Engineering, Computer Science, Artificial Intelligence, Computer Vision and Pattern Recognition
52
Scopus Publications
430
Scholar Citations
11
Scholar h-index
12
Scholar i10-index
Scopus Publications
A Comparative Study of Deep Learning Models for Photo-to-Sketch Recognition with CAT Preprocessing Philomina Princiya Mascarenhas, Sannidhan M S, Aashna Mathias, Dabis Camero, Jason Elroy Martis Proceedings of 5th International Conference on Communication Computing and Electronics Systems Iccces 2026, 2026 In recent years, facial recognition systems have become widely used in many applications, especially in biometrics and law enforcement. Advances in the field have led to the development of pre-trained deep learning models that achieve good accuracy even when training data is limited. Earlier studies have shown that these models perform well on original photographs but struggle when the input comes from other domains such as sketches. In crime investigations, officers often have only the suspect's sketch, and using pre-trained models directly on such sketches gives low accuracy because important texture and lighting details are missing. To address this issue, our study applies a Contour Accentuation Technique (CAT) to enhance the texture information in sketches. This improves the clarity of sketch features and supports better learning by deep learning models. To evaluate the effectiveness of CAT, we conduct a comparative study using multiple recognition models with and without CAT. The models are tested under a unified setup with cross-validation. The results show that the use of CAT improves face recognition performance, with an average accuracy gain of 7.7%. The working model of our paper is found in https://github.com/Princiya1990/faceRecognition.
An Approach For The Enhancement Of Facial Images Captured Under Low Light Aishwarya Salian, M.S. Sannidhan, Jason Elroy Martis 2025 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies Inspect 2025, 2025 Due to poor lighting conditions, images captured in outdoor scenes can of reduced in quality. Since quality is a must and Low-light conditions offer any, we choose image enhancement to create a much more appealing picture. One such case is Criminal identification. When a crime takes place in dark and dull places it is very difficult to identify the people involved or even spectate the event. The paper provides details on the low-light facial image enhancement which can be done by using the approach of estimating illumination map. This approach is a spatialdomain enhancement which operates on particular pixel values. The initial illumination map is processed and is used for enhancing the low-light facial image according to simplified Retinex model. The result will be quality images.
Automated Hive Image Analysis: A Comparative study on Machine Learning Approach for Bee Detection and Classification Pratheeksha Hegde N, Jason Elroy Martis, Sannidhan M S, Dabis Camero Proceedings of the 9th International Conference on Electronics Communication and Aerospace Technology Iceca 2025, 2025 Honeybee populations are essential for pollination and agricultural productivity but face increasing threats from parasites, pesticides, and climate change. To address the need for effective hive monitoring, this study introduces a deep learning-based system for automated bee detection and classification. Utilizing the YOLO (You Only Look Once) architecture, the proposed method performs real-time identification of various bee types, including worker bees, pollen carriers, hornets, and queen bees. The system consists of four stages: object detection, bee isolation, feature extraction, and classification. A dataset of 5,025 annotated hive images was used to train and compare multiple YOLO versions. Among them, YOLOv8 achieved the highest accuracy—98.87% at 100 training epochs. Evaluation metrics such as confusion matrices and performance curves confirm the system's effectiveness in distinguishing between bee categories. The proposed approach offers a scalable, accurate, and efficient solution for intelligent beekeeping. Future work will focus on real-time behavior analysis, handling environmental variability, and deployment on low-power edge devices.
Evaluating Performance of LG-CycleGAN for Photo-Sketch Generation Niveditha Chatra, Sannidhan M S, Jason Elroy Martis, Pradeep Nazareth Proceedings of 2025 International Conference on Intelligent Systems and Pioneering Innovations in Robotics and Electric Mobility Transforming Mobility and Automation Through Intelligent Engineering Inspire 2025, 2025 Human faces are the most important part of the daily life because they are the way we connect and recognise the people on everyday basis. Face photo-sketch synthesis and identification has many applications in the modern world, which include law enforcement, improving security systems and making creative digital art or animation. In recent times, baseline CycleGAN performance has been enhanced by different improvements, but they have not been explicitly considered in maintaining facial geometry and finer feature mapping. In this paper, we have proposed the Bidirectional Photo-Sketch CycleGAN with the Landmark-Guided Style Injection model to improve the structural aspect of the face. It helps in maintaining the positions of significant facial landmarks like eyes, mouth and nose, which in return helps in retaining the form and texture of the face better when translating between photos and sketches. Both the sketch-to-photo and photo-to-sketch tasks are used in the experiments using the CUHK dataset. The results obtained from the proposed model show SSIM scores of 0.76 for photos and 0.70 for sketches, which are better than those achieved by the baseline CycleGAN model.
