LOAD: Local Orientation Adaptive Descriptor for Texture and Material Classification

TL;DR

This paper introduces LOAD, a new local feature descriptor for texture and material classification that is robust to illumination and rotation, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents LOAD, a novel local descriptor using an adaptive coordinate system and binary sequences, improving texture and material classification performance.

Findings

Achieved 65.4% accuracy on Flickr Material Database, the highest to date.

LOAD outperforms existing descriptors in texture classification tasks.

Combining LOAD with CNN features yields even better results.

Abstract

In this paper, we propose a novel local feature, called Local Orientation Adaptive Descriptor (LOAD), to capture regional texture in an image. In LOAD, we proposed to define point description on an Adaptive Coordinate System (ACS), adopt a binary sequence descriptor to capture relationships between one point and its neighbors and use multi-scale strategy to enhance the discriminative power of the descriptor. The proposed LOAD enjoys not only discriminative power to capture the texture information, but also has strong robustness to illumination variation and image rotation. Extensive experiments on benchmark data sets of texture classification and real-world material recognition show that the proposed LOAD yields the state-of-the-art performance. It is worth to mention that we achieve a 65.4\% classification accuracy-- which is, to the best of our knowledge, the highest record by far --on Flickr Material Database by using a single feature. Moreover, by combining LOAD with the feature extracted by Convolutional Neural Networks (CNN), we obtain significantly better performance than both the LOAD and CNN. This result confirms that the LOAD is complementary to the learning-based features.