A5069192282- Handwritten Text Recognition Techniques
- Image Retrieval and Classification Techniques
- Vehicle License Plate Recognition
- Image Processing and 3D Reconstruction
- Advanced Image and Video Retrieval Techniques
- Face and Expression Recognition
- Medical Image Segmentation Techniques
- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Brain Tumor Detection and Classification
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- Smart Agriculture and AI
- Image and Object Detection Techniques
- COVID-19 diagnosis using AI
- Image Enhancement Techniques
- Spectroscopy and Chemometric Analyses
- Advanced Image Fusion Techniques
- Advanced Image Processing Techniques
- AI in cancer detection
- Emotion and Mood Recognition
- EEG and Brain-Computer Interfaces
- Software Engineering Research
- Digital Imaging for Blood Diseases
JSS Science and Technology University
2016-2024
Nottingham Trent University
2020
Sri Jayadeva Institute of Cardiovascular Sciences and Research
2015-2019
Jaypee University of Information Technology
2019
JSS Dental College and Hospital
2016
Dr. Hari Singh Gour University
2010-2012
University of Mysore
2006-2010
University of Genoa
2010
Maharaja Engineering College
2010
International School of Europe
2010
Skin cancer is one of the most rapidly spreading illnesses in world and because limited resources available. Early detection skin crucial accurate diagnosis identification for preventive approach general. Detecting at an early stage challenging dermatologists, as well recent years, both supervised unsupervised learning tasks have made extensive use deep learning. One these models, Convolutional Neural Networks (CNN), has surpassed all others object classification tests. The dataset screened...
The recent outbreak of the novel Coronavirus Disease (COVID-19) has given rise to diverse health issues due its high transmission rate and limited treatment options. Almost whole world, at some point time, was placed in lock-down an attempt stop spread virus, with resulting psychological economic sequela. As countries start ease measures reopen industries, ensuring a healthy workplace for employees become imperative. Thus, this paper presents mobile app-based intelligent portable healthcare...
Abstract Coronavirus disease (COVID-19) has infected over more than 28.3 million people around the globe and killed 913K worldwide as on 11 September 2020. With this pandemic, to combat spreading of COVID-19, effective testing methodologies immediate medical treatments are much required. Chest X-rays widely available modalities for diagnosis COVID-19. Hence, automation detection COVID-19 from chest X-ray images using machine learning approaches is greater demand. A model detecting proposed...
Violent event detection is an interesting research problem and it a branch of action recognition computer vision.The violent events significant for both the public private sectors.The automatic surveillance system more attractive because its wide range applications in abnormal detection.Since many years researchers were worked on activity they have proposed different feature descriptors vision acoustic technology.Challenges still exist due to illumination, complex background, scale changes,...
The performance of a character recognition system depends heavily on what features are being used. Though many kinds have been developed and their test performances standard database reported, there is still room to improve the rate by developing improved features. In this paper, we propose novel based radon transform for handwritten digit recognition. We used function which represents an image as collection projections along various directions. resultant feature vector applying method input...
The present paper presents one of the efficient approaches toward multilingual text detection for video indexing. In this paper, we propose a method detecting textlocated in varying and complex background images/video. approach comprises four stages: first stage, combination wavelet transform Gabor filter is applied. By applying single level 2D decomposition with Filter, intrinsic features comprising sharpen edges texture an input image are obtained. second resultant classified using k-means...
In the present work, we describe study and performance of a robust text detection method in color regular images. The system employs two important stages: Firstly combination wavelet transforms gabor filter is applied to extract sharpened edges textural features given input image. second stage, entropy imposed get an energy value resulted image order find high frequency texture elements processed one determine true region Experiments are conducted on standard ICDAR database with...
This paper presents a Picture Fuzzy Clustering (PFC) method for MRI brain image segmentation. The PFC is based on the fuzzy set, which generalization of traditional set and intuitionistic set. In problem uncertainty arises in defining membership function. Intuitionistic handles this by considering hesitation degree. However, fails to solve real time problems require answers like yes, abstain, no refusal. picture solves these refusal degree along with membership, neutral nonmembership Thus,...
Corona virus disease (COVID-19) has infected over more than 10 million people around the globe and killed at least 500K worldwide by end of June 2020. As this continues to evolve scientists researchers world now trying find out way combat in most effective way. Chest X-rays are widely available modality for immediate care diagnosing COVID-19. Precise detection diagnosis COVID-19 from these chest would be practical current situation. This paper proposes one shot cluster based approach...
In this paper, recognition system for totally unconstrained handwritten characters south Indian language of Kannada is proposed. The proposed feature extraction technique based on Fourier Transform and well known Principal Component Analysis (PCA). trains the appropriate frequency band images followed by PCA scheme. For subsequent classification technique, Probabilistic Neural Network (PNN) used. tested large database containing also standard COIL-20 object results were found to be better...
Character segmentation has become a crucial task for character recognition in many OCR systems. It is an important step because incorrectly segmented characters are unlikely to be recognized correctly. For segmenting cursive scripts leads more challenging of presence touching characters. Kannada the one popular language south India and also some letters nature. In this paper, new algorithm unconstrained handwritten presented. The proposed method based on thinning, branch point mixture...
Crop grading is one of the important stages in crop management. The different grades can be done by classification. In this paper, we propose texture based arecanut. Different features are extracted from arecanut applying approaches such as Wavelet, Gabor, Local Binary Pattern (LBP), Gray Level Difference Matrix (GLDM) and Co-Occurrence (GLCM) features. For classification Nearest Neighbor (NN) classifier used. Experimentation conducted using a dataset 700 images 7 classes to demonstrate...
Automatic moving object detection and tracking is very important task in video surveillance applications. In this paper, we propose a novel scheme for based on Locality Preserving Projections (LPP). It also known as Laplacian eigenmaps, which optimally preserves the neighborhood structure of data set [1]. The proposed method was tested standard PETS dataset many real time sequence results satisfactory.