Texture Classification Using High-Order Local Derivative Pattern and KNN Classifier

• Author(s): B. Satish Babu; M. Bhavana; M. Hema SriVani; Rubeena Mehak; Y. Karthik
• Paper ID: 1714818
• Page: 291-297
• Published Date: 09-03-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 9 March-2026

Abstract

Texture classification is a fundamental issue in image processing and computer vision. It has been used in material classification, surface analysis, document analysis, and industrial automation. In this paper, a texture classification algorithm based on Local Derivative Pattern (LDP) is proposed. The algorithm extracts high-order directional texture features from grayscale images and represents them using normalized histograms. A K-Nearest Neighbor (KNN) classifier with cosine distance is employed to classify texture images into multiple categories. Simulation experiments on a practical texture image database demonstrate that the proposed algorithm can achieve accurate classification results with low computational complexity.

Keywords

Local Derivative Pattern, Texture Classification, High-Order Descriptor, Cosine Distance, KNN, Image Texture Analysis.

Citations

IRE Journals:
B. Satish Babu, M. Bhavana, M. Hema SriVani, Rubeena Mehak, Y. Karthik "Texture Classification Using High-Order Local Derivative Pattern and KNN Classifier" Iconic Research And Engineering Journals Volume 9 Issue 9 2026 Page 291-297 https://doi.org/10.64388/IREV9I9-1714818

IEEE:
B. Satish Babu, M. Bhavana, M. Hema SriVani, Rubeena Mehak, Y. Karthik "Texture Classification Using High-Order Local Derivative Pattern and KNN Classifier" Iconic Research And Engineering Journals, 9(9) https://doi.org/10.64388/IREV9I9-1714818