Febin I P
Areas of Interest & Expertise
- AI and Computer Vision for Social Good
- Satellite Image Analysis for Environmental Threat detection and biodiversity conservation
- Medical Image Analysis for Early Detection of Diseases
- Mathematical Image Processing and Inverse Problems in Imaging
- Deep Generative Networks
Biography
Febin is a specialist in Image Processing and Computer Vision with a strong focus on computational methods for real-world applications. She began her career with a Bachelor’s in Information Technology (BTech IT) and spent nearly three years in the IT industry. Driven by a growing interest in using technology for social good, she transitioned to research and completed an MTech in Computer Science with a specialisation in Image Processing, followed by doctoral studies in Image Processing and Machine Learning.
During her Master’s, she worked on violence detection in videos for intelligent surveillance systems, resulting in a Springer journal publication in video-based violence detection.
Febin completed her PhD at the National Institute of Technology (NIT), Karnataka. Her doctoral research focused on inverse problems in imaging, where she developed non-local Total Variation (TV)-based mathematical models for the restoration and enhancement of corrupted satellite and medical images. She later extended this work by proposing Total Generalised Variation (TGV)-based models for improved reconstruction performance.
In her postdoctoral research at NIT Karnataka, she explored Deep Image Prior (DIP) frameworks and fractional-order gradient-based TV methods for enhancing and despeckling Synthetic Aperture Radar (SAR) images.
Febin is deeply passionate about the broader field of Computer Vision, particularly in exploring how images and videos can function as a machine’s “eye” to interpret and understand the world. She is especially interested in how machine vision — capable of extending beyond the limitations of the visible spectrum — can be leveraged to address social and environmental challenges.
Publications
Chapters in edited books
- Febin, I.P., Bini, A.A., & Jidesh, P. (2026). A Retinex driven fractional-order regularisation model for despeckling and enhancing Synthetic Aperture Radar images. In J. Kakarla, R. Balasubramanian, S. Murala, S.K. Vipparthi, & D. Gupta (Eds.), Computer Vision and Image Processing (CVIP 2024). Springer. https://link.springer.com/book/10.1007/978 – 3‑031 – 93697‑5
- Febin, I.P., & Jidesh, P. (2021). A fast computing model for despeckling ultrasound images. In A. Awasthi, S. J. John, & S. Panda (Eds.), Computational Sciences – Modelling, Computing and Soft Computing (CSMCS 2020) (Communications in Computer and Information Science), 1345, pp 217 – 228. Springer. https://doi.org/10.1007/978 – 981-16 – 4772-7_17
- Smitha, A., Jidesh, P., & Febin, I.P. (2020). Retinal vessel classification using the non-local Retinex method. In U. Tiwary & S. Chaudhury (Eds.), Intelligent Human
Computer Interaction (IHCI 2019) (Lecture Notes in Computer Science), 11886, pp.163 – 174. Springer. https://doi.org/10.1007/978 – 3‑030 – 44689-5_15
Journal articles
- Febin, I.P., Jayasree, K., & Joy, P.T. (2020). Violence detection in videos for an intelligent surveillance system using MoBSIFT and movement filtering algorithm. Pattern Analysis and Applications, 23, 611 – 623. https://doi.org/10.1007/s10044-018 – 00755‑2
- Febin, I. P., Jidesh, P., & Bini, A. A. (2020). A Retinex based variational model for enhancement and restoration of low contrast remote sensed images corrupted by shot noise. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 941 – 949. https://doi.org/10.1109/JSTARS.2020.2975044
- Jidesh, P., & Febin, I. P. (2020). A perceptually inspired variational model for enhancing and restoring remote sensing images. IEEE Geoscience and Remote Sensing Letters, 18(2), 251 – 255. https://doi.org/10.1109/LGRS.2020.2969411
- Febin, I. P., & Jidesh, P. (2021). Despeckling and enhancement of ultrasound images using non-local variational framework. The Visual Computer, 38, 1413 – 1426. https://doi.org/10.1007/s00371-021 – 02076‑8
- Smitha, A., Febin, I. P., & Jidesh, P. (2022). A Retinex based non-local total generalised variation framework for OCT image restoration. Biomedical Signal Processing and Control, 71, 103234. https://doi.org/10.1016/j.bspc.2021.103234
- Febin, I. P., & Jidesh, P. (2018). Noise classification and automatic restoration system using non-local regularisation frameworks. The Imaging Science Journal, 66(8), 479 – 491. https://doi.org/10.1080/13682199.2018.1518760
- Jidesh, P., & Febin, I. P. (2019). Noise estimation and analysis for denoising images using non-local regularisation frameworks. Arabian Journal for Science and Engineering, 44, 3425 – 3437. https://doi.org/10.1007/s13369-018 – 03306‑2