Isolated Handwritten Digit Recognition Using LPQ and LBP Features
Abdeljalil Gattal, Faycel Abbas · 2020
Several approaches for handwritten digits recognition are proposed an appearance approach based on feature extraction. In this paper we process handwritten digit image without any normalization method using Local Binary Pattern (LBP) and Local Phase Quantization (LPQ) extracted from the complete image as well as from different regions of the image by applying a uniform grid sampling to the image. LBP and LPQ is a very efficient feature descriptor for handwritten which is arise from variations in size, shape and slant. Moreover, the SVM has been employed as classifier which has better responses. The experimental study is conducted on CVL dataset and achieved high recognition rates which is comparable with the state of the art.