Multi-Scale FCN With Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting in the Wild
Dafang He, Xiao Yang, Chen Liang, Zihan Zhou, Alexander G. Ororbi II, Daniel Kifer, C. Lee Giles
Abstract
Scene text detection has attracted great attention these years. Text potentially exist in a wide variety of images or videos and play an important role in understanding the scene. In this paper, we present a novel text detection algorithm which is composed of two cascaded steps: (1) a multi-scale fully convolutional neural network (FCN) is proposed to extract text block regions; (2) a novel instance (word or line) aware segmentation is designed to further remove false positives and obtain word instances. The proposed algorithm can accurately localize word or text line in arbitrary orientations, including curved text lines which cannot be handled in a lot of other frameworks. Our algorithm achieved state-of-the-art performance in ICDAR 2013 (IC13), ICDAR 2015 (IC15) and CUTE80 and Street View Text (SVT) benchmark datasets.
BibTeX
@inproceedings{cvpr2017_multiscalefcnwit,
title = {Multi-Scale FCN With Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting in the Wild},
author = {Dafang He and Xiao Yang and Chen Liang and Zihan Zhou and Alexander G. Ororbi II and Daniel Kifer and C. Lee Giles},
booktitle = {CVPR 2017},
year = {2017}
}