Current Issue – Vol.5, Issue.3 (July-September 2025)

Abstract

A CAPTCHA (Completely Automated Public Turing test to Tell Computers and Humans Apart) should be as convenient as easy for human and almost impossible for bots. User should not be irritated by solving AI problems; it must be very easy going with fun. Proposed system is able to serve hard AI problem that can be easily solved by human but almost impossible for bots. This system is based on umpire’s call where user is to take decision as a cricket umpire whether batsman is out or not. It has been reviewed that cricket LBW trajectory can only be more precise with hawk eye cameras that mount over the roof of cricket stadium. Even hawk eye trajectory cannot be applied in image processing if a normal camera’s coordinates have been captured. It can be done at real time when co-ordinates have been attained from hawk eye and projected at that time. Cricket ball trajectory requires ball speed, angle, position and path; that can only possible with high speed camera. A normal camera is not able to identify the speed of the ball and some co-ordinates also.

Key-Words / Index Term: CAPTCHA, Web Security, DRS, Cricket, LBW, Hawk eye, Camera, Game Theory.

Citation

Arun Pratap Singh, "LBW Dismissal Umpire Decision Prediction CAPTCHA using Backwards Induction & Rational Game Theory (Umpire’s Call CAPTCHA)" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.3, pp.1-08, 2025.

Abstract

Cricket has evolved into a technology-driven sport where decision accuracy plays a pivotal role in maintaining fairness and transparency. One of the most critical aspects of Decision Review System (DRS) is predicting the cricket ball’s trajectory after impact with the pad, which assists in adjudicating Leg Before Wicket (LBW) decisions. Traditional ball-tracking systems such as Hawk-Eye rely on multi-camera setups and physics-based models, which, while accurate, are expensive and prone to occasional errors due to occlusions, shadows, and complex bounce conditions. With advancements in deep learning and computer vision, it is now possible to develop a data-driven approach that learns ball dynamics directly from large datasets of match footage. In this work, we propose a deep learning–based cricket ball trajectory projection model that combines convolutional neural networks (CNNs) for spatial tracking, recurrent neural networks (RNNs/LSTMs) for temporal sequence modeling, and physics-informed loss functions for realistic trajectory prediction. The proposed method aims to provide a robust, cost-effective, and highly accurate alternative to traditional ball-tracking technologies for cricket DRS applications.

Key-Words / Index Term: Cricket, Decision Review System (DRS), Ball Trajectory, Deep Learning, Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Computer Vision, Sports Analytics.

Citation

Arun Pratap Singh, Sanjay Kumar Sharma, "Cricket Ball Trajectory Projection for DRS using Deep Learning" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.3, pp.09-15, 2025.

Abstract

The rapid growth of digital media distribution has raised critical concerns about copyright protection. Unauthorized use, duplication, and manipulation of images threaten intellectual property rights, making watermarking a crucial security mechanism. Traditional watermarking methods often face challenges such as vulnerability to attacks, loss of image quality, and limited robustness. This paper proposes a machine learning–based intelligent watermarking framework to embed secret watermarks within digital images for copyright protection. The proposed approach leverages deep learning for feature extraction, adaptive embedding, and robust detection of watermarks under various distortions. Experimental results demonstrate that machine learning–driven watermarking enhances imperceptibility, robustness, and security compared to conventional approaches, providing a reliable mechanism for copyright enforcement in digital media.

Key-Words / Index Term: Watermarking, Copyright Protection, Machine Learning, Deep Learning, Digital Security, Image Processing.

Citation

Sachin Soni, A.P. Singh, "Intelligent Watermarking for Image Copyright Protection using Machine Learning Techniques" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.3, pp.16-22, 2025.

Abstract

The increasing threat of terrorism and armed attacks in public spaces necessitates advanced automated surveillance systems. Traditional visual spectrum cameras often fail under low-light or night-time conditions, making thermal imaging a promising alternative for detecting concealed weapons and potential suicide bombers. This research proposes a deep learning-based framework for real-time detection of suicide bombers and weapons using thermal imagery. The approach leverages convolutional neural networks (CNNs) and transfer learning to extract discriminative features from thermal images, enabling accurate identification under diverse environmental conditions. Experimental results demonstrate high detection accuracy, robustness to occlusion and variable poses, and real-time applicability. This study highlights the potential of thermal imaging combined with deep learning to enhance public security and preemptively mitigate threats.

Key-Words / Index Term: Suicide Bomber Detection, Weapon Detection, Thermal Imaging, Deep Learning, Convolutional Neural Networks (CNN), Object Detection, Surveillance Systems, Real-Time Threat Detection, Security Monitoring, Transfer Learning.

Citation

Utkarsh Dubey, "Deep Learning-Based Suicide Bomber and Weapon Detection in Thermal Imaging for Enhanced Security Surveillance" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.3, pp.23-28, 2025.