No abstract

Applying and securing accreditation from the ABET and NCAAA on the first attempt can be a daunting target, although not impossible. The task is indeed strenuous; however, a methodical and step-wise approach positively facilitates the way to success. After establishing a new program in a public university in the Kingdom of Saudi Arabia, the majority of funding from the Ministry of Higher Education depends on acquiring the national accreditation (NCAAA). When it comes to the engineering programs in particular, along with the national accreditation, there is a tremendous pressure from the same Ministry to attain some international accreditation, primarily from the ABET. This paper will shed some light on several key aspects where work between the two accreditation processes can be shared and, thus, help reduce the burden thereof.

This paper evaluates and compares the performance of K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Sparse Representation Classifier (SRC) for recognition of isolated Arabic handwritten characters. The proposed framework converts the gray-scale character image to a binary image through Otsu thresholding, and size-normalizes the binary image for feature extraction. Next, we exploit image down-sampling and the histogram of image gradients as features for image classification and apply fusion (combination) of these features to improve the recognition accuracy. The performance of the proposed system is evaluated on Isolated Farsi/Arabic Handwritten Character Database (IFHCDB) – a large dataset containing gray scale character images. Experimental results reveal that the histogram of gradient consistently outperforms down-sampling based features, and the fusion of these two feature sets achieves the best performance. Likewise, SRC and SVM both outperform KNN, with the latter performing the best among the three. Finally, we achieved a commanding accuracy of 93.71% in character recognition with fusion of features classified by SVM, where 92.06% and 91.10% is achieved by SRC and KNN respectively.

No abstract