HDO: A novel local image descriptor
Wonjun Kim, ByungIn Yoo, Jae‐Joon Han · 2014
This paper presents a simple, yet powerful local image descriptor, called the histograms of dominant orientations (HDO). The HDO consists of two components, namely the dominant orientation and its coherence, which represents how intensively gradients in the local region are distributed along the dominant orientation. For a given image patch, we incorporate these two components into a 1-D histogram and define it as our HDO descriptor. Compared to previous approaches suffering from the presence of clutters and significant distortions, our HDO descriptor has a great ability to preserve the underlying image structure, and it can thus be successfully applied to various applications (e.g., object detection). The proposed method has been extensively tested on several challenging data sets and results show that our HDO descriptor is effective for object detection in images.