In the machine learning and computer vision domain, images are represented using their features. Color, shape, and texture are some of the prominent types of features. Over time, the local features of an image have gained importance over the global features due to their high discerning ability in localized regions. The texture features are widely used in image indexing and content-based image retrieval. In the last two decades, various local texture features have been formulated. For a complete description of images, effective and efficient features are necessary. In this paper, we provide algorithms for 10 local texture feature extraction. These texture descriptors have been formulated since the year 2015. We have designed algorithms so that they are time efficient and memory space-efficient. We have implemented these algorithms and verified their output correctness.
|Journal||Journal of Physics: Conference Series|
|Publication status||Published - 11-01-2022|
|Event||1st International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2021 - Manipal, Virtual, India|
Duration: 28-10-2021 → 30-10-2021
All Science Journal Classification (ASJC) codes
- Physics and Astronomy(all)