Summary
|
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. |
|
Pre-Processing for Fine-Grained Image Classification Hao GE Feng YANG Xiaoguang TU Mei XIE Zheng MA Publication IEICE TRANSACTIONS on Information and Systems Vol.E100-D No.8 pp.1938-1942 Publication Date: 2017/08/01 Publicized: 2017/05/12 Online ISSN: 1745-1361 DOI: 10.1587/transinf.2017EDL8076 Type of Manuscript: LETTER Category: Image Recognition, Computer Vision Keyword: fine-grained classification, object detection, neural network, Full Text: PDF(944KB)>>
Summary: Recently, numerous methods have been proposed to tackle the problem of fine-grained image classification. However, rare of them focus on the pre-processing step of image alignment. In this paper, we propose a new pre-processing method with the aim of reducing the variance of objects among the same class. As a result, the variance of objects between different classes will be more significant. The proposed approach consists of four procedures. The “parts” of the objects are firstly located. After that, the rotation angle and the bounding box could be obtained based on the spatial relationship of the “parts”. Finally, all the images are resized to similar sizes. The objects in the images possess the properties of translation, scale and rotation invariance after processed by the proposed method. Experiments on the CUB-200-2011 and CUB-200-2010 datasets have demonstrated that the proposed method could boost the recognition performance by serving as a pre-processing step of several popular classification algorithms. | ||||||||||
| ||||||||||