Douma,A.Sengul,G.Ibrahim Salem,F.G.Ali Ahmed,A.Computer Engineering2024-07-052024-07-0520210978-166541856-010.1109/MI-STA52233.2021.94644992-s2.0-85113701473https://doi.org/10.1109/MI-STA52233.2021.9464499https://hdl.handle.net/20.500.14411/3998the aim of this paper is to recognize the Arabic handwriting letters by using histogram of oriented gradients (HOG). We collected 2240 letters by 8 people, each person wrote 28 alphabet letter 10 times. First of all we resize All 2240 hand writing letter of Arabic Alphabet as images(pre-processing) after that extract these images by using one of feature extraction methods which is histogram of oriented gradients (HOG).For classification, the K-Nearest Neighbor (KNN) is used. The results are shown by using 1120 images in the one case and 2240 images in the second case and evaluate these results with the confusion matrix. Other cases we used leave one out (LOO), 2-fold classification and leave one out cross validation. The best fully performance of HOG was with leave one out technique because of the ability of HOG algorithm to capture the shape of letter in the image according to its edges (gradients). © 2021 IEEE.eninfo:eu-repo/semantics/closedAccess2-fold classificationArabic AlphabetConfusion MatrixHistogram of Oriented GradientK-Nearest Neighborleave one out (LOO)Conference Object350355