A5004971679- Remote Sensing and Land Use
- Remote-Sensing Image Classification
- Remote Sensing in Agriculture
- Advanced Image Fusion Techniques
- Spectroscopy and Chemometric Analyses
- Vehicle License Plate Recognition
- Face and Expression Recognition
- Face recognition and analysis
- Land Use and Ecosystem Services
- Handwritten Text Recognition Techniques
- Video Surveillance and Tracking Methods
- Smart Agriculture and AI
- Hand Gesture Recognition Systems
- Smart Parking Systems Research
- Time Series Analysis and Forecasting
- Image Enhancement Techniques
- Advanced Chemical Sensor Technologies
- Phytochemicals and Medicinal Plants
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Traditional Chinese Medicine Studies
- Autonomous Vehicle Technology and Safety
- Online Learning and Analytics
- Neural Networks Stability and Synchronization
- Leaf Properties and Growth Measurement
Siddhartha Medical College
2011-2024
Jawaharlal Nehru Technological University, Kakinada
2023
Vellore Institute of Technology University
2017-2021
International Institute of Information Technology, Hyderabad
2013
Recognizing human faces in the wild is emerging as a critically important, and technically challenging computer vision problem. With few notable exceptions, most previous works last several decades have focused on recognizing captured laboratory setting. However, with introduction of databases such LFW Pubfigs, face recognition community gradually shifting its focus much more unconstrained settings. Since introduction, verification benchmark getting lot attention various researchers...
The technological advancements in spectroscopy give rise to acquiring data about different materials on earth's surface which can be utilized a variety of potential applications. But, the hundreds spectral bands are generally equipped with highly correlated information limited training samples. This will degrade Hyperspectral Image (HSI) classification accuracy. So Dimensionality Reduction (DR) has become inevitable and necessary step need incorporate before HSI classification. main...
Hyper spectral remote sensing image is also known as an "Imaging Spectrometry" one of emerged technology for detection and identification minerals, terrestrial vegetation, man-made materials, water bodies backgrounds. The word "Hyper spectral" used to discriminate sensors with many tens or hundreds bands from the more traditional multiple sensors. success hyper classification techniques based on several factors where features have vital role. Different objects materials reflect absorb sun's...
Hyperspectral image (HSI) consists of hundreds contiguous spectral bands, which can be used in the classification different objects on earth. The inclusion both as well spatial features stands essential order that high accuracy is achieved. However, incorporation and information without preserving intrinsic structure data leads to downscaling accuracy. To address issue aforementioned, proposed method involves using unsupervised band selection based three major constrains: (i) low...
Dimensionality Reduction (DR) is an indispensable step to enhance classifier accuracy with data redundancy in hyperspectral images (HSI). This paper proposes a framework for DR that combines band selection (BS) and effective spatial features. The conventional clustering methods BS typically face hard encounters when we have less items matched the dimensionality of accompanying feature space. So, fully mine information, established using dual partitioning ranking. bands from undergone...
Automatic gender detection through facial features has become a critical component in the new domain of computer human observation and interaction (HCI). numerous applications area recommender systems, focused advertising, security surveillance. Detection by using is done many methods such as Gabor wavelets, artificial neural networks support vector machine. In this work, we have used global feature distance measure pre-cursor to perform machine based classification technique improve...
Hyperspectral image (HSI) classification is major and necessary task related to HSI analysis in the field of remote sensing. The fundamental steps this are band selection (BS), spatial feature extraction, classification. HSIs generally equipped with rich spectral information having properties such as non-stationary non-Gaussian. To process information, wavelet transform (WT) perfect candidate. Also, multiscale system wavelets will be used complete extraction. So, implemented by application...
Multispectral Image classification is one of the Important and complex tasks in remote sensing image analysis. Many approaches have been studied to improve performance. Most these methods use pixel based Classification. Unlike, this paper proposed object Classification which uses Vector data by make geometrical shapes like lines polygons. Series steps are designed implemented for satellite images Deimos-2 Cartosat-1. The Overall Accuracy (OA) Kappa coefficient values shown effectiveness...
Contrast enhancement is one of the primary aspects in computer vision. In order to understand image, contrast image should be clear. many scenarios, especially biomedical images, security and surveillance, visual quality source images or video not up expected quality. There exist algorithms such as histogram equalization, genetic neural networks improve images. this work, we summarized state art made comparative study among techniques. Comparisons are done two cases: based techniques,...
The high volume and replication of data in hyperspectral images results improper classification. This paper addresses a non-linear spectral feature extraction using Local Linear Embeddings which graph-based structures are utilized. representative features then trained for smoothed spatial filter. extracted classification nonlinear version Support Vector Machine. proposed model is tested on two datasets: Indian Pines & Pavia. Proposed approach with well-known dimensionality reduction...
Automatic license plate localization is one of the crucial steps for any intelligent transportation system. This requires a series complex image processing in which edge detection plays major role case non standard as edges give information regarding location. In order to localize real time, amount data be processed must minimized at stage where are identified. this work we proposed Cellular Neural Network based time computation edges. The performance method has been tested under various...
Automatic license plate recognition is one of the crucial steps for any intelligent transportation application. License done in many approaches. However, Indian scenario very complex because, there no unique standard plate. Even though government stipulated standards on how to write and where display, people disobey those rules, making it systems recognize. The proposed morphological based method aptly suits context. results obtained show that location can be by following method. Future work...