MUMBAI, India, Sept. 12 -- Intellectual Property India has published a patent application (202421016170 A) filed by Tata Consultancy Services Limited, Maharashtra, on March 7, 2024, for 'method and system for targeted extraction of labelled listings and information from a product flyer.'
Inventor(s) include Vasudevan, Bagya Lakshmi; Abraham, Kuruvilla; Sharma, Gaurav; Chatterjee, Kallol; Chakrapani, Chakrapani; and Som, Suvodip.
The application for the patent was published on Sept. 12, under issue no. 37/2025.
According to the abstract released by the Intellectual Property India: "Extracting valuable insights from retail or marketing flyers is crucial for both retailers and consumers. Existing techniques reliant on training flyer images, which struggle with abrupt variations in flyer layouts and designs. A flyer is received in a portable document format as an input document. Each page of the input document is processed by mask region-based convolutional neural network (R-CNN) to convert into images based on PDF processing library. Regions of Interest (ROIs) is identified for each image based on attribute classes of the products by using (i) a class overlapping measures, and (ii) a class distance measures. A textual information is extracted from the identified ROIs within each image by implementing an optical character recognition (OCR) based on the attribute classes. The extracted textual information is segmented by a price extraction technique to create bounding boxes around each character within a Price ROI of a Product ROI. A pricing information is extracted using the OCR within height-based clusters."
Disclaimer: Curated by HT Syndication.
