MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202611000835 A) filed by Mangalmay Institute Of Management & Technology, Greater Noida, Uttar Pradesh, on Jan. 5, for 'a cnn-based system for security-assured image watermarking generation and method thereof.'
Inventor(s) include Prerna Mahajan; and Ambica Yadav.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a CNN-based system and method for security-assured image watermarking generation, embedding, extraction, and verification. The system employs a convolutional neural network to extract spatial and frequency-domain features of a host image and determine optimal embedding regions with minimal perceptual impact. A secure watermark is generated using payload data, image-specific features, and a cryptographic key, and is adaptively embedded into the host image to ensure robustness against compression, noise, filtering, geometric transformations, and other attacks. The embedded watermark can be reliably extracted and verified using a CNN-based decoder, thereby enabling authentication, ownership verification, and tamper detection of digital images in secure multimedia applications."
Disclaimer: Curated by HT Syndication.
