Text Extraction from Natural Images Using Maximally Stable Extremal Regions
- Yash chugh
- Ranjeeta kaushik
text detection, scene text, MSER, connected-component, stroke, OCR
Detecting text in natural images is an important prerequisite. A large number of techniques have been proposed to address this problem and the purpose of this paper is to classify and review these techniques. In this paper a novel text detection algorithm as connected component based text detection algorithm is used for detection and recognition of text from the natural images using edge enhanced Maximally Stable Extremal Regions and stroke Width transform. Basic idea is to extract the connected component with MSER algorithms and then these candidates aare filtered using CC based analysis and stroke width filtering. The text detected is then can be recognized using optical character recognizer.
Yash chugh, Ranjeeta kaushik. "Text Extraction from Natural Images Using Maximally Stable Extremal Regions".INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH ISSN:2321-9939, Vol.3, Issue 2, pp.948-951, URL :https://rjwave.org/ijedr/papers/IJEDR1502166.pdf
Volume 3 Issue 2
Pages. 948-951
