- Image and Signal Denoising Methods
- Advanced Image Fusion Techniques
- Machine Fault Diagnosis Techniques
- Gear and Bearing Dynamics Analysis
- Image Processing Techniques and Applications
- Sensorless Control of Electric Motors
- Electric Motor Design and Analysis
- Advanced Image Processing Techniques
- Noise Effects and Management
- Emotion and Mood Recognition
- Fault Detection and Control Systems
- Anomaly Detection Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Advancements in Semiconductor Devices and Circuit Design
- Speech Recognition and Synthesis
- Analog and Mixed-Signal Circuit Design
- Electric Power Systems and Control
- Lung Cancer Diagnosis and Treatment
- Neural Networks and Applications
- Advanced Image and Video Retrieval Techniques
- EEG and Brain-Computer Interfaces
- Advanced machining processes and optimization
- Advanced Memory and Neural Computing
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
Odisha University of Technology and Research
2022
Odisha University of Agriculture and Technology
2022
National Institute of Technology Durgapur
2020
Indian Institute of Technology Bhubaneswar
2015-2018
Indian Institute of Technology Kharagpur
2006-2017
We present the performance of three popular image feature extraction methods such as Scale Invariant Feature Transformation (SIFT), Speeded-Up Robust Features (SURF) and Histogram Oriented Gradient (HOG). Specifically, we compare detection for images corrupted with different types noise. The efficiency are measured by considering number correct matches between original noisy found algorithm. In this study, use noise gaussian, salt & pepper speckle. It is observed from experimental results...
We develop an efficient MRI denoising algorithm based on sparse representation and curvelet transform with variance stabilizing transformation framework. By using representation, a MR image is decomposed into sparsest coefficients matrix more no of zeros. Curvelet directional in nature it preserves the important edge texture details images. In order to get sparsity preservation, we post process result method through transform. To use our proposed remove rician noise images, forward inverse...
Image denoising algorithm in transform domain which uses learning of dictionary has better PSNR performance than others. It is seen that the popular algorithms based on K-SVD proposed earlier still use. However, texture part image could not be preserved during process denoising. also effect becomes more visible with increased value standard deviation Gaussian noise. The this work curvelet along to retain image. method shows as compared only K-SVD.
The paper presents an image based method for classification of extreme emotions. Facial images were analyzed using action units derived from the distance-measures, taken centers eyes and mouth. After initial edge detection, contours mouth further traced smoothened active snake model. Two states emotions i.e. happy sad have been tested in this paper. ratio opening average distance between center has considered as indicator emotional states.
Abstract Winding function theory has been successfully applied for the calculation of magnetizing inductances asynchronous and synchronous rotating machines steady-state transient analysis. The computational burden in such simulations is heavy because a large number stator rotor circuit coils, at every time step, each which requires evaluation definite integrals products winding functions, their distributions inverse air gap functions around periphery. This article proposes modified discrete...
Squirrel Cage induction motors are manufactured and designed to meet the performance criteria depending on type of loadings duty cycle. A detailed model motor describing actual layout geometry stator phase windings rotor bars is essential for simulation analysis under fault mode operation. The depends physical construction motor. Even a newly may have unequal phases, non uniform air-gap. This paper addresses experimental validation coupled circuit useful asymmetrical as well operation three...
We briefly discuss the fundamental of color space and compare some state-of-the-art image denoising methods in presence Gaussian noise. Specifically, we three leading techniques such as C-BM3D, OWT SURE-LET, LPG-PCA describe their performance terms PSNR. conduct several experiments, to recognize advantages disadvantages these methods. It is observed from comparison that C-BM3D achieves better PSNR at a reasonable computational complexity. The comprehensive study this paper will provide good...
Road traffic noise is likely the most thorough and inescapable kind of pollution in charge negative effects that are destructive to nature group health mankind. Residential area/towns close by roads additionally casualty issue, extraordinarily have high danger hearing loss due exposure. The Objectives present review were concentrate attributes survey predominance because on 52 people working 8 12 hours periphery NH 8E going through Una Town performing audiometric test. Consequence study...
The naturalness of the speech in any human being comes from his or her emotions. All beings deliver and construe messages with heavy use So there is a need to develop interface through which emotions embedded signal can be analyzed processed. There are many translation systems developed intent interpret inherent signals but lack processing as because lacuna their modeling depiction. main objective system retrieve interesting information like features, models so that retrieved knowledge...
The reduction in transistor size has led to the failure of conventional square-law devices describing Short Channel and Moderate Weak inversion devices. shortcomings these are addressed by g <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</inf> /I xmlns:xlink="http://www.w3.org/1999/xlink">d</inf> method that traverses between hand calculations circuit simulation. In this literature, a structured process for design Two-Stage Operational...