MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202541126516 A) filed by Dayananda Sagar Academy Of Technology And Management; Indu B; Aniruddha S P; Mohammed Rehan; Keshava Gowda V; and Jaya Krishna Datta, Bengaluru, Karnataka, on Dec. 14, 2025, for 'enhanced text extraction from images using cnn-assisted image preprocessing and ocr techniques.'
Inventor(s) include Dayananda Sagar Academy Technology And Management; Indu B; Aniruddha S P; Mohammed Rehan; Keshava Gowda V; and Jaya Krishna Datta.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an advanced system and method for enhanced text extraction from images using a combination of CNN-assisted preprocessing and optimized OCR techniques. The system comprises of a configurable enhancement selection module that applies basic, advanced, or high-contrast image enhancement operations, including contrast adjustment, CLAHE, bilateral filtering, adaptive contrast, and noise reduction. The system further comprises of an optional CNN-based enhancement module designed to intelligently refine image features and improve text clarity before OCR processing. After enhancement, an OCR engine performs text recognition followed by an optional export or post-processing stage. The present invention ensures high-accuracy text extraction, even from low-quality, noisy, blurred, shadowed, or low-contrast images, by adaptively selecting enhancement methods and leveraging deep-learning models. This integrated approach improves character recognition reliability across printed, handwritten, multilingual, and real-world image datasets, making it suitable for document digitization, mobile scanning, automated data entry, and assistive technologies."
Disclaimer: Curated by HT Syndication.
