Every image was annotated with the corresponding ground truth label indicating the facial expression. The experimental findings unveiled substantial disparities in the efficacy of various algorithms. CNN achieved the highest accuracy, reaching 96.3%, closely followed by GBM with an accuracy of 97.2%. SVM, Random Forest, and KNN demonstrated competitive performance, whereas Decision Trees showed slightly lower accuracy in comparison to the other algorithms.

format_quoteGBM reached 97.2% accuracy, highlighting competitive performance among machine learning algorithms in FER.format_quote

Download

Multimodal Attention CNN for Human Emotion Recognition

Springer, 2023

Human face is the mirror of mind. The face generally tells all that is going on in one's heart an... more Human face is the mirror of mind. The face generally tells all that is going on in one's heart and mind. Just by looking at the face of our known ones, we may easily guess their mood. But many a times, when we meet some unfamiliar person, it's hard to get his or her mood just by looking at their faces. This is just because the person may have certain face structure which makes them by default looking angry, happy or sad. So, we need to spend some time with that person to analyse other parameters before concluding their state of mood. The current work proposed a novel approach that integrates facial images with Electroencephalography (EEG) signals for facial expression recognition task. When Attention based deep CNN analyses the facial traits of the subject, a parallel Long Short-Term Memory (LSTM) network analyse the EEG signals. A late fusion network combines the features extracted from both the networks and finally a classification network tells about what is the current mood of the subject. Combining multiple modalities for emotion recognition has shown promising results when compared with other state of art models. There are multiple real life applications of emotion recognition models, such as Advertisement Industry, Human-Robot Interaction, Automatic Depression Detection, Mood Audio/Video Players etc.

Download

Improved remote user authentication scheme using bilinear pairings

Proceedings of the 2009 International Conference on Hybrid Information Technology - ICHIT '09, 2009

In 2005 Das et al. [5] proposed a remote user authentication scheme using bilinear pairings. Fang... more In 2005 Das et al. [5] proposed a remote user authentication scheme using bilinear pairings. Fang and Huang [7] analyzed the scheme and pointed out some weaknesses. They also proposed an improvement. Recently, Giri and Srivastava [9] observed that the improved scheme is still insecure to off-line attack and an improvement. However, the improved scheme is still insecure. In this paper, we show some weaknesses in the existing scheme and propose an improvement. The proposed scheme also enables users to choose and change the password without the help of the remote server.

Download

Dr. K K Goyal

Uploads

Papers by Dr. K K Goyal

Log In