All articles
29 articles
-
AI-Based Deepfake Voice Detection Model for Hindi Language
Abstract: Most current research on deepfake voice detection focuses heavily on English or Mandarin, creating a significant security gap for Hindi speakers. To address this, we developed a detection framework specifically tailored for the Hindi language using a lightweight approach: Mel-Frequency Cepstral Coefficient (MFCC) feature extraction paired with an XGBoost classifier. We trained the system on a large dataset comprising over 99,000 real voice samples and roughly 3,800 synthetic samples, each …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 2, 2026 Read article
-
DEVELOPING A DRIVER DROWSINESS DETECTION SYSTEM (DDDS)
Abstract: Driver drowsiness accounts for over 18% of all traffic accidents in India, making it a major contributing factor. This study proposes a real-time, edge-based Driver Drowsiness Detection System (DDDS) that detects early fatigue signs and alerts drivers prior to accidents. The system employs a multimodal, bimodule strategy. In order to track face traits such eye closure, blink rate, yawning, head position, and gaze direction, the first module uses computer vision. …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 2, 2026 Read article
-
A Study on CNN-Based Image Mosaicing
Abstract: The intricate tapestry of image mosaicing, while a cornerstone of computer vision, has long been constrained by the rigidity of classical, geometry-driven pipelines. Hand-crafted feature detectors and homography estimators, while effective in controlled environments, prove brittle when confronted with the challenges of real-world scenes: significant parallax, dynamic moving objects, repetitive textures, and illumination variance. This work introduces a fundamental paradigm shift, proposing a deep convolutional neural network (CNN) architecture designed …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 1–7 Read article
-
Advanced Classification of Diabetic Retinopathy Using GAN and Deep Residual CNN Model
Abstract: Diabetic retinopathy (DR) is a leading cause of blindness worldwide, impacting the largest number of individuals who have diabetes. Early identification of diabetic retinopathy may help to prevent severe effects; however, the very limited availability of labeled datasets, and the possibility of overfitting of the model, presents obstacles to obtaining an accurate diagnosis. In this research, a hybrid deep learning strategy is introduced, where Generative Adversarial Networks (GANs) are used …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 8–16 Read article
-
Vani-Adapt: A Zero-Shot Accent Trans-Adaptation Framework for Robust Indic Speech Recognition
Abstract: In countries like India with multilingual and accent-rich dialects, speech-based human–computer interaction is important to expand digital services for better accessibility. Even with recent advancements in Automatic Speech Recognition (ASR), existing systems are still very reactive to regional accents and non-standard speech patterns which is not suitable for seamless experience. Traditional perspectives rely on accent-specific fine-tuning, which is unrealistic for real-world deployment and requires a lot of labeled data, which …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 17–22 Read article
-
Enhancing Facial Expression Analysis Using CNNs: Insights from ML and Deep Learning Comparisons
Abstract: Emotion recognition from facial manifestations increases the interaction between humans and computers by enabling the interaction between humans and computers to effectively explain human feelings. This study presents a comparative analysis of three approaches to the emotional recognition of faces: a custom Convolutional Neural Network (CNN) model, Traditional Machine Learning (ML) methods, and other deep learning architectures such as VGG, ResNet, and Hybrid CNN–RNN models. The proposed CNN-based system, developed …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 23–31 Read article
-
A Comprehensive Review of Convolutional Neural Network Architectures and Evolution
Abstract: Convolutional Neural Networks (CNNs) have become a foundational deep learning framework in computer vision because they can automatically extract layered, increasingly complex features directly from raw image data. CNNs use convolutional, pooling, and activation layers to extract spatial patterns from basic edges to intricate object components, drawing inspiration from the human visual cortex. An overview of CNNs’ basic architecture is given in this study, along with an explanation of important …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 32–40 Read article
-
Gourmet Sage Using Deep Learning With Calories Chart
Abstract: Gourmet Sage via Deep Learning with Calories Chart is an innovative system that merges advanced deep learning technology with nutrition science to help users make healthier dietary choices. By leveraging YOLOv8, a cutting-edge object detection model, the system allows real-time identification of food items, estimating their calorie content and ingredient composition with remarkable accuracy. It goes beyond detection by providing a comprehensive nutritional breakdown, including macronutrients (proteins, fats, carbs) and …
Published in International Journal of Image Processing and Pattern Recognition Read article
-
Automated Image Captioning Using Xception–CNN and LSTM for Descriptive Sentence Generation
Abstract: Generating descriptive texts for images is a complex and challenging task that requires advanced deep learning techniques. This paper presents a descriptive sentence generator for images using a combination of convolutional neural networks and recurrent neural networks. The proposed model utilizes a pretrained convolutional neural network, Xception, to extract image features, which are then processed by a long short-term memory network to generate meaningful textual descriptions. The model is trained …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 · pp. 20–28 Read article
-
Audio & Video Translate System
Abstract: With the increasing expansion of digital media and globalization, there is a rising need for sophisticated audio and video translation systems to overcome language and cultural barriers. This paper explores the role of these systems in localizing multimedia content, ensuring accessibility, and complying with global standards, including those focused on individuals with disabilities. The research aims to investigate how various translation technologies, such as dubbing, subtitling, and audio descriptions, contribute …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 · pp. 6–12 Read article
