Development of AI/ML Based Solution for Detection of Face-Swap Based Deepfake Videos Software
Blockchain-Enhanced Hybrid Biometric Authentication using Deep Learning for Identity Verification
Fabric Fashion Customized Design System using Intelligent Pattern and Color Integration for User-Driven Textile Printing
Design and Development of a Blockchain Based Students Attendance System
Enhancing Lung Cancer Detection Accuracy using CNNs and Advanced Image Preprocessing
Landslide Susceptibility Mapping through Weightages Derived from Statistical Information Value Model
An Efficient Foot Ulcer Determination System for Diabetic Patients
Statistical Wavelet based Adaptive Noise Filtering Technique for MRI Modality
Real Time Sign Language: A Review
Remote Sensing Schemes Mingled with Information and Communication Technologies (ICTS) for Flood Disaster Management
FPGA Implementation of Shearlet Transform Based Invisible Image Watermarking Algorithm
A Comprehensive Study on Different Pattern Recognition Techniques
User Authentication and Identification Using NeuralNetwork
Flexible Generalized Mixture Model Cluster Analysis withElliptically-Contoured Distributions
Efficient Detection of Suspected areas in Mammographic Breast Cancer Images
Deep learning has proven effective in a variety of tough issues, including computer vision, human-level control, and large data analytics. However, as deep learning technology advanced, software was developed that jeopardized national security, democracy, and privacy. Deepfake is a new technology that uses deep learning to create fake photos and videos that look very real. It's important to have tools that can automatically detect and check the quality of these AI- created images and videos. These systems help us quickly tell if a picture or video is real, edited, or fake, and they ensure that the quality is good and not misleading. An investigation of the strategies used to construct the most significant deepfakes, as well as the approaches proposed in the literature for detecting them. We provide a complete examination of the difficulties highlighted by deepfake technology, as well as recommendations for future and upcoming research opportunities. It also supports creating new and more reliable ways to handle deepfakes as they become more complex.
As the demand for efficient and secure identity verification increases, AI-driven biometric technologies continue to advance further. This study presents a cluster of biometric auth that employs AI with a novel approach, layering together two biometric technologies—facial recognition and fingerprint verification—so as to increase precision, and at the same time offering the user privacy and scalability. By performing score-level fusion at the backend, the system achieves more robust matching and significantly reduces false acceptance and rejection. For the data protection of the users, AES-256 encryption and SHA-256 hashing are the methods employed that give the users confidentiality and integrity at the same time. One of the unique features of the system is its capability of real-time dynamic enrollment, offline operation, and user-friendly interface developed in Python with OpenCV. Through the experimental implementation, the framework's potential is inferred to render identity verification that is not only efficient but also secure and thus suitable for sensitive environments. The present research demonstrates the practical benefits offered by the fusion of multimodal biometrics with AI in terms of strengthening authentication reliability without resorting to blockchain integration.
The research verifies the effective use of artificial intelligence, specifically text-to-image diffusion models, in the design of traditional Indian textile patterns, particularly in the form of Kalamkari art. With the use of the deployment of descriptive prompts within the framework of cultural motifs, color, and linework, the system is able to create high-quality digital images that are within the level of hand-painted textile art in terms of detail and beauty. The results indicate that these kinds of AI machines can be valuable allies in textile design, both as artistic inspiration and efficient prototyping. Designers and artisans can use this technology to quickly imagine complex patterns, explore diverse cultural themes, and try out arrangement and hue combinations without tedious hand redrawing or material cost. However, while the model succeeds in isolating visual characteristics, it does not necessarily understand the cultural significance or spiritual meaning inherent in traditional art. So, ethical use demands knowing and respectful practice, making sure that AI is a partner and not a replacement for human imagination, particularly in heritage art. The broader implications of this work extend to fashion innovation, educational content, cultural heritage, and digital enablement of craftspeople. In a future where co-creation with AI is the norm, such systems hold the potential to digitally conserve, reimagine, and celebrate traditional Indian art forms in new, universally accessible formats. This convergence of art, technology, and tradition marks a turning point in the history of design processes and gives us a glimpse of how AI can introduce culture and advance cultural heritage through innovation.
The increasing challenges of proxy attendance, manual errors, and data tampering in conventional student attendance systems highlight the need for a secure and automated solution. The current research proposes the design and development of a Blockchain-Based Student Attendance System that integrates facial recognition with decentralized storage. The system employs HOG (Histogram of Oriented Gradients) for face detection, CNN (Convolutional Neural Network) for feature extraction, and KNN (K-Nearest Neighbors) for classification, ensuring accurate identification of students. Once attendance is verified, records are securely stored on a Hyperledger Fabric blockchain, providing immutability, transparency, and tamper-proof management. A web-based interface allows real- time monitoring for faculty, students, and administrators, reducing administrative workload while enhancing trust and accountability.
Lung cancer represents a significant health challenge, impacting thousands of individuals each year. Patients with this condition have a notably low survival rate if they are not identified at an early stage. To tackle this challenge, the importance of early detection supported by artificial intelligence (AI) techniques cannot be overstated. This study presents a computer-assisted system for lung cancer detection, which utilizes a hospital-sourced dataset and employs Convolutional Neural Network (CNN) methodologies. Despite the numerous algorithms developed over the years, achieving accurate predictions has remained a challenge. This investigation presents a methodology employing CNNs to detect abnormal growth patterns in lung tissue. The method employs a robust instrument to improve detection precision and increase the likelihood of identifying irregularities. Manual interpretation frequently results in inaccuracies and incorrect diagnoses. The lung images of both healthy individuals and those with malignant conditions underwent meticulous examination to confirm the methodology's validity. The proposed neural network utilizes an efficient training function in its development. This approach exhibits exceptional detection accuracy, yielding results that exceed those of other current detection methods. The meticulous execution of pre-processing steps and a highly effective training function are responsible for the impressive results.
