LOOP Descriptor: Local Optimal Oriented Pattern
This work addresses rotation invariance in image descriptors for computer vision applications, particularly in fine-grained species recognition, but it is incremental as it builds on existing binary descriptor methods.
The authors tackled the problem of rotation invariance in binary descriptors by introducing LOOP, which encodes rotation invariance directly into its formulation, eliminating the need for post-processing and improving accuracy and time complexity. They demonstrated that LOOP performs as well or better than previous binary descriptors on standard benchmarks and a new dataset for fine-grained lepidoptera species recognition.
This letter introduces the LOOP binary descriptor (local optimal oriented pattern) that encodes rotation invariance into the main formulation itself. This makes any post processing stage for rotation invariance redundant and improves on both accuracy and time complexity. We consider fine-grained lepidoptera (moth/butterfly) species recognition as the representative problem since it involves repetition of localized patterns and textures that may be exploited for discrimination. We evaluate the performance of LOOP against its predecessors as well as few other popular descriptors. Besides experiments on standard benchmarks, we also introduce a new small image dataset on NZ Lepidoptera. Loop performs as well or better on all datasets evaluated compared to previous binary descriptors. The new dataset and demo code of the proposed method are to be made available through the lead author's academic webpage and GitHub.