Full Description
This book constitutes the proceedings of the Second International Conference on Signal Processing and Computer Vision, SIPCOV 2025, held in Silchar, India, during August 8-9, 2025.
The 36 full papers were included in this were carefully reviewed and selected from 146 submissions. They focus on Signal Processing, Computer Vision, and Biomedical Image Processing.
Contents
.- Part I: Signal Processing and Artificial Intelligence for Biomedical Imaging and Health Informatics.
.- Capturing Chronic Condition Variance: A Spectrogramto-Latent-Space Differentiation via Autoencoders.
.- Attention-Weighted Spectral Token Classification for Non-Invasive Detection of Fetal Breathing Movements Using Transformer-Based Acoustic Signal Modeling.
.- WeeCare: A Benchmark Database for the Analysis of Fetal Stress Condition from Cardiotocography Signals.
.- Unveiling Cognitive Dissonance in Pain Perception Through Cluster-Based Subject Modeling.
.- GAN-Based Transfer Learning Model for Brain Tissue Classification in Progressive Multiple Sclerosis Using Electron Microscopy Images.
.- HMST-Lite: A Lightweight Multi-Scale Transformer for Early Breast Cancer Stage Classification.
.- MelanoXAI: Explainable AI for Melanoma Detection in Dermatoscopic Images.
.- Explainable Deep Supervised Attention U-Net for Fetal Abdominal Structure Segmentation.
.- Lifestyle-Based Machine Learning Models for the Early Detection of Heart Disease.
.- Differentiation of Basal and Activated Autophagy using CNN Algorithm.
.- Automated Sperm Morphology and Quality Scoring using Explainable EfficentNet-B0 Driven Framework.
.- Hybrid Bi-directional GRU-Attention U-Net with MLP Classifier for Accurate Pneumonia Segmentation and Classification.
.- Lung infectious diseases diagnosis with Convolutional Neural Network using Chest X-ray images.
.- Evaluation of Deep Learning Model using optimal rotationally transformed data for the detection of age-related macular degeneration.
.- Internet Addiction Recognition from EEG Signals Using Laplacian Energy Features.
.- Robust microaneurysm Detection in Retinal Fundus Images Using an Optimized ResNet50-UNet Model.
.- Designing a system to detect psychological stability status using AI-Driven Analysis.
.- Design and Implementation of Cardiac Arrest Detection.
.- Investigations and Analysis of Textile Electrocardiogram Electrodes for Wearable Health Monitoring System.
.- Part II: Computer Vision and Deep Learning for Visual Perception, Image Understanding, and Scene Analysis.
.- CNN based structural damage detection by reducing sensors through SHAP method Know.
.- A Robust Machine Vision Model to Detect Wildfire Utilizing Advanced AI-Based Deep Learning.
.- Multiple Face Detection, Recognition, and Tracking for Enhanced Security and Surveillance Applications.
.- Automated Attendance Tracking System Using Facial Recognition Web Application.
.- MiGRoW: A Multi-Perspective Feature Weighting Scheme Using Gini, Entropy, and Mutual Information.
.- An Underwater Image Enhancement Usin Integro-Differential Equation Based Model.
.- Part III: Signal Processing and Intelligent Systems for Human Computer Interaction.
.- Movement Analysis in Performing Arts from Human Body Pose Estimation.
.- DeepFood: Enhancing Recipe Selection through AI-Based Ingredient Recognition.
.- CrookFoot: An Android-Based Deep Learning Application for Real-Time Foot Deformity Detection and Arch Index Estimation.
.- Pneumatically Actuated Lower Limb Exoskeleton: A Design and Control Approach.
.- Quantum-Based Encryption Model for Satellite Video Images: A Comparative Analysis.
.- Bridging Communication Gaps: An Integrated GUI for ISL Gesture-to-Voice and Voice-to-Sign Translation.
.- Designing a system to detect psychological stability status using AI-Driven Analysis.
.- DL-AAT: An Automatic Annotation Tool for Efficient Data Labeling in Vision-Based Systems.
.- Speaker Recognition using Kannada Language Emotional Speech Text Dependent Corpus.
.- Resource-Conscious Predictive Load Balancing (RCPLB) for Single Board Computers (SBC) using Support Vector Machines (SVM).
.- Real-Time Sign Language Recognition Using an Attention-Driven Ensemble of Deep Models.
