Patents Filed by Dr. Mrinal Kanti Bhowmik

A system and method for segmenting suspicious hyperthermic regions from breast thermograms

New Indian Patent Application No: 202031027352

Abstract: The Appearance of suspicious hyperthermic regions (SHRs) in breast thermograms is the single most marker of breast abnormality. Hence, accurate segmentation and analysis of SHRs are very crucial for grading the degree of severity in breast thermograms. A novel breast abnormality grading approach namely Morphology Model of Suspicious Hyperthermic Regions (MMSHRs) has been proposed here. The proposed MMSHRs method first segments the SHRs and then, the morphology of the SHRs has been analyzed to grade the thermograms according to their degree of severity. The experimental results show that the proposed segmentation method can extract the SHRs more accurately with higher average accuracy rate compared to the other state-of-the-art methods. The segmentation of SHRs is followed by the extraction of morphological features of SHRs, which categorizes the abnormal thermograms into mild abnormal and severely abnormal with classification accuracy of 91% based on the degree of severity present in the thermograms.

Type: Application

Filed: June 27, 2020

Publication Date: Pending

Applicants: Usha Rani Gogoi (DST - INSPIRE Fellow, Department of Computer Science and Engineering, Tripura University), Mrinal Kanti Bhowmik (Assistant Professor, Department of Computer Science & Engineering, Tripura University)

System and Method for Detecting Object in Adverse Atmosphere by Restoring Degraded Image in Deep Convolutional Layer

New Indian Patent Application No: 202131002651

Abstract: The present invention discloses a system and method for detecting objects in real-time adverse weather-degraded scenes. A single-stage CNN architecture is adopted, namely, AWDRDNet for detecting objects more accurately in adverse weather-degraded realistic scenes. The present invention relates to a feed-forward deeper convolutional layer comprising a plurality of convolution blocks (B1,..,BK,..,BN) producing better quality of restoration images (RI1,..,RIK,..,RIN); wherein receptive field plays an important role in analyzing local features over degraded scenes. Another key feature of the proposed invention is the clipping of pre-defined multi-scale anchor boxes per cell to a restorated de-convolutional feature map (DC) only at the top of the network, which allows to efficiently reduce time-consumption. In terms of detection accuracy (recall-precision graph and mAP), the results of the reference dataset demonstrates the optimal performance of the proposed model and reveals the performance accuracy in low-light or rainy conditions to be higher than that in dusty or foggy conditions.

Type: Application

Filed: January 20, 2021

Publication Date: Pending

Applicants: Anu Singha (Ph.D Scholar, Department of Computer Science and Engineering, Tripura University), Sourav Dey Roy (Ph.D Scholar, CSIR-SRF-Direct, Department of Computer Science and Engineering, Tripura University), Mrinal Kanti Bhowmik (Assistant Professor, Department of Computer Science & Engineering, Tripura University)