Patchy Image Structure Classification Using Multi-Orientation Region Transform
This addresses a specific challenge in computer vision for fine-grained image classification, offering an incremental improvement by combining multi-scale orientation features with deep learning techniques.
The paper tackles the problem of classifying patchy image structures with similar contours and flexible internal structures by proposing a Multi-Orientation Region Transform (MORT) that integrates contour and structure features simultaneously, achieving state-of-the-art results on challenging tasks like ultra-fine-grained cultivar, insect wing, and butterfly recognition.
Exterior contour and interior structure are both vital features for classifying objects. However, most of the existing methods consider exterior contour feature and internal structure feature separately, and thus fail to function when classifying patchy image structures that have similar contours and flexible structures. To address above limitations, this paper proposes a novel Multi-Orientation Region Transform (MORT), which can effectively characterize both contour and structure features simultaneously, for patchy image structure classification. MORT is performed over multiple orientation regions at multiple scales to effectively integrate patchy features, and thus enables a better description of the shape in a coarse-to-fine manner. Moreover, the proposed MORT can be extended to combine with the deep convolutional neural network techniques, for further enhancement of classification accuracy. Very encouraging experimental results on the challenging ultra-fine-grained cultivar recognition task, insect wing recognition task, and large variation butterfly recognition task are obtained, which demonstrate the effectiveness and superiority of the proposed MORT over the state-of-the-art methods in classifying patchy image structures. Our code and three patchy image structure datasets are available at: https://github.com/XiaohanYu-GU/MReT2019.