Mining the displacement of max-pooling for text recognition. (September 2019)

• Record Type: Journal Article
• Authors: Zheng, Yuchen; Iwana, Brian Kenji; Uchida, Seiichi
• Is Part Of: Pattern recognition. Volume 93(2019:Sep.)
• Page Start: 558
• Page End: 569
• Publication Date: 2019-09
• Subjects: Convolutional neural networks -- Max-pooling -- Displacement feature -- Text recognition; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.014
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A new feature named "displacement features" are extracted from the pooling layer. Combining the displacement features and pooling features for text recognition. Analyzing and mining the behaviors of the displacement features. Graphical abstract: Abstract: The max-pooling operation in convolutional neural networks (CNNs) downsamples the feature maps of convolutional layers. However, in doing so, it loses some spatial information. In this paper, we extract a novel feature from pooling layers, called displacement features, and combine them with the features resulting from max-pooling to capture the structural deformations for text recognition tasks. The displacement features record the location of the maximal value in a max-pooling operation. Furthermore, we analyze and mine the class-wise trends of the displacement features. The extensive experimental results and discussions demonstrate that the proposed displacement features can improve the performance of the CNN based architectures and tackle the issues with the structural deformations of max-pooling in the text recognition tasks.