MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641109245 A) filed by Vignan'S Nirula Institute Of Technology And Science For Women on September 11, 2026, for A Method And System For The Recognition Of Entropy Based Adaptive Number Plate.
Inventors include Joseph Sanam; P. Ganesh Babu; Shaik Sumayya Parveen; Davuluri Koteswari; Balaga Keerthi; Peddinti Meghana; Kamatham Jesmitha; Nannuri Naga Jyothi; Lingala Sri Lekha; Dasari Kamala Devi; and E. Bhanu Prasad.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: A SYSTEM AND METHOD FOR ENTROPY-GUIDED ADAPTIVE NUMBER PLATE RECOGNITION. A system and method for automatic vehicle number plate recognition is disclosed. A grayscale image is generated from an acquired vehicle image, and its local Shannon entropy is used to compute a spatially adaptive morphological structuring-element radius, which consolidates candidate plate regions while suppressing background clutter. A composite score, fusing normalized area, aspect-ratio conformity, and edge density, is computed for each candidate region to select the localized plate region. Segmented character sub-images are compared with reference templates using a Gaussian-weighted structural correlation measure, and a confidence-margin decision rule accepts a character label only when the margin between the best and second-best scores exceeds a threshold; otherwise, it flags the character as ambiguous. The invention retains the low cost of classical pipelines while improving illumination robustness and confidence. Reference Figure: FIG. 1.
Disclaimer: Curated by HT Syndication.
