A5033940920- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- AI in cancer detection
- Face and Expression Recognition
- Medical Image Segmentation Techniques
- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Optimization and Mathematical Programming
- Remote-Sensing Image Classification
- Video Analysis and Summarization
- Lung Cancer Diagnosis and Treatment
- Advanced Data Compression Techniques
- Multi-Criteria Decision Making
- Face recognition and analysis
- COVID-19 diagnosis using AI
- Robotic Path Planning Algorithms
- Image Processing and 3D Reconstruction
- Image and Signal Denoising Methods
- Radiomics and Machine Learning in Medical Imaging
- Human Pose and Action Recognition
- Gene expression and cancer classification
- Machine Learning in Healthcare
- Digital Imaging for Blood Diseases
- Gastrointestinal Bleeding Diagnosis and Treatment
- Forecasting Techniques and Applications
SRM University
2020-2024
SRM University, Andhra Pradesh
2020-2024
National Institute of Science and Technology
2016-2017
Indian Institute of Technology Kharagpur
2012-2016
Global plastic waste is increasing rapidly. In general, densely populated regions generate tons of daily, which sometimes disposed on land or diverged to sea. Most the plastics created in form have complex degradation behavior and are non-biodegradable by nature. These remain intact environment for a long time span potentially originate complications within terrestrial marine life ecosystems. The strategic management recycling can preserve environmental species associated costs. key...
This contribution applies tools from the information theory and soft computing (SC) paradigms to embedding extraction of watermarks in aerial remote sensing (RS) images protect copyright. By time 5G came along, Internet usage had already grown exponentially. Regarding copyright protection, most important responsibility digital image watermarking (DIW) approach is provide authentication security for content. In this paper, our main goal RS transmitted over by proposal a hybrid using both...
Content representation for images with well‐defined inter‐class boundaries in the feature space remains to be a difficult task. Simple distance‐based retrieval (SDR) approaches those operate on content‐based image (CBIR) are, therefore claimed inefficient by many researchers. Different CBIR have been proposed surmount drawbacks of SDR scheme. This study proposes novel In this scheme, effort is taken reduce overall search time recently approach called ‘class membership‐based retrieval’ (CMR)....
This paper provides a method to understand the underlying semantics of <i>Bharatnatyam</i> dance motion and classifies it. Each performance is audio-driven spans over space time. The captured analyzed, which helpful in cultural heritage preservation, tutoring systems assist naive learner. attempts solve fundamental problem; recognizing motions during based on motion-pattern. used dataset video recordings an Indian Classical Dance form known as <i>Bharatanatyam</i>. different <i>Adavus</i>...
Many systems have been developed for computer analysis of the lungs in high resolution computed tomography (HRCT) scans detection and Interstitial Lung Diseases (ILDs). This paper presents a novel approach classification lung tissue patterns affected with (ILDs) scans. The proposed scheme makes use texture features obtained using Discrete Wavelet Transform (DWT) multiple classifiers to obtain initial decisions on input image. from all are fused final decision pattern. method is tested...
Interstitial lung disease (ILD) is complicated group of pulmonary disorders. High Resolution Computed Tomography (HRCT) considered to be best imaging technique for analysis different HRCT findings can categorised in several patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Nodular, Normal etc. based on their texture like appearance. Clinician often find it difficult diagnosis these pattern because complex nature. In such scenario computer-aided system could help clinician...
Identifying k ey frames is the first and necessary step before solving variety of other B haratanatyam problems. The paper aims to partition momentarily stationary (key frame s) from this dance video's motion frames. proposed key s (KFs) localization novel, simple, effective compared existing video analysis methods. It distinctive standard KFs detection algorithms as used in human videos. In dance's basic structure, occurrence during performances often not completely varies with form...
Breast cancer is reported as the second most deadly in world on which public awareness has been increasing during last few decades. Early detection can play an effective role prevention and reliable technology mammography. At early stages of breast cancer, clinical signs are very mild vary appearance, making diagnosis difficult even for specialists. Therefore, automatic reading medical images becomes highly desirable. This paper aims to develop automated system mass classification digital...
Content Based Image Retrieval (CBIR) system could exploit the wealth of High-Resolution Computed Tomography (HRCT) data stored in archive by finding similar images to assist radiologists for self learning and differential diagnosis Interstitial Lung Diseases (ILDs). HRCT findings ILDs are classified into several categories (e.g. consolidation, emphysema, ground glass, nodular etc.) based on their texture like appearances. Therefore, analysis is considered as a problem. Many approaches have...
Radio Frequency Identification (RFID) is primarily used to resolve the problems of taking care majority nodes perceived and tracking tags related items. Utilizing contactless radio frequency identification data can be communicated distantly using electromagnetic fields. In this paper, comparison analysis made between Clustered RFID with existing protocols Ad hoc On-demand Multicast Distance Vector Secure Adjacent Position Trust Verification (AOMDV_SAPTV) Optimal Distance-Based Clustering...
Content-Based Remote Sensing Image Retrieval (CBRSIR) is used to find relevant images from large collections of remote sensing images. CBRSIR works by indexing each image in the database with a feature vector. Deep semantic features generated using convolutional neural networks (CNNs) are more powerful than low-level for tasks because they can comprehend context and content within an image. However, major problem deep its vector size which turn impact performance retrieval system susceptible...
Finding similar images or reference is one way to assist radiologist during daily clinical practice for differential diagnosis of Interstitial Lung Diseases (ILDs). Content Based Image Retrieval (CBIR) system could exploit the wealth HRCT data stored in archive by finding radiologists practice. We have designed a special purpose CBIR (Med-IR) (ILDs), where user can provide interstitial disease pattern as input and will retrieve few most patterns available database. Three different feature...
Real-time roadway-environment perception is one of the primary applications IoT based autonomous driving to improve road safety. Roadway-environment insights include on-road detection any type moving vehicles, non-vehicle (persons, animals, etc.), curves and lanes. There have been various studies that provided Artificial Intelligence (AI)-based approaches, however, most methods are atomistic which not well suited for such real-time owing high latency low accuracy. Therefore, in this paper,...
Automated segmentation of pathological bearing region is the first step towards development lung CAD. Most work reported in literature related to automated analysis tissue aims classification fixed sized block into one classes. This level tissues image never results accurate or smooth boundaries between different regions. In this work, effort taken investigate performance three algorithms those among patterns commonly encountered HRCT images thorax. A public database that consists from...
Abstract In this paper, a viable, robust, and highly accurate additive hybrid model employing autoregressive fractionally integrated moving average (ARFIMA) support vector machine (SVM) with functionally expanded inputs (Additive‐ARFIMA‐SVM) is presented for forecasting the air quality index (AQI). Additionally, thirteen multiplicative models are introduced. Several alternatives in feature engineering functional expansion of incorporated to boost performance models. Furthermore, gradient...