Photo-to-Sketch Transformation using Contour Accentuation for High-Quality Outputs Philomina Princiya Mascarenhas, Sannidhan M S, Niveditha Niveditha, Dabis Camero, Jason Elroy Martis Proceedings 3rd International Conference on Self Sustainable Artificial Intelligence Systems Icssas 2025, 2025 Sketches play a vital role in forensic investigations and other fields but creating them is a time-consuming process that relies heavily on human effort. We have explored various image processing techniques to assist in sketch generation and research has shown that production of high-quality sketches from photographs poses a significant challenge. This article introduces a Contour Accentuation Technique (CAT), which is a method designed to improve composite sketch generation and enhance facial feature visibility in sketches. The proposed works in four key steps namely Grayscaling, Blending, Contrast Correction and Edge Enhancement. Also, the technique removes color information, helping the system focus on intensity variations by sharpening the edges and reducing noise. It also improves contrast thereby enhancing the visibility of facial contours by adjusting intensity levels. Experimental results show significant improvements: the NIQE score decreased from 3.39 to 2.76, SSIM increased from 0.82 to 0.88, and Absolute Error (AE) dropped from 89.26 to 71.41, confirming the effectiveness of CAT in improving sketch clarity and quality.
Improving acne severity detection: a GAN framework with contour accentuation for image deblurring Philomina Princiya Mascarenhas, M. S. Sannidhan, Ancilla J. Pinto, Dabis Camero, Jason Elroy Martis Frontiers in Bioinformatics, 2025 Teledermatology, a growing field of telemedicine, is widely used to diagnose skin conditions like acne, especially in young adults. Accurate diagnosis depends on clear images, but blurring is a common issue in most images. In particular, for acne images, it obscures acne spots and facial contours, leading to inaccurate diagnosis. Traditional methods to address blurring fail to recover fine details, making them unsuitable for teledermatology. To resolve this issue, the study proposes a framework based on generative networks. It comprises three main steps: the Contour Accentuation Technique, which outlines facial features to create a blurred sketch; a deblurring module, which enhances the sketch’s clarity; and an image translator, which converts the refined sketch into a color photo that effectively highlights acne spots. Tested on Acne Recognition Dataset, the framework achieved an SSIM of 0.83, a PSNR of 22.35 dB, and an FID score of 10.77, demonstrating its ability to produce clear images for accurate acne diagnosis. Further, the details of research can be found on the project homepage at: https://github.com/Princiya1990/CATDeblurring.
OPTIMIZATION OF HEALTHCARE SERVICE DELIVERY USING DEEP GENETIC ALGORITHM GIRIMURUGAN B, Ashvin T.K, Hemalatha T, Riyaz Hussain Sk, Sannidhan M S, UMAYA SALMA Salma Informing Science, 2025 Aim/Purpose: The main goal of this work is a new framework that combines genetic algorithms with deep learning. The delivery of healthcare services will be optimized as the aim of this research. Background: Optimizing the provision of healthcare services is essential to ensuring that patients get suitable and timely treatments and materials. Methodology: This work presents a new framework for DGA-based healthcare service delivery optimization by the application of this methodology. The procedure consists of two stages: training a deep neural network to assess the feasibility of possible solutions and encoding the problem space into a format appropriate for genetic operations. The neural network evaluations are used as the guiding principle as the genetic algorithm iteratively creates a population of solutions by selection, crossover, and mutation. Contribution: The main contribution of this work is the solution of the optimization issues related to the provision of healthcare services by combining deep learning and genetic algorithms. Ultimately, we want to improve patient outcomes and resource use by leveraging the potential of DGAs to improve the efficacy and efficiency of healthcare systems. Findings: The results of laboratory experiments show that the proposed approach is successful in optimizing the provision of healthcare services. The proposed DGAs enable more high-quality solutions than conventional optimization methods. Recommendation for Researchers: This work presents a novel framework that uses deep genetic algorithms (DGAs) to effectively optimize the provision of healthcare services and address these issues. Future Research: This work can be enhanced using several deep-learning algorithms to achieve better accuracy and performance.
