Learning rotation invariant convolutional filters for texture classification

Abstract

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to the state-of-the-art. Compared to standard shallow CNNs, the proposed method obtains higher classification performance while reducing by an order of magnitude the number of parameters to be learned.

6 pages, in ICPR 2016

References in corpus (1)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction

Cited by in corpus (10)

• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• Rotation equivariant vector field networks
• Histogram Layers for Texture Analysis
• Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks
• Topological Learning for Brain Networks
• Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
• Particle Identification In Camera Image Sensors Using Computer Vision
• Learning Test-time Augmentation for Content-based Image Retrieval
• Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps
• Cosmic topology. Part IVa. Classification of manifolds using machine learning: a case study with small toroidal universes