A5101778558- Advanced Image Processing Techniques
- Image and Signal Denoising Methods
- Handwritten Text Recognition Techniques
- Advanced Vision and Imaging
- Image Processing Techniques and Applications
- Advanced Image Fusion Techniques
- Advanced Image and Video Retrieval Techniques
- Vehicle License Plate Recognition
- Natural Language Processing Techniques
- Image Retrieval and Classification Techniques
- Digital Media Forensic Detection
- Remote-Sensing Image Classification
- Chaos-based Image/Signal Encryption
- Advanced Steganography and Watermarking Techniques
- Authorship Attribution and Profiling
- COVID-19 diagnosis using AI
- Artificial Intelligence in Healthcare
- Image Enhancement Techniques
- Generative Adversarial Networks and Image Synthesis
- Image and Video Quality Assessment
- Image Processing and 3D Reconstruction
- Medical Image Segmentation Techniques
- Infrared Target Detection Methodologies
- Robotics and Automated Systems
- Text and Document Classification Technologies
Bennett University
2022-2024
Indian Institute of Technology Kharagpur
2024
Jaipur National University
2015-2022
Manipal University Jaipur
2019-2020
Central Electronics Engineering Research Institute
2017-2019
Seoul National University
2019
Indian Institute of Technology Delhi
2015-2017
University of Allahabad
2016
National Institute of Technology Hamirpur
2011
This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus proposed solutions and results. The had 4 tracks. Track 1 employed standard bicubic downscaling setup, while Tracks 2, 3 realistic unknown downgrading operators simulating camera acquisition pipeline. were learnable through provided pairs high train images. tracks 145, 114, 101, 113 registered participants, resp., 31 teams competed final testing...
This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., recovery of whole-scene hyperspectral (HS) information a 3-channel image. The was divided into 2 tracks: "Clean" track sought HS noiseless images obtained known response function (representing spectrally-calibrated camera) while "Real World" challenged participants to recover cubes JPEG-compressed generated by an unknown function. To facilitate challenge, BGU Hyperspectral Image Database [4]...
Hyperspectral cameras are used to preserve fine spectral details of scenes that not captured by traditional RGB comprehensively quantizes radiance in images. Spectral provide additional information improves the performance numerous image based analytic applications, but due high hyperspectral hardware cost and associated physical constraints, images easily available for further processing. Motivated deep learning various computer vision we propose a 2D convolution neural network 3D...
Sensors 4.0 are indispensable components of Industry 4.0. Ultrasonic sensors play a crucial role for enabling automation in the current era The purpose this study is to explore potential using affordable and accessible technology tackle contemporary spatial management challenges. proposed system caters growing need effective personal space due increasing population density offers practical solution remote monitoring supervision occupancy spaces. An independent proximity sensing developed by...
This paper reviews the first NTIRE challenge on video super-resolution (restoration of rich details in low-resolution frames) with focus proposed solutions and results. A new REalistic Diverse Scenes dataset (REDS) was employed. The divided into 2 tracks. Track 1 employed standard bicubic downscaling setup while had realistic dynamic motion blurs. Each competition 124 104 registered participants. There were total 14 teams final testing phase. They gauge state-of-the-art super-resolution.
Image quality assessment is a challenging computer vision task due to the lack of corresponding reference (pristine) images. This no-reference bottleneck has been tackled with utilisation subjective mean opinion scores (MOS) termed as supervised blind image (BIQA) methods. However, inaccessible score scenarios limits their applicability. To relieve these limitations, we propose employ reconstruction based learning trained only on pristine permits an implicit distribution images and deviation...
This paper reviews the NTIRE challenge on image colorization (estimating color information from corresponding gray image) with focus proposed solutions and results. It is first of its kind. The had 2 tracks. Track 1 takes a single as input. In 2, in addition to input image, some seeds (randomly samples latent are also provided for guiding process. operators were learnable through pairs training images. tracks 188 registered participants, 8 teams competed final testing phase.
Recognizing text from degraded and low-resolution document images is still an open challenge in the vision community. Existing recognition systems require a certain resolution fails if of or heavily noisy. This paper presents end-to-end trainable deep-learning based framework for joint optimization enhancement recognition. We are using generative adversarial network (GAN) to perform image denoising followed by deep back projection (DBPN) super-resolution use these super-resolved features...
This paper proposes ontology based conceptual framework for storage and retrieval of Digitized Museum Artifacts. The proposed uses structure automatic image annotation. It supports semantic by combining ontological concepts, visual textual features automatically extracted from images their descriptions. Ontology-driven analysis module generates annotation domain objects. also reports a new dataset designed its evaluation. consists displayed in various galleries Allahabad museum along with...
Removed.
This paper presented a comprehensive survey of image thresholding methodologies and categorise them under uniform notation, indicate their differences or similarities, finally as basis for performance comparison. Images have been categorised into six groups according to the information they are exploiting, such as, histogram shape-based methods, clusteringbased entropy-based object attribute-based spatial methods local methods. In total 44 binarisation summarised.
Our paper is motivated from the advancement in deep learning algorithms for various computer vision problems. We are proposing a novel end-to-end based framework image super-resolution. This simultaneously calculates convolutional features of low-resolution (LR) and high-resolution (HR) patches learns non-linear function that maps these LR to their corresponding HR features. Here, proposed super-resolution architecture termed as coupled auto-encoder (CDCA) which provides state-of-the-art...
Recognizing text from noisy low-resolution (LR) images is extremely challenging and an open problem for the computer vision community. Super-resolving a LR image results in High Resolution (HR) image, as super-resolution (SR) leads to spatial correlation noise, further cannot be de-noised successfully. Traditional noise-resilient methods utilize denoising algorithm prior SR but process loss of some high frequency details, output HR has missing information (texture details edges). This paper...
Convolutional neural network based architectures have achieved decent perceptual quality super resolution on natural images for small scaling factors (2X and 4X). However, image super-resolution large magnication (8X) is an extremely challenging problem the computer vision community. In this paper, we propose a novel Improved Residual Gradual Up-Scaling Network (IRGUN) to improve of super-resolved magnification factor. IRGUN has Upsampling Residue-based Enhancment (GUREN) which comprises...
A different and efficient method of image hiding is proposed here. It based on unitary similarity transformation, involving calculation eigen values vectors a matrix then transforming it into diagonal matrix. Only secret needs to be transformed embedded the cover image. Inverse transformation can used recover from stego-image. The vector acts as decryption key. This algorithm simple easily implemented. greatly improve security system, robustness image-hiding. quality stego-image recovered...