Face Image Recognition Based on Linear Discernment Analysis and Cuckoo Search Optimization with SVM By Jamal Mustafa AL-Tuwaijari Suhad Ibrahim Mohammed Department of Computer Science - College of Science - University of Diyala - Iraq Abstract Face image recognition became an effective research area over last two decades, It covers a wide range of activities from many aspects of life such as authentication and identification, airport security, inmate tracking, e-commerce and facebook's automatic tag. The aim of face image recognition is to recognize the face of a persons depend on the features extracted from their faces. In this paper, two proposed systems were developed, the conventional proposed system of image recognize include many steps to recognize faces. The first step is the preprocessing of images for all training and testing images. The second step is detecting accurate the accuracy of the face by using Viola and Jones algorithm. The third step is features extraction and selection by using linear discernment analysis (LDA). In the final step the support vector machine (SVM) is applied to reorganize the faces as known or unknown face. The proposed system has been implemented by using a datasets set (MUCT). This dataset is considered taking the processing of faces for frontal position. The results show that the SVM classifier recognition provides an accuracy rate of 99.25% with cuckoo search algorithm, and 96% without cuckoo search algorithm for the same test images. Keywords—Face Detection ; Face Recognition ; Linear Discernment Analysis (LDA); Support Vector Machine (SVM) ; cuckoo search algorithm (CS); Feature Extraction ; MUCT. Viola-Jones 1. Introduction Recently, face image recognition is a rapidly increasing field for its several uses in the several applications such as security, biometric authentication and neuromas other area. There are numerous problems that appear because to the exactness of several factors that affects the feature of image. When processing images one must take into account the variations in light, image quality, the persons pose and facial expressions along with others. The face image recognition is an essential ability of human, but it is hard for face image recognition systems to perform as well as human under different conditions, including illumination, variation of poses, expressions, occlusion..etc [1]. International Journal of Computer Science and Information Security (IