Rajoo Pandey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rajoo Pandey has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Balla Pavan Kumar
Department of Electronics and Communication Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India
9 shared publications - Arvind Kumar
National Institute of Technology
8 shared publications Umesh Ghanekar
ECE Department; NIT Kurukshetra (Haryana), INDIA
7 shared publications- Chhagan Charan
National Institute of Technology
5 shared publications - Rajiv Verma
National Institute of Technology
4 shared publications Arvind Kumar
3 shared publications
Latest Publications
- 22 March 2026
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 45 (10) , 1-22
A Multi-branch Generative Adversarial Network for Single Image Super-Resolution with Enhanced Edge Preservation
- 22 March 2026
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 45 (10) , 1-22
A Multi-branch Generative Adversarial Network for Single Image Super-Resolution with Enhanced Edge Preservation
- 1 December 2025
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 35 (4) , 674-683
Two-Stage Internal Prior Generative Adversarial Network for Single Image Superresolution
In generative adversarial network based single image superresolution, most of the networks are using residual-in-residual dense block. However, it cannot improve the content and perceptual quality simultaneously. To improve upon, this paper presents a two-stage internal prior generative adversarial network which improves both reconstruction accuracy and visual quality in the superresolved image. The first stage uses an optimized block for image content, whereas the second stage uses an optimized block for visual content. The first stage is further improved by using attention block and fractal connections to leverage prior information in the network. The experimental results highlight the effectiveness of the proposed network in terms of the peak signal-to-noise ratio, structural similarity index measure, and learned perceptual image patch similarity and demonstrate its superiority over other state-of-the-art models.
- 1 December 2025
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 35 (4) , 674-683
Two-Stage Internal Prior Generative Adversarial Network for Single Image Superresolution
In generative adversarial network based single image superresolution, most of the networks are using residual-in-residual dense block. However, it cannot improve the content and perceptual quality simultaneously. To improve upon, this paper presents a two-stage internal prior generative adversarial network which improves both reconstruction accuracy and visual quality in the superresolved image. The first stage uses an optimized block for image content, whereas the second stage uses an optimized block for visual content. The first stage is further improved by using attention block and fractal connections to leverage prior information in the network. The experimental results highlight the effectiveness of the proposed network in terms of the peak signal-to-noise ratio, structural similarity index measure, and learned perceptual image patch similarity and demonstrate its superiority over other state-of-the-art models.
- 17 September 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (06)
Hazy Input Upgradation and Multi-Feature Fusion-based Multi-Scale Residual Neural Network for Haze Removal
Many algorithms were developed for haze removal in digital images. However, the spatial haze features are not effectively utilized and extracted in many dehazing methods, which produce under-exposure and over-saturation. Hence, this paper presents a novel model called multi-feature fusion-based multi-scale residual convolutional neural network (MFF-MSRNN) to overcome these challenges. First, the hazy input upgradation approach is developed that considers the spatial haze features as an additional entity along with the hazy input image, and provides it as input to MFF-MSRNN. Then the feature extraction is performed as part of MSRNN to effectively obtain the low-haze, moderate-haze and high-haze features of the hazy input image. The proposed MFF-MSRNN model is trained and tested with multiple databases, unlike previous approaches, and delivers improved outcomes in comparison to previous haze removal techniques.
- 17 September 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (06)
Hazy Input Upgradation and Multi-Feature Fusion-based Multi-Scale Residual Neural Network for Haze Removal
Many algorithms were developed for haze removal in digital images. However, the spatial haze features are not effectively utilized and extracted in many dehazing methods, which produce under-exposure and over-saturation. Hence, this paper presents a novel model called multi-feature fusion-based multi-scale residual convolutional neural network (MFF-MSRNN) to overcome these challenges. First, the hazy input upgradation approach is developed that considers the spatial haze features as an additional entity along with the hazy input image, and provides it as input to MFF-MSRNN. Then the feature extraction is performed as part of MSRNN to effectively obtain the low-haze, moderate-haze and high-haze features of the hazy input image. The proposed MFF-MSRNN model is trained and tested with multiple databases, unlike previous approaches, and delivers improved outcomes in comparison to previous haze removal techniques.
