A5012409289- Handwritten Text Recognition Techniques
- Vehicle License Plate Recognition
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Digital Media Forensic Detection
- Image Processing and 3D Reconstruction
- Generative Adversarial Networks and Image Synthesis
- Image and Object Detection Techniques
- Text and Document Classification Technologies
- Anomaly Detection Techniques and Applications
- COVID-19 diagnosis using AI
- Image Processing Techniques and Applications
- Natural Language Processing Techniques
- AI in cancer detection
- Hand Gesture Recognition Systems
- Digital Imaging for Blood Diseases
- Advanced Image Processing Techniques
- Video Analysis and Summarization
- Imbalanced Data Classification Techniques
- Advanced Neural Network Applications
- Artificial Intelligence in Healthcare
- Advanced Steganography and Watermarking Techniques
- Seismology and Earthquake Studies
- Radiomics and Machine Learning in Medical Imaging
- Cell Image Analysis Techniques
UiT The Arctic University of Norway
2023-2024
Centre for Arctic Gas Hydrate, Environment and Climate
2023
Jadavpur University
2010-2020
Indian Institute of Engineering Science and Technology, Shibpur
2011-2017
Institute of Engineering
2012
Deepfake is a type of face manipulation technique using deep learning that allows for the replacement faces in videos very realistic way. While this technology has many practical uses, if used maliciously, it can have significant number bad impacts on society, such as spreading fake news or cyberbullying. Therefore, ability to detect deepfake become pressing need. This paper aims address problem detection by identifying forgeries video sequences. In paper, solution said presented, which at...
Abstract The novel coronavirus (COVID-19), has undoubtedly imprinted our lives with its deadly impact. Early testing isolation of the individual is best possible way to curb spread this virus. Computer aided diagnosis (CAD) provides an alternative and cheap option for screening said In paper, we propose a convolution neural network (CNN)-based CAD method COVID-19 pneumonia detection from chest X-ray images. We consider three input types identical base classifiers. To capture maximum...
The holistic approaches for handwritten word recognition treat the words as single, indivisible entity and attempt to recognize from their overall shape. In present work, a novel technique Bangla is proposed. Histograms of Oriented Gradients (HOG) are used feature set represent each sample at space neural network based classifier applied classify images. On basis HOG set, performance achieved by on small dataset quite satisfactory.
Holistic word recognition attempts to recognize the entire image as a single pattern. In general, it performs better than segmentation based model for known, fixed and small sized lexicon. The present work deals with of handwritten words in Hindi holistic way. Features like area, aspect ratio, density, pixel longest run, centroid projection length are extracted either from or hypothetically generated sub-images same. An 89-elements feature vector has been designed represent each space five...