Video Text Localization with an emphasis on Edge Features
This addresses text localization for video analysis and retrieval, but it appears incremental as it builds on edge-based and morphological techniques without major breakthroughs.
The paper tackled the problem of localizing text in natural scene images and videos by proposing a method based on sobel edge emphasizing, achieving detection of texts of various sizes, fonts, and colors on standard datasets.
The text detection and localization plays a major role in video analysis and understanding. The scene text embedded in video consist of high-level semantics and hence contributes significantly to visual content analysis and retrieval. This paper proposes a novel method to robustly localize the texts in natural scene images and videos based on sobel edge emphasizing approach. The input image is preprocessed and edge emphasis is done to detect the text clusters. Further, a set of rules have been devised using morphological operators for false positive elimination and connected component analysis is performed to detect the text regions and hence text localization is performed. The experimental results obtained on publicly available standard datasets illustrate that the proposed method can detect and localize the texts of various sizes, fonts and colors.