MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202631081557 A) filed by Indian Institute Of Information Technology Ranchi on July 02, 2026, for An Image Processing System And Method For Automatic Characterization Of Abnormalities.
Inventors include Abhinav Kumar; Roshan Singh; Dhiran Kumar Mahto; and Rajeev Srivastava.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT “AN IMAGE PROCESSING SYSTEM AND METHOD FOR AUTOMATIC CHARACTERIZATION OF ABNORMALITIES” The present invention provides an image processing system (100) for automatic characterization of knee osteoarthritis abnormalities comprising a processor (101) that includes an input interface (201) for receiving images for analysis, a modified backbone module (202) comprising convolutional neural network integrated with convolutional block attention module to extract image features and generate refined feature maps, a feature pyramid network (203) to generate multi-scale feature representations for identifying suspected abnormal regions, a region proposal network (204), a region of interest alignment module (205), a cascade region convolutional neural network head (206) classifies the regions and generates confidence scores and refined bounding boxes, while the mask head generates segmentation masks, a mask head (207), a localization module (208) that module refines abnormality localization and output interface (209) presents detected abnormalities with associated labels and localization information. Figure 1 on sheet no. 1 of the drawings may accompany the abstract when published.
Disclaimer: Curated by HT Syndication.
