Writer identification based on arabic handwriting recognition by using speed up robust feature and K-nearest neighbor classification

Abstract EN

In a writer recognition system, the system performs a “one-to-many” search in a large database with handwriting samples of known authors and returns a possible candidate list.

This paper proposes method for writer identification handwritten Arabic word without segmentation to sub letters based on feature extraction speed up robust feature transform (SURF) and K nearest neighbor classification (KNN) to enhance the writer's identification accuracy.

After feature extraction, it can be cluster by K- means algorithm to standardize the number of features.

The feature extraction and feature clustering called to gather Bag of Word (BOW); it converts arbitrary number of image feature to uniform length feature vector.

The proposed method experimented using (IFN/ENIT) database.

The recognition rate of experiment result is (96.666).