Title :
Text Detection in Natural Images Using Bio-inspired Models
Author :
Zagoris, Konstantinos ; Pratikakis, Ioannis
Author_Institution :
Dept. of Electr. & Comput. Eng., Democritus Univ. of Thrace, Xanthi, Greece
Abstract :
Textual information in images constitutes a very rich source of high-level semantics for multimedia indexing and retrieval. In this paper, a new approach is proposed for detecting text in natural images inspired by the properties of the Human Visual System (HVS). In particular, the detection is based upon the functionality of the OFF and ON center-surround cells of the HVS. Cells are combined at different scales to guide a both efficient and effective algorithm. Performance evaluation relies on the ICDAR 2011 Robust Reading Dataset.
Keywords :
text detection; HVS; ICDAR robust reading dataset; OFF center-surround cell functionality; ON center-surround cell functionality; bio-inspired models; effective algorithm; efficient algorithm; high-level semantics; human visual system; multimedia indexing; multimedia retrieval; natural images; performance evaluation; text detection; textual information; Brightness; Cells (biology); Filtering; Image edge detection; Retina; Text analysis; Visualization; Human Vision System; Text Detection;
Conference_Titel :
Document Analysis and Recognition (ICDAR), 2013 12th International Conference on
Conference_Location :
Washington, DC
DOI :
10.1109/ICDAR.2013.277
