OACNNs: Orientation adaptive convolutional neural networks

Article type: Research Article

Authors: Ye, Xiang | He, Zihang | Li, Bohan | Li, Yong^{; *}

Affiliations: Beijing University of Posts and Telecommunications

Correspondence: [*] Corresponding author. Yong Li, Beijing University of Posts and Telecommunications. E-mail: [email protected].

Abstract: Geometric invariant feature representation plays an indispensable role in the field of image processing and computer vision. Recently, convolution neural networks (CNNs) have witnessed a great research progress, however CNNs do not excel at dealing with geometrically transformed images. Existing methods enhancing the ability of CNNs learning invariant feature representation rely partly on data augmentation or have a relatively weak generalization ability. This paper proposes orientation adaptive kernels (OA kernels) and orientation adaptive max pooling (OA max pooling) that comprise a new topological structure, orientation adaptive neural networks (OACNNs). OA kernels output the orientation feature maps which encode the orientation information of images. OA max pooling max-pools the orientation feature maps by automatically rotating the pooling windows according to their orientation. OA kernels and OA max pooling together allow for the eight orientation response of images to be computed, and then the max orientation response is obtained, which is proved to be a robust rotation invariant feature representation. OACNNs are compared with state-of-the-art methods and consistently outperform them in various experiments. OACNNs demonstrate a better generalization ability, yielding a test error rate 3.14 on the rotated images but only trained on “up-right” images, which outperforms all state-of-the-art methods by a large margin.

Keywords: Orientation adaptive kernel, rotation invariance, image transformation, feature extraction

DOI: 10.3233/JIFS-213051

Journal: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 5749-5758, 2022