- 22 August 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 236-242
Scale invariable hybrid-attention Generative Adversarial Network for Single Image Super Resolution
- 22 August 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 236-242
Scale invariable hybrid-attention Generative Adversarial Network for Single Image Super Resolution
- 16 December 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
A Novel Three-Stage Dehazing Model Using Improved Auto-Color Transfer Method, Adaptive Dehazing, and Adaptive Contrast Enhancement
The problems of underexposure, under-detail-enhancement and residual haze are detected in the previous dehazing techniques. These issues occur due to different reasons and are highly difficult to be resolved using a single algorithm. Therefore, a three-stage dehazing model (TSDM) is proposed in this paper using pre-processing, dehazing and post-processing modules. The improved auto-color transfer (IACT) approach is presented as part of pre-processing to efficiently enhance the hazy image to overcome underexposure. Also, adaptive dehazing (AD) is developed in this work which considers the global characteristics of the hazy image as a parameter, to adaptively enhance the details. Moreover, adaptive contrast enhancement (ACE) is proposed as a post-processing operation that adaptively fuses the dehazed image and its contrast-enhanced image to effectively improve the contrast. However, the IACT operation is performed on the hazy image only when dark regions are detected. Similarly, the ACE is performed only when a dehazed image exhibits residual haze. Based on these prior conditions, the proposed work can be implemented in four distinct ways i.e. using only the AD technique; using IACT and AD approaches, using AD and ACE methods, and using all IACT, AD and ACE algorithms. The proposed TSDM is experimentally analyzed using many databases which shows improved results compared to previous techniques.
- 16 December 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
A Novel Three-Stage Dehazing Model Using Improved Auto-Color Transfer Method, Adaptive Dehazing, and Adaptive Contrast Enhancement
The problems of underexposure, under-detail-enhancement and residual haze are detected in the previous dehazing techniques. These issues occur due to different reasons and are highly difficult to be resolved using a single algorithm. Therefore, a three-stage dehazing model (TSDM) is proposed in this paper using pre-processing, dehazing and post-processing modules. The improved auto-color transfer (IACT) approach is presented as part of pre-processing to efficiently enhance the hazy image to overcome underexposure. Also, adaptive dehazing (AD) is developed in this work which considers the global characteristics of the hazy image as a parameter, to adaptively enhance the details. Moreover, adaptive contrast enhancement (ACE) is proposed as a post-processing operation that adaptively fuses the dehazed image and its contrast-enhanced image to effectively improve the contrast. However, the IACT operation is performed on the hazy image only when dark regions are detected. Similarly, the ACE is performed only when a dehazed image exhibits residual haze. Based on these prior conditions, the proposed work can be implemented in four distinct ways i.e. using only the AD technique; using IACT and AD approaches, using AD and ACE methods, and using all IACT, AD and ACE algorithms. The proposed TSDM is experimentally analyzed using many databases which shows improved results compared to previous techniques.
- 1 December 2024
- Published by Springer Nature
- p. 381-388
A Single-Image Dehazing Approach Using Brightness Enhancement and Double Transmission Maps
- 1 December 2024
- Published by Springer Nature
- p. 381-388
A Single-Image Dehazing Approach Using Brightness Enhancement and Double Transmission Maps
- 1 March 2024
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 100
A 4-channelled hazy image input generation and deep learning-based single image dehazing
- 1 March 2024
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 100
A 4-channelled hazy image input generation and deep learning-based single image dehazing
- Open Access
- 8 February 2024
- Published by Springer Nature
- p. C1
Correction to: A Very Deep Adaptive Convolutional Neural Network (VDACNN) for Image Dehazing
- 8 February 2024
- Published by Springer Nature
- p. C1
Open AccessCorrection to: A Very Deep Adaptive Convolutional Neural Network (VDACNN) for Image Dehazing
- 3 December 2023
- Published by Springer Nature
- p. 41-47
A Very Deep Adaptive Convolutional Neural Network (VDACNN) for Image Dehazing
- 3 December 2023
- Published by Springer Nature
- p. 41-47
A Very Deep Adaptive Convolutional Neural Network (VDACNN) for Image Dehazing
- 14 November 2023
- Published by Springer Nature in Sādhanā
- Vol. 48 (4) , 1-12
Probabilistic algebraic attack on plantlet lightweight stream cipher
- 14 November 2023
- Published by Springer Nature in Sādhanā
- Vol. 48 (4) , 1-12
Probabilistic algebraic attack on plantlet lightweight stream cipher