-
Blind Assistance System Using Digital Image Processing
Abstract: This paper brings forth state-of-the-art blind assistance, and the system here provides a combination of an OpenCV-based DNN module based on YOLOv3’s algorithm; the system would support real-time object detection, with associated auditory notifications to enable visually impaired individuals to understand their autonomy couched with safety about improved fast recognition of objects allied with auditory responses. The live video captures from a webcam were done and further processed by the …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 · pp. 13–19 Read article
-
A Review of Real-Time Human Detection
Abstract: The real-time human detection and counting system leverages deep learning and computer vision to detect individuals, classify gender, and estimate age from live video feeds or CCTV footage. Implemented using flask as a lightweight web framework, the system manages user authentication, detection control, and real-time result display. A Python-based detection script operates asynchronously, ensuring smooth execution, while results – including counts of males, females, and total individuals – are stored …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 · pp. 29–39 Read article
-
Deep Learning with CNNs: A Survey of Techniques and Real-World Applications
Abstract: Convolutional Neural Networks (CNNs) have emerged one of the most powerfully used tools in deep learning, particularly in image and pattern recognition tasks. CNNs are being revolutionized through deep learning resulting in a dominant architecture in computer vision as well as other various domains. This paper provides a comprehensive survey of CNN-based deep learning, its methodologies, regularizations, and computational efficiencies. We also address the challenges and future directions of CNN. …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 · pp. 1–5 Read article
-
A Review on Design and Analysis Model for Detectionand Classification of Lung Diseases Using Medical Images
Abstract: A key component of the human respiratory system, the lung regulates blood oxygen levels through gasexchange. Diseases linked to the lungs are becoming more common as pollution levels rise. In order topreserve human life, it is crucial to identify lung disorders early. In order to forecast lung disease, clinicalprofessionals analyze medical imaging, such as CT or X-rays. Clinicians identify lung disease by applyingtheir medical expertise and knowledge. Because expert knowledge …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 2, 2025 Read article
-
Advanced Security System for Residential Complexes
Abstract: A sophisticated apartment safety system aimed at preventing unauthorized access and enhancing security within residential complexes. The system employs facial recognition technology to identify residents and regular visitors while capturing the pictures and data of unknown individuals upon entry. These individuals are provided with an RFID tag, enabling continuous tracking of their movement within the premises until they reach their intended destination so that we can monitor the person and …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 1–7 Read article
-
AI in e-Skin: A Study
Abstract: For years, the concept of electronic skin, or e-skin, has captivated imaginations. Imagine a material that could mimic the sensitivity, flexibility, and even the healing properties of human skin. This isn’t just science fiction anymore. E-skin, a network of flexible sensors and electronic components, is rapidly becoming a reality. And now, thanks to the power of artificial intelligence (AI), this technology is poised to revolutionize various aspects of our lives, …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 8–16 Read article
-
Advancing Maize Leaf Disease Detection: A Machine Learning Approach
Abstract: Every day, countless grains and fruits are cultivated around the world. To keep up with the growing population’s needs, farmers are constantly adopting new and advanced techniques. Furthermore, the development and application of new technologies enable the quick and simple detection of plant diseases. Identifying plant diseases at an early stage is crucial to minimizing their effects on crop productivity and quality. Traditional diagnostic methods often rely on expert knowledge …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 17–25 Read article
-
Advanced Diabetic Retinopathy Detection Using Deep Learning Classifiers
Abstract: Diabetic Retinopathy (DR) is an eye condition that arises from diabetes-related complications, making early detection essential for effective treatment. As diabetes advances, an individual’s vision may deteriorate, potentially resulting in diabetic retinopathy. This condition is divided into two primary types: Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR). Early treatment to maintain a strategic distance from a change less visual impedance is basic as it may save diabetic retinopathy …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 26–33 Read article
-
Evaluation of Deep Learning Optimizers for Gujarati Handwritten Numerals
Abstract: Handwritten digit recognition is a fundamental task in the field of pattern recognition and computer vision with numerous applications. The development of deep learning algorithms has greatly increased the efficiency and accuracy of recognition of handwritten digits systems. However, the choice of optimizer plays a crucial role in determining the convergence rate and final performance of deep learning models. In this study, we provide a thorough analysis of many deep …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 34–41 Read article
-
Denoise Mechanism for Digital Images
Abstract: With the rapid advancement of today’s information technology, the analysis of digital images has endured rapid evolution in technology and is frequently utilized in everyday situations and enterprises. There are specific problems in the transmission process. Images are influenced by the compression of data and communication. In color image processing, a variety of well-established approaches to suppressing noise are offered. The variety of noise corrupting the image determines the nature …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 10, Issue 2, 2024 · pp. 11–17 Read article