Lokesh Gopinath
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lokesh Gopinath has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Azad Ruhan Bevi
Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Chengalpattu, India
3 shared publications A. Ruhan Bevi
Department of Electronics and Communication Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, Tamil Nadu 603203, India
1 shared publication- Hari Unnikrishnan
Saveetha Engineering College
1 shared publication
Latest Publications
- 24 July 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
- Vol. 33 (05) , 549-558
A Hybrid Network with Multicategory Adversarial Feature Learning: McAFL Fusion
The integration of Near-Infrared and visible images is critical in fields such as surveillance, medical imaging, and remote sensing, necessitating high-quality image fusion. The proposed hybrid image fusion network develops a Near-Infrared and visible image fusion system using a multicategory adversarial mechanism within the feature space. Compared to current methods, this approach’s fusion rules are more rational and perform better. An autoencoder network, trained with spatial and channel attention, extracts feature and reconstructs images. A Generative Adversarial Network then derives fusion rules from the trained encoder’s feature space. The hybrid network includes a feature fusion network (generator) that combines features from the source image and a multiclassifier (discriminator) ensuring the fused features match the probability distribution of both Near-Infrared and visible modes. The trained decoder reconstructs the fused image, preserving salient features. Experimental results show the proposed hybrid network surpasses contemporary techniques like GTF, MDLatLRR, DenseFuse, FusionGAN, and U2Fusion in subjective quality.
- 24 July 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
- Vol. 33 (05) , 549-558
A Hybrid Network with Multicategory Adversarial Feature Learning: McAFL Fusion
The integration of Near-Infrared and visible images is critical in fields such as surveillance, medical imaging, and remote sensing, necessitating high-quality image fusion. The proposed hybrid image fusion network develops a Near-Infrared and visible image fusion system using a multicategory adversarial mechanism within the feature space. Compared to current methods, this approach’s fusion rules are more rational and perform better. An autoencoder network, trained with spatial and channel attention, extracts feature and reconstructs images. A Generative Adversarial Network then derives fusion rules from the trained encoder’s feature space. The hybrid network includes a feature fusion network (generator) that combines features from the source image and a multiclassifier (discriminator) ensuring the fused features match the probability distribution of both Near-Infrared and visible modes. The trained decoder reconstructs the fused image, preserving salient features. Experimental results show the proposed hybrid network surpasses contemporary techniques like GTF, MDLatLRR, DenseFuse, FusionGAN, and U2Fusion in subjective quality.
- Open Access
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (2) , 1593-1601
Two-scale decomposition and deep learning fusion for visible and infrared images
The paper focuses on the fusion of visible and infrared images to generate composite images that preserve both the thermal radiation information from the infrared spectrum and the detailed texture from the visible spectrum. The proposed approach combines traditional methods, such as two-scale decomposition, with deep learning techniques, specifically employing an autoencoder architecture. The source images are subjected to two-scale decomposition, which extracts high-frequency detail and low-frequency base information. Additionally, an algorithmic unravelling technique establishes a logical connection between deep neural networks and traditional signal processing algorithms. The model consists of two encoders for decomposition and a decoder after the unravelling operation. During testing, a fusion layer merges the decomposed feature maps, and the decoder generates the fused image. Evaluation metrics including entropy, average gradient, spatial frequency and standard deviation are employed to subjectively assess fusion quality. The proposed approach demonstrates promise for effectively combining visible and infrared imagery for various applications.
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (2) , 1593-1601
Open AccessTwo-scale decomposition and deep learning fusion for visible and infrared images
The paper focuses on the fusion of visible and infrared images to generate composite images that preserve both the thermal radiation information from the infrared spectrum and the detailed texture from the visible spectrum. The proposed approach combines traditional methods, such as two-scale decomposition, with deep learning techniques, specifically employing an autoencoder architecture. The source images are subjected to two-scale decomposition, which extracts high-frequency detail and low-frequency base information. Additionally, an algorithmic unravelling technique establishes a logical connection between deep neural networks and traditional signal processing algorithms. The model consists of two encoders for decomposition and a decoder after the unravelling operation. During testing, a fusion layer merges the decomposed feature maps, and the decoder generates the fused image. Evaluation metrics including entropy, average gradient, spatial frequency and standard deviation are employed to subjectively assess fusion quality. The proposed approach demonstrates promise for effectively combining visible and infrared imagery for various applications.
- 2 June 2024
- Published by Springer Nature
- p. 165-175
Anisotropic Guided Filtering and Multi-level Disintegration Method for NIR and Visible Image Fusion
- 2 June 2024
- Published by Springer Nature
- p. 165-175
Anisotropic Guided Filtering and Multi-level Disintegration Method for NIR and Visible Image Fusion
- 18 November 2023
- Published by Springer Nature
- p. 629-645
A Dimensionality Reduction Method for the Fusion of NIR and Visible Image
- 18 November 2023
- Published by Springer Nature
- p. 629-645
A Dimensionality Reduction Method for the Fusion of NIR and Visible Image