Content-Based Video Browsing by Text Region Localization and Classification

TL;DR

This paper introduces a novel spatiotemporal approach for localizing and classifying text regions in videos, enhancing content-based browsing by automatically identifying semantic text features within video sequences.

Contribution

It proposes a new method combining text region localization and classification using visual features, improving video indexing and browsing efficiency.

Findings

Effective text region detection through split and merge on edge differences

Successful classification of text regions using visual grammar descriptors

Generation of a semantic video content table

Abstract

The amount of digital video data is increasing over the world. It highlights the need for efficient algorithms that can index, retrieve and browse this data by content. This can be achieved by identifying semantic description captured automatically from video structure. Among these descriptions, text within video is considered as rich features that enable a good way for video indexing and browsing. Unlike most video text detection and extraction methods that treat video sequences as collections of still images, we propose in this paper spatiotemporal. video-text localization and identification approach which proceeds in two main steps: text region localization and text region classification. In the first step we detect the significant appearance of the new objects in a frame by a split and merge processes applied on binarized edge frame pair differences. Detected objects are, a priori, considered as text. They are then filtered according to both local contrast variation and texture criteria in order to get the effective ones. The resulted text regions are classified based on a visual grammar descriptor containing a set of semantic text class regions characterized by visual features. A visual table of content is then generated based on extracted text regions occurring within video sequence enriched by a semantic identification. The experimentation performed on a variety of video sequences shows the efficiency of our approach.