Signal & Image Processing

The field of signal and image processing encompasses the theory and practice of algorithms and hardware that convert signals produced by artificial or natural means into a form useful for a specific purpose. The signals might be speech, audio, images, video, sensor data, telemetry, electrocardiograms, or seismic data, among others; possible purposes include transmission, display, storage, interpretation, classification, segmentation, or diagnosis. Faculty members in this field span the areas of digital and statistical signal processing, condition monitoring and fault diagnosis, image/video compression, analysis & processing, speech processing, music information retrieval and computer audition.

Current research in signal processing includes robust and low complexity filter design, signal reconstruction, filter bank theory, and wavelets. In statistical signal processing, faculty interests include adaptive filtering and learning algorithms for neural networks. Image processing work is in restoration, compression, quality evaluation, computer vision, and medical imaging. Speech processing research includes modeling, compression, and recognition. Also, faculty members are actively involved in the research and design of condition monitoring and fault diagnosis systems through advanced signal processing approaches using IoT and machine learning techniques.

 Sub-Topics

  • Signal & Image Processing

    The researchers in this field design algorithms to process and analyse signals in various domains. These signals can be images, videos, audio etc. Various operations like signal pre-processing, enhancement, spatial or frequency domain filtering, compression, segmentation, and feature extraction, are then performed on these signals to interpret or diagnose a particular condition. The researcher focuses on fundamental as well as application-based problems. Various applications on which we research are moving object detection and tracking, Image watermarking, noise reduction, and fault diagnoses. In this field, we also use Machine and deep learning methods to solve contemporary problems.

 

  • Condition Monitoring and Fault Diagnosis using Signal Processing techniques

    The researchers in this field apply advanced signal processing techniques through machine learning and artificial intelligence algorithms to process and analyse signals in various domains. These signals can be images, videos, audio etc. Various operations like signal pre-processing, enhancement, spatial or frequency domain filtering, compression, segmentation, feature extraction and classification are then performed on these signals to interpret and diagnose faults in various domains.

Associated Faculty Members

 Significant Publications

  1. Sudarsan Sahoo, D.P. Jena, S.N. Panigrahi, “Gear Fault Diagnosis Using Active Noise Cancellation and Adaptive Wavelet Transform”, Measurement, vol. 47, pp. 356-372, 2014.
  2. Sudarsan Sahoo and Jitendra Kumar Das, “Application of Adaptive Wavelet Transform for Gear Fault Diagnosis Using Modified-LLMS Based Filtered Vibration Signal”, Recent Advances in Electrical & Electronic Engineering, vol. 1(11), 2018.
  3. Sudarsan Sahoo, J. K. Das, Bapi Debnath, Rolling Element Bearing Condition Monitoring Using Filtered Acoustic Emission, International Journal of Electrical and Computer Engineering, vol. 8 (5), pp. 3560~3567, 2018.
  4. Sudarsan Sahoo et al., A System for diagnosing the Cognitive Effect of Tele-series on the Human Brain using De-noised EEG Signals, German Patent No. 202021106795.0, 2022 (Patent granted).
  5. Moudgollya, Rhittwikraj, Arun Kumar Sunaniya, Abhishek Midya, and Jayasree Chakraborty, “A multi features based background modeling approach for moving object detection”, Optik, Elsevier, vol. 260, pp 168980, 2022.
  6. Subhajit Das and A. K. Sunaniya, “FPGA Implementation of High-fidelity Hybrid Reversible Watermarking Algorithm”, Journal of Microprocessor and Microsystems, Elsevier, vol. 89, pp. 104442, 2022.
  7. Subhajit Das, A. K. Sunaniya, R. Maity and N. P. Maity, “Efficient FPGA Implementation and Verification of Difference Expansion Based Reversible Watermarking with Improved Time and Resource Utilization”, Journal of Microprocessor and Microsystems, Elsevier, vol. 83, pp. 103092, 2021.
  8. Subhajit Das, A. K. Sunaniya, R. Maity and N. P. Maity, “Efficient FPGA Implementation of Corrected Reversible Contrast Mapping Algorithm for Video Watermarking”, Journal of Microprocessor and Microsystems, Elsevier, vol. 76, pp. 103092, 2020.
  9. Subhajit Das, A. K. Sunaniya, R. Maity and N. P. Maity, “Parallel Hardware Implementation of Efficient Embedding Bit Rate Control Based Contrast Mapping Algorithm For Reversible Watermarking”, IEEE Access, vol. 8, pp. 69072-69095, 2020.
  10. Rhittwikraj Moudgollya, Abhishek Midya, Arun Kumar Sunaniya, Jayasree Chakraborty, “Dynamic background modeling using intensity and orientation distribution of video sequence” Multimedia Tools and Applications, Springer Nature, vol. 78(16), pp 22537–22554, 2019.
  11. Neeraj Kumar Singh, Arun Kumar Sunaniya, “An Adaptive Image Sharpening Scheme based on Local Intensity Variations”, Springer Journal of Signal, Image and Video Processing, vol. 11, pp. 777-784, 2016.
  12. S. Biswas and R. Hazra, “State-of-the-art level set models and their performances in image segmentation: A decade review”, Archives of Computational Methods, Springer, vol. 29, pp. 2019-2042, 2022.
  13. S. Biswas and R. Hazra, “A level set model by regularizing local fitting energy and penalty energy term for image segmentation”, Signal Processing, Elsevier, vol. 183, 108043, 2021.
  14. S. Biswas and R. Hazra, “Active contours driven by modified LoG energy term and optimized penalty term for image segmentation”, IET Image Processing, vol. 14(13), 2020.
  15. S. Biswas and R. Hazra, “A new binary level set model using L0 regularizer for image segmentation”, Signal Processing, Elsevier, vol. 174, 107603, 2020.
  16. S. Biswas and R. Hazra, “Robust edge detection based on Modified Moore-Neighbor”, Optik-International Journal of Light and Electron Optics, Elsevier, vol. 168, pp. 931-943, 2018.
  17. S. Biswas, D. Ghoshal and R. Hazra, “A new algorithm of Image Segmentation using Curve Fitting Based Higher Order Polynomial Smoothing”, Optik, International Journal for Light and Electron Optics, Elsevier, vol. 127(20), pp. 8916-8925, 2016.