Rashmi S – Machine Learning Techniques | Senior Research Fellow at JSS Science and Technology University, India
Rashmi S. is an accomplished Ph.D. research scholar specializing in Computer Vision and Machine Intelligence. Her academic focus is particularly on medical image analysis, with a concentration on radiographic image annotation using AI and deep learning techniques. With approximately five years of experience in the tech industry as a Core Java Developer, Rashmi brings a unique blend of software development expertise and advanced research skills. She is currently working at the Pattern Recognition & Image Processing Lab at JSS Science and Technology University, Mysuru. Rashmi is driven by the ambition to enhance healthcare systems through innovative AI solutions, and her research contributions aim to create more accurate, automated systems for interpreting medical imagery.
Profile Verification
Google Scholar
Education
Rashmi S. completed her Bachelor of Engineering (B.E.) in Computer Science and Engineering from SJCE, Mysore, graduating with a CGPA of 9.05. She then pursued her Master’s degree in Computer Engineering (M.Tech) from the same institution, achieving an outstanding CGPA of 9.77. Currently, she is pursuing her Ph.D. in Computer Science and Engineering at JSS S&TU, where she is expected to submit her thesis in September 2024. Her academic journey has been marked by a strong commitment to research excellence, particularly in Machine Learning and Deep Learning, both of which she applies in her medical image analysis research.
Experience
Rashmi S. has held various roles in both academic and industry settings, which have enriched her research and technical skills. She began her career in software engineering, working with Cisco Video Technology in Bengaluru, where she was involved in the development of Java-based software for Set-Top Boxes. She later moved on to Oracle India Pvt. Ltd. as an Application Engineer, working on software maintenance and the development of Oracle Projects Fusion, a project management tool. Rashmi’s academic career includes positions as a Junior Research Fellow and Senior Research Fellow at JSS Science and Technology University, where she currently conducts her doctoral research. Her professional journey in both the software industry and academia gives her a unique edge in developing and implementing cutting-edge research in healthcare.
Research Interests
Rashmi S. is primarily focused on Machine Learning, Deep Learning, and Image Processing, especially in the context of medical image analysis. Her research interests revolve around improving diagnostic tools through AI-powered systems. Specifically, her work addresses cephalometric landmark annotation in radiographs using both traditional machine learning algorithms and deep learning techniques. Rashmi has explored applications of EEG signal processing and computer vision in healthcare, striving to develop solutions that can automate the annotation of medical images for more accurate diagnoses. Her research aims to bridge the gap between artificial intelligence and clinical practices, potentially revolutionizing medical imaging and diagnostic procedures.
Awards
Rashmi S. has received several prestigious awards throughout her academic and professional career. She was awarded the UGC-NET Junior Research Fellowship in November 2021, which has enabled her to pursue her doctoral research in depth. She was also recognized with the Senior Research Fellowship by the University Grants Commission in February 2024. Additionally, Rashmi has been the recipient of several scholarships, including the MHRD & GATE Scholarships during her undergraduate and postgraduate studies. Her commitment to research excellence has also earned her multiple accolades for her academic performance, including being recognized for her outstanding contributions to machine learning in the medical field.
Publications
“Cephalometric Skeletal Structure Classification Using Convolutional Neural Networks and Heatmap Regression“, co-authored with P. Murthy, V. Ashok, and S. Srinath, published in SN Computer Science (2022). This study leverages convolutional neural networks (CNNs) and heatmap regression for advanced skeletal structure classification in cephalometric radiographs, with a focus on enhancing the accuracy of diagnostic tools in orthodontics.
“Extended Template Matching Method for Region of Interest Extraction in Cephalometric Landmarks Annotation“, co-authored with S. Srinath, R. Rakshitha, and B.V. Poornima, presented at the 2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical… This paper introduces an extended template matching method aimed at improving the extraction of regions of interest (ROIs) in cephalometric image annotation, a crucial step for automatic landmark detection.
“Lateral Cephalometric Landmark Annotation Using Histogram Oriented Gradients Extracted from Region of Interest Patches“, co-authored with S. Srinath, K. Patil, P.S. Murthy, and S. Deshmukh, published in Journal of Maxillofacial and Oral Surgery (2023). This research presents a novel approach for lateral cephalometric landmark annotation by extracting histogram-oriented gradients from ROIs, advancing the methods for more precise orthodontic assessments.
“A Novel Method for Cephalometric Landmark Regression Using Convolutional Neural Networks and Local Binary Pattern“, co-authored with V. Ashok, presented at the 5th International Conference on Computer Vision and Image Processing (2021). This paper explores a novel technique for landmark regression in cephalometric images using a combination of CNNs and local binary patterns, enhancing the automation of cephalometric analysis.
“Landmark Annotation Through Feature Combinations: A Comparative Study on Cephalometric Images with In-depth Analysis of Model’s Explainability“, co-authored with S. Srinath, S. Murthy, and S. Deshmukh, published in Dentomaxillofacial Radiology (2024). This comparative study examines various feature combinations for landmark annotation and provides an explainability analysis of the models used, aiming to make machine learning-based medical imaging more transparent and understandable.
“Recognition of Indian Sign Language Alphanumeric Gestures Based on Global Features“, co-authored with B.V. Poornima, S. Srinath, and R. Rakshitha, presented at the 2023 IEEE International Conference on Distributed Computing, VLSI… This paper investigates the use of global features for recognizing Indian Sign Language gestures, contributing to the development of gesture recognition systems in communication technologies.
“ISL2022: A Novel Dataset Creation on Indian Sign Language“, co-authored with R. Rakshitha, S. Srinath, and S. Rashmi, presented at the 2023 10th International Conference on Signal Processing and Integrated…. This paper presents the creation of the ISL2022 dataset, a significant step toward improving machine learning models for Indian Sign Language recognition, highlighting the importance of datasets in advancing language recognition research.
“Cephalometric Landmark Annotation Using Transfer Learning: Detectron2 and YOLOv8 Baselines on a Diverse Cephalometric Image Dataset“, co-authored with S. Srinath, S. Deshmukh, S. Prashanth, and K. Patil, published in Computers in Biology and Medicine (2024). This work leverages transfer learning techniques, using Detectron2 and YOLOv8 models, to annotate cephalometric landmarks on a diverse dataset, pushing the envelope for automated medical image analysis.
“Crack SAM: Enhancing Crack Detection Utilizing Foundation Models and Detectron2 Architecture“, co-authored with R. Rakshitha, S. Srinath, N. Vinay Kumar, and B.V. Poornima, published in Journal of Infrastructure Preservation and Resilience (2024). This research explores advanced crack detection techniques, using foundation models and Detectron2, to improve the detection of cracks in infrastructure.
“Enhancing Crack Pixel Segmentation: Comparative Assessment of Feature Combinations and Model Interpretability”, co-authored with R. Rakshitha, S. Srinath, N. Vinay Kumar, and B.V. Poornima, published in Innovative Infrastructure Solutions (2024). This paper focuses on crack pixel segmentation, offering insights into the comparative performance of various feature combinations and the interpretability of machine learning models used in infrastructure monitoring.
Conclusion
Rashmi S. has demonstrated exceptional skill and dedication to the field of Computer Vision and Machine Intelligence. With her substantial industry experience and strong academic background, Rashmi has contributed significantly to AI research in healthcare. Her work has the potential to revolutionize medical image analysis, offering more efficient and accurate diagnostic tools. Through her awards, publications, and ongoing research, Rashmi S. stands as an exemplary candidate for the Best Researcher Award, with the promise of continuing to make groundbreaking advancements in her field.