Detection and classification of peripheral plasmodium parasites in blood smears using filters and machine learning algorithms Ceur Workshop Proceedings, 2023
A comprehensive review on various state-of-the-art techniques for image enhancement International Journal of Engineering and Technology Uae, 2018
A comparative analysis of quality metrics between different image enhancement techniques for facial sketches International Journal of Engineering and Technology Uae, 2018
DANE: An inbuilt security extension C. Aishwarya, Raghuram M A, Sachin Hosmani, M.S. Sannidhan, Balaji Rajendran, K. Chandrasekaran, B.S. Bindhumadhava Proceedings of the 2015 International Conference on Green Computing and Internet of Things Icgciot 2015, 2016
A Comparative Study of Deep Learning Models for Photo-to-Sketch Recognition with CAT Preprocessing PP Mascarenhas, MS Sannidhan, A Mathias, D Camero, JE Martis 2026 5th International Conference on Communication, Computing and … , 2026 2026
Evaluating Performance of LG-CycleGAN for Photo-Sketch Generation N Chatra, MS Sannidhan, JE Martis, P Nazareth 2025 International Conference on Intelligent Systems and Pioneering … , 2025 2025
An Approach For The Enhancement Of Facial Images Captured Under Low Light A Salian, MS Sannidhan, JE Martis 2025 IEEE International Conference on Intelligent Signal Processing and … , 2025 2025
Computer Vision System for Real-Time Nasal-Jaw Distance Measurement in Dental Applications JE Martis, MS Sannidhan, VN Salian, VK Ronith, I Pavan 2025 10th International Conference on Communication and Electronics Systems … , 2025 2025
Empowering Sustainable Agriculture Through IoT and Multimodal Recommendation Systems: A Deep Learning Approach JE Martis, MS Sannidhan, CV Aravinda Internet of Things and Analytics for Agriculture, Volume 4, 73-100 , 2025 2025
Photo-to-Sketch Transformation using Contour Accentuation for High-Quality Outputs PP Mascarenhas, MS Sannidhan, N Niveditha, D Camero, JE Martis 2025 3rd International Conference on Self Sustainable Artificial … , 2025 2025 Citations: 2
Improving acne severity detection: a GAN framework with contour accentuation for image deblurring PP Mascarenhas, MS Sannidhan, AJ Pinto, D Camero, JE Martis Frontiers in Bioinformatics 5, 1485797 , 2025 2025 Citations: 4
Optimization of healthcare service delivery using deep genetic algorithm B Girimurugan, TK Ashvin, T Hemalatha, RH Sk, MS Sannidhan, ... Informing Science 28, 3 , 2025 2025 Citations: 1
Exploring Machine Learning and Deep Learning Models for Effective Sentiment Analysis on Twitter P Hegde, JE Martis, RR Bangera 2024 9th International Conference on Communication and Electronics Systems … , 2024 2024
Lightweight Cryptographic Authentication Using Facial Landmarks and LFSR for IoT Security MS Sannidhan, JE Martis, P Hegde, C Ballal 2024 International Conference on Computing, Semiconductor, Mechatronics … , 2024 2024
Deep Learning Based Covid-19 Diagnosis and Severity Assessment Using Computed Tomography Imaging S Namratha, K Hitha, MS Sannidhan 2024 International Conference on Integrated Intelligence and Communication … , 2024 2024
Genetic algorithms and deep learning for unique facial landmark-based key generation MS Sannidhan, JE Martis, KN Pallavi, V Ravi, HL Gururaj, TJ Alahmadi Computers and Electrical Engineering 118, 109427 , 2024 2024 Citations: 3
Novel hybrid quantum architecture-based lung cancer detection using chest radiograph and computerized tomography images JE Martis, S MS, B R, AM Mutawa, M Murugappan Bioengineering 11 (8), 799 , 2024 2024 Citations: 30
Precision sketching with de-aging networks in forensics JE Martis, MS Sannidhan, N Pratheeksha Hegde, L Sadananda Frontiers in Signal Processing 4, 1355573 , 2024 2024 Citations: 8
A swarm‐optimized microbial colony counter S MS, JE Martis, S Krivic, S KB, P Nazareth Expert Systems 41 (3), e13510 , 2024 2024 Citations: 2
Enhancing Automotive Safety through Advanced Human Action Recognition Techniques. CV Aravinda, MS Sannidhan, S Aswath, J Shetty, BC Arjun ATAIT, 13-24 , 2024 2024
Application of Active Learning Technique with CNN for the Classification of Microscopic Breast Cancer Images N Pratheeksha Hegde, JE Martis, MS Sannidhan, CV Aravinda, ... International Conference on Business Intelligence and Information Technology … , 2023 2023
Predicting Citrus Limon Maturity with Precision Using Transfer Learning MS Sannidhan, JE Martis, MV Suhas 2023 International Conference on Recent Advances in Information Technology … , 2023 2023 Citations: 4
Automated Exposure of Colorimetric Fluctuations in Aspergillus Flavus to Permit Feasible Extraction of Antibiotics P Nazareth, MS Sannidhan, JE Martis, P Hegde 2023 IEEE International Conference on Distributed Computing, VLSI … , 2023 2023
