Abstract
Candidate text region extraction plays a critical role in convolutional neural network (CNN) based text detection from natural images. In this paper, we propose a CNN based scene text detection algorithm with a new text region extractor. The so called candidate text region extractor I-MSER is based on Maximally Stable Extremal Region (MSER), which can improve the independency and completeness of the extracted candidate text regions. Design of I-MSER is motivated by the observation that text MSERs have high similarity and are close to each other. The independency of candidate text regions obtained by I-MSER is guaranteed by selecting the most representative regions from a MSER tree which is generated according to the spatial overlapping relationship among the MSERs. A multi-layer CNN model is trained to score the confidence value of the extracted regions extracted by the I-MSER for text detection. The new text detection algorithm based on I-MSER is evaluated with wide-used ICDAR 2011 and 2013 datasets and shows improved detection performance compared to the existing algorithms.
Original language | English |
---|---|
Title of host publication | VCIP 2016 - 30th Anniversary of Visual Communication and Image Processing |
Publisher | IEEE |
Number of pages | 4 |
ISBN (Electronic) | 978-1-5090-5316-2 |
DOIs | |
Publication status | Published - 4 Jan 2017 |
Event | 2016 IEEE Visual Communication and Image Processing - Chengdu, China Duration: 27 Nov 2016 → 30 Nov 2016 |
Conference
Conference | 2016 IEEE Visual Communication and Image Processing |
---|---|
Abbreviated title | VCIP 2016 |
Country/Territory | China |
City | Chengdu |
Period | 27/11/16 → 30/11/16 |
Bibliographical note
-Keywords
- CNN
- deep learning model
- I-MSER
- scene text detection
- text region extraction