Skeleton Matching based approach for Text Localization in Scene Images
This addresses the problem of accurately localizing text in complex scene images for applications like image analysis and OCR, but it appears incremental as it builds on existing skeleton and template matching techniques.
The paper tackles text localization in scene images by proposing a skeleton matching approach that segments images into blocks, extracts skeletons, and compares them with trained templates to classify text and non-text blocks, achieving detection of texts across various sizes, fonts, and colors on standard datasets.
In this paper, we propose a skeleton matching based approach which aids in text localization in scene images. The input image is preprocessed and segmented into blocks using connected component analysis. We obtain the skeleton of the segmented block using morphology based approach. The skeletonized images are compared with the trained templates in the database to categorize into text and non-text blocks. Further, the newly designed geometrical rules and morphological operations are employed on the detected text blocks for scene text localization. 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.