Ranjith V G

@niuniv.com

Assistant Professor and Head, Computer Science and Engineering
Noorul Islam Centre for Higher Education

Ranjith V G


               Download Compact PDF  
https://researchid.co/ranjith

EDUCATION

BSc Computer Science
MSc Computer Science
M Tech Computer and Information Technology
PhD Computer Science and Engineering

RESEARCH INTERESTS

Image Processing, CBIR
9

Scopus Publications

27

Scholar Citations

3

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Liver Segmentation Using Modified CAG-SwinUNet with Explainability
    Kumar S. S., Vinod Kumar R. S., Ranjith V. G.
    Journal of Biomedical Photonics and Engineering, 2026
    Accurate liver segmentation from computed tomography (CT) images is crucial for clinical applications such as tumor detection and surgical planning but remains challenging due to anatomical complexity and imaging variability. Existing deep learning models, struggle with ambiguous liver boundaries, noise sensitivity, and weak feature integration across scales, leading to segmentation errors. This study introduces Cross-Attention Gate-Shifted Window U-Net (CAG-SwinUnet), an enhanced Swin-UNet variant that incorporates a Cross-Attention Gate (CAG) in skip connections to selectively refine feature fusion. Unlike traditional concatenation, CAG dynamically enhances encoder features based on decoder context, integrating residual connections and output projection to balance local and global information. Extensive evaluation on Liver Tumor Segmentation (LiTS) and Segmentation of the Liver Competition 2007 (SLIVER07) demonstrates state-of-the-art performance, achieving 97.75% Dice Similarity Coefficient (DSC) and 2.40 mm Hausdorff Distance (HD) on LiTS, and 96.65% DSC and 3.10 mm HD on SLIVER07, respectively. To enhance explainability, gradient-weighted class activation mapping, provide visual insights into the model’s decision-making process, ensuring transparency and reliability in liver segmentation.
  • Decentralized Blockchain-Powered Smart Contract Based Money Lending System
    M. Kavitha Margret, V. Ranjith, M. Sakthivel, P. Yuven Krishna
    Lecture Notes in Electrical Engineering, 2026
  • Age Classification for Safe Search Toggling using Face Detection and Swin Tranformers: A Deep Learning Approach
    Ramesh Dadi, Vanga Ranjith, Mohammed Akramuddin, Sanka Santhosh Kumar, Vighnesh Bachwal
    Proceedings of 6th International Conference on Expert Clouds and Applications Icoeca 2026, 2026
    Correct user age classification from face images is critical to allowing automated content filtering, especially in web browsing settings to shield minors from objectionable content. Conventional approaches tend to be imprecise with variable lighting and poses. This work suggests a deep learning framework with Swin Transformers combined with face detection for age classification into minor (less than 18) or major (18 and older) categories. A pre-trained Swin Transformer model (microsoft/swin-tiny-patch4-window7-224) was trained on a balanced dataset of about 9,975 facial images taken from major and minor folders and obtained 0.80 accuracy on the test set. The system integrates Haar Cascade for detecting initial faces and Swin Transformer for feature extraction and classification, trained with batch size 16 on five epochs using AdamW optimizer at a learning rate of 1e-5. After classification, the system switches safe search modes automatically in a browser extension through real-time webcam inference. The generality of the model was tested through ablation studies among pretrained and scratch-trained versions, with the pretrained version performing better by being more accurate. In this work, a new use case of Swin Transformers to apply real-time age-gating control is presented, presenting a scalable solution for user safety in online platforms, with the option for ONNX export for easy deployment.
  • Convolution neural network-AlexNet with gazelle optimization algorithm-based software defect prediction
    S. V. Gayetri Devi, V. G. Ranjith, P. Ramani, A. Kavitha
    Knowledge and Information Systems, 2025
  • Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images
    S.S. Kumar, R.S. Vinod Kumar, V.G. Ranjith, S. Jeevakala, S. Sajithra Varun
    Computers and Electrical Engineering, 2024
  • Survey on Fusion of Audiovisual Information for Multimedia Event Recognition
    S. L. Jayalakshmi, S. L. Jothilakshmi, V. G. Ranjith, Siddharth Jain
    Lecture Notes in Electrical Engineering, 2022
  • Color-texture based feature modeling for content-based video retrieval
    Journal of Advanced Research in Dynamical and Control Systems, 2019
  • Color-texture based feature modeling for content based image retrieval
    Journal of Advanced Research in Dynamical and Control Systems, 2019
  • Multi resolution feature combined with ODBTC technique for robust CBIR system
    V.G. Ranjith, M.K. Jeyakumar, S. Palanikumar
    International Journal of Signal and Imaging Systems Engineering, 2018
    Content based image retrieval (CBIR) is a system that retrieves a set of images that most resembles the query image. The technology is used in many applications. Currently used image content retrieval method is ordered-dither block truncation coding (ODBTC). This method is used to produce image content descriptors. In this system, it gives only an average accuracy of 70.5%. Our aim is to create a more robust and accurate system for CBIR. For this purpose in addition to colour cooccurrence feature (CCF) and bit pattern features (BPF), contourlet and wavelet features from the query image is extracted for image retrieval process. In our experiment the system is first tested with ODBTC and wavelet and then ODBTC and contourlet. The results obtained with ODBTC and contourlet is more accurate and produced accuracy 91.5%. The dataset used for our experiment is CorelDB.

