LOAD: Local Orientation Adaptive Descriptor for Texture and Material Classification
This work addresses texture and material recognition in computer vision, offering an incremental improvement through a new descriptor that enhances robustness and discriminative power.
The paper tackles texture and material classification by proposing a novel local feature called LOAD, which achieves state-of-the-art performance with a 65.4% accuracy on the Flickr Material Database using a single feature and shows complementary benefits when combined with CNN features.
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.