تخطي إلى التنقل الرئيسي تخطي إلى البحث تخطي إلى المحتوى الرئيسي

Semantic Segmentation and Categorization of Printed-Media Pages Using Deep Neural Networks

المشروع: RESEARCH PROJECT

تفاصيل المشروع

Description

Printed media digitization has gained wide interest around the world. Archives of digitized newspapers and magazines contain a wealth of information that spans decades. To extract this abundance of information, optical character recognition (OCR) techniques with extensive manual page annotation has been done. The OCR techniques extract the text from the raw image of the page, while page annotation adds meta-data about the content of the page such as the category of the page and the location of articles and other elements. To automate this process, we propose an end-to-end language-agnostic framework for semantically segmenting and categorizing printed media pages. The framework will only use the visual features of the digitized printed media to classify the printed media type, classify the page category, and decompose the page into its main elements (news articles, advertisements and page headers). The framework will extract and categorize printed media articles preparing them for the OCR methods to extract meaningful information. The framework is language-agnostic allowing it to extract the articles from printed media from different languages (e.g., Arabic, English, French, etc). The framework will use a type of deep neural networks called Convolutional Neural Networks (CNN) to classify and semantically segment the printed media.
الحالةمنتهي
تاريخ البدء/النهاية الساري1/03/21 → 28/02/23

بصمة

استكشف موضوعات البحث التي تناولها هذا المشروع. يتم إنشاء هذه الملصقات بناءً على الجوائز/المنح الأساسية. فهما يشكلان معًا بصمة فريدة.