For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Bilateral Convolutional Activations Encoded with Fisher Vectors for Scene Character Recognition
Zhong ZHANG Hong WANG Shuang LIU Tariq S. DURRANI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2018/05/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
bilateral convolutional activations, Fisher vectors, scene character recognition,
Full Text: PDF(215.6KB)>>
A rich and robust representation for scene characters plays a significant role in automatically understanding the text in images. In this letter, we focus on the issue of feature representation, and propose a novel encoding method named bilateral convolutional activations encoded with Fisher vectors (BCA-FV) for scene character recognition. Concretely, we first extract convolutional activation descriptors from convolutional maps and then build a bilateral convolutional activation map (BCAM) to capture the relationship between the convolutional activation response and the spatial structure information. Finally, in order to obtain the global feature representation, the BCAM is injected into FV to encode convolutional activation descriptors. Hence, the BCA-FV can effectively integrate the prominent features and spatial structure information for character representation. We verify our method on two widely used databases (ICDAR2003 and Chars74K), and the experimental results demonstrate that our method achieves better results than the state-of-the-art methods. In addition, we further validate the proposed BCA-FV on the “Pan+ChiPhoto” database for Chinese scene character recognition, and the experimental results show the good generalization ability of the proposed BCA-FV.