RECENT SCHOLAR PUBLICATIONS

  • Liver Segmentation Using Modified CAG-SwinUNet with Explainability
    SS Kumar, VK RS, VG Ranjith
    Journal of Biomedical Photonics & Engineering 12 (1), 010303 , 2026
    2026.0
  • Convolution neural network-AlexNet with gazelle optimization algorithm-based software defect prediction
    SV Devi, VG Ranjith, P Ramani, A Kavitha
    KNOWLEDGE AND INFORMATION SYSTEMS 67 (7), 6285-6306 , 2025
    2025.0
    Citations: 4
  • Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images
    SS Kumar, RSV Kumar, VG Ranjith, S Jeevakala, SS Varun
    Computers and Electrical Engineering 117, 109248 , 2024
    2024.0
    Citations: 16
  • Survey on Fusion of Audiovisual Information for Multimedia Event Recognition
    SL Jayalakshmi, SL Jothilakshmi, VG Ranjith, S Jain
    Artificial Intelligence and Technologies: Select Proceedings of ICRTAC-AIT … , 2021
    2021.0
  • Color-texture based Feature Modeling for Content-based Video Retrieval
    SP V.G. Ranjith, M.K. Jeyakumar
    Jour of Adv Research in Dynamical & Control Systems 11 (04-Special Issue … , 2019
    2019.0
  • Color-Texture based Feature Modeling for Content based Image Retrieval
    SP V.G. Ranjith, M.K. Jeyakumar
    Jour of Adv Research in Dynamical & Control Systems 11 (04-Special Issue … , 2019
    2019.0
  • Multi resolution feature combined with ODBTC technique for robust CBIR system
    VG Ranjith, MK Jeyakumar, S Palanikumar
    International Journal of Signal and Imaging Systems Engineering 11 (4), 237-245 , 2018
    2018.0
    Citations: 1
  • A singular point detection based fingerprint representation and matching algorithm:A Survey
    VGR J. P. Jeyan, M. K. Jeyakumar
    International Journal of Advanced Research Trends in Engineering and … , 2016
    2016.0
  • Automatic machine learning forgery detection based on SVM classifier
    SL Jothilakshmi, VG Ranjith
    IJCSIT) InternationalJournal of Computer Science and Information … , 2014
    2014.0
    Citations: 4
  • Block truncation coding for cbir systems using halftoning based techniques in compressed images: a survey,(2016)
    VG Ranjith
    IJCEA 10 (9), 15-25 , 0
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images
    SS Kumar, RSV Kumar, VG Ranjith, S Jeevakala, SS Varun
    Computers and Electrical Engineering 117, 109248 , 2024
    2024.0
    Citations: 16
  • Convolution neural network-AlexNet with gazelle optimization algorithm-based software defect prediction
    SV Devi, VG Ranjith, P Ramani, A Kavitha
    KNOWLEDGE AND INFORMATION SYSTEMS 67 (7), 6285-6306 , 2025
    2025.0
    Citations: 4
  • Automatic machine learning forgery detection based on SVM classifier
    SL Jothilakshmi, VG Ranjith
    IJCSIT) InternationalJournal of Computer Science and Information … , 2014
    2014.0
    Citations: 4
  • Block truncation coding for cbir systems using halftoning based techniques in compressed images: a survey,(2016)
    VG Ranjith
    IJCEA 10 (9), 15-25 , 0
    Citations: 2
  • Multi resolution feature combined with ODBTC technique for robust CBIR system
    VG Ranjith, MK Jeyakumar, S Palanikumar
    International Journal of Signal and Imaging Systems Engineering 11 (4), 237-245 , 2018
    2018.0
    Citations: 1
  • Liver Segmentation Using Modified CAG-SwinUNet with Explainability
    SS Kumar, VK RS, VG Ranjith
    Journal of Biomedical Photonics & Engineering 12 (1), 010303 , 2026
    2026.0
  • Survey on Fusion of Audiovisual Information for Multimedia Event Recognition
    SL Jayalakshmi, SL Jothilakshmi, VG Ranjith, S Jain
    Artificial Intelligence and Technologies: Select Proceedings of ICRTAC-AIT … , 2021
    2021.0
  • Color-texture based Feature Modeling for Content-based Video Retrieval
    SP V.G. Ranjith, M.K. Jeyakumar
    Jour of Adv Research in Dynamical & Control Systems 11 (04-Special Issue … , 2019
    2019.0
  • Color-Texture based Feature Modeling for Content based Image Retrieval
    SP V.G. Ranjith, M.K. Jeyakumar
    Jour of Adv Research in Dynamical & Control Systems 11 (04-Special Issue … , 2019
    2019.0
  • A singular point detection based fingerprint representation and matching algorithm:A Survey
    VGR J. P. Jeyan, M. K. Jeyakumar
    International Journal of Advanced Research Trends in Engineering and … , 2016
    2016.0