MUMBAI, India, June 26 -- Intellectual Property India has published a patent application (202631070567 A) filed by Kalinga Institute Of Industrial Technology Kiit Deemed To Be University on June 05, 2026, for Content-Based Image Retrieval Using Hybrid Deep Neural Network Feature Fusion.
Inventors include Dev, Raghunath; and Piri, Jayashree.
The application for the patent was published on June 19, 2026, under issue no. 25/2026.
Abstract: ABSTRACT CONTENT-BASED IMAGE RETRIEVAL USING HYBRID DEEP NEURAL NETWORK FEATURE FUSION A system (100) for content-based image retrieval includes a preprocessing module (102) configured to receive an input image and resize the input image to a standardized dimension, a first feature extraction module (104) including a first pre-trained convolutional neural network configured to extract a first feature vector from the preprocessed input image, a second feature extraction module (106) including a second pre-trained convolutional neural network having a different architecture than the first pre-trained convolutional neural network configured to extract a second feature vector from the preprocessed input image, a feature fusion module (108) configured to concatenate the first feature vector and the second feature vector to generate a fused feature vector, and a similarity measurement module (110) configured to compare the fused feature vector with stored feature vectors of database images and retrieve images based on similarity scores.
Disclaimer: Curated by HT Syndication.