Handwritten Kannada character recognition using convolutional neural networks and transfer learning SB Madhu, CV Aravinda, MS Sannidhan Journal of Physics: Conference Series 2571 (1), 012012 , 2023 2023 Citations: 4
MOST CITED SCHOLAR PUBLICATIONS
Detection of antibiotic constituent in aspergillus flavus using quantum convolutional neural network MS Sannidhan, JE Martis, RS Nayak, SK Aithal, KB Sudeepa International Journal of E-Health and Medical Communications (IJEHMC) 14 (1 … , 2023 2023 Citations: 68
A Study on various state of the art of the Art Face Recognition System using Deep Learning Techniques S Chokkadi, MS Sannidhan, KB Sudeepa, A Bhandary International Journal of Advanced Trends in Computer Science and Engineering … , 2019 2019 Citations: 46
Evaluating the performance of face sketch generation using generative adversarial networks MS Sannidhan, GA Prabhu, DE Robbins, C Shasky Pattern Recognition Letters 128, 452-458 , 2019 2019 Citations: 37
Novel hybrid quantum architecture-based lung cancer detection using chest radiograph and computerized tomography images JE Martis, S MS, B R, AM Mutawa, M Murugappan Bioengineering 11 (8), 799 , 2024 2024 Citations: 30
A novel approach for matching composite sketches to mugshot photos using the fusion of SIFT and SURF feature descriptor R Kokila, MS Sannidhan, A Bhandary 2017 international conference on advances in computing, communications and … , 2017 2017 Citations: 28
RETRACTED ARTICLE: Performance enhancement of generative adversarial network for photograph–sketch identification MS Sannidhan, GA Prabhu, KM Chaitra, JR Mohanty Soft Computing 27 (1), 435-452 , 2023 2023 Citations: 20
Car damage assessment recommendation system using neural networks JE Martis, MS Sannidhan, CV Aravinda, R Balasubramani Materials Today: Proceedings 92, 24-31 , 2023 2023 Citations: 18
A novel approach for generating composite sketches from mugshot photographs S Pallavi, MS Sannidhan, KB Sudeepa, A Bhandary 2018 international conference on advances in computing, communications and … , 2018 2018 Citations: 14
A study and analysis of various techniques to match sketches to Mugshot photos R Kokila, MS Sannidhan, A Bhandary 2017 international conference on inventive communication and computational … , 2017 2017 Citations: 14
A rapid automated process for organizing bacterial cluster segments using deep neural networks JE Martis, KB Sudeepa, MS Sannidhan, A Bhandary 2020 Third International Conference on Smart Systems and Inventive … , 2020 2020 Citations: 11
A cost effective approach for detecting electricity theft using raspberry pi board MS Sannidhan, JE Martis, A Bhandary 2017 International Conference on Current Trends in Computer, Electrical … , 2017 2017 Citations: 11
DANE: An inbuilt security extension C Aishwarya, MA Raghuram, S Hosmani, MS Sannidhan, B Rajendran, ... 2015 International Conference on Green Computing and Internet of Things … , 2015 2015 Citations: 10
Precision sketching with de-aging networks in forensics JE Martis, MS Sannidhan, N Pratheeksha Hegde, L Sadananda Frontiers in Signal Processing 4, 1355573 , 2024 2024 Citations: 8
Lemon Maturity estimator: an approach using color image processing techniques MS Sannidhan, A Bhandary 2018 international conference on electrical, electronics, communication … , 2018 2018 Citations: 8
A farmer-friendly connected IoT platform for predicting crop suitability based on farmland assessment JE Martis, MS Sannidhan, KB Sudeepa Internet of Things and Analytics for Agriculture, Volume 3, 247-272 , 2021 2021 Citations: 7
Retrieval of facial sketches using linguistic descriptors: an approach based on hierarchical classification of facial attributes S Pallavi, MS Sannidhan, A Bhandary International Conference on Artificial Intelligence and Data Engineering … , 2019 2019 Citations: 7
Text-to-sketch synthesis via adversarial network J Martis, S Shetty, M Pradhan, U Desai, B Acharya Computers, Materials, & Continua 76 (1), 915 , 2023 2023 Citations: 6
A novel key generation approach based on facial image features for stream cipher system MS Sannidhan, KB Sudeepa, JE Martis, A Bhandary 2020 third international conference on smart systems and inventive … , 2020 2020 Citations: 6
Generic IoT platform for analytics in agriculture B Pradeep, R Balasubramani, JE Martis, MS Sannidhan Internet of Things and Analytics for Agriculture, Volume 2, 225-248 , 2019 2019 Citations: 6
Assessment of image enhancement procedures for matching sketches to photos MS Sannidhan, KM Chaitra 2019 IEEE International Conference on Distributed Computing, VLSI … , 2019 2019 Citations: 6