| Automatic character detection and segmentation in natural scene images |
| |
| 作者姓名： | ZHU Kai-hua QI Fei-hu JIANG Ren-jie XU Li |
| |
| 作者单位： | Department of Computer Science and Technology，Shanghai Jiao Tong University，Shanghai 200030，China |
| |
| 基金项目： | Project supported by OMRON under PVS project |
| |
| 摘 要： | INTRODUCTION Text detection and segmentation from a naturalscene is very useful in many applications. With theincreasing availability of high performance, lowpriced, portable digital imaging devices, the applica-tion of scene text recognition is rapidly expanding. Byusing cameras attached to cellular phones, PDAs, orstandalone digital cameras, we can easily capture thetext occurrences around us, such as street signs, ad-vertisements, traffic warnings or restaurant menus.Automatic recogn…
|
| 关 键 词： | 自然景物图象 文本探测 文本分割 Adaboost算法 分级器 |
| 收稿时间： | 2005-10-18 |
| 修稿时间： | 2006-02-22 |
Automatic character detection and segmentation in natural scene images |
| |
| ZHU Kai-hua QI Fei-hu JIANG Ren-jie XU Li.Automatic character detection and segmentation in natural scene images[J].Journal of Zhejiang University Science,2007,8(1):63-71. |
| |
| Authors: | Kai-hua Zhu Fei-hu Qi Ren-jie Jiang Li Xu |
| |
| Institution: | (1) Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, 200030, China |
| |
| Abstract: | We present a robust connected-component (CC) based method for automatic detection and segmentation of text in real-scene images. This technique can be applied in robot vision, sign recognition, meeting processing and video indexing. First, a Non-Linear Niblack method (NLNiblack) is proposed to decompose the image into candidate CCs. Then, all these CCs are fed into a cascade of classifiers trained by Adaboost algorithm. Each classifier in the cascade responds to one feature of the CC. Proposed here are 12 novel features which are insensitive to noise, scale, text orientation and text language. The classifier cascade allows non-text CCs of the image to be rapidly discarded while more computation is spent on promising text-like CCs. The CCs passing through the cascade are considered as text components and are used to form the segmentation result. A prototype system was built, with experimental results proving the effectiveness and efficiency of the proposed method. |
| |
| Keywords: | Text detection and segmentation Adaboost NLNiblack decomposition method Attentional cascade |
| 本文献已被 CNKI 维普 SpringerLink 等数据库收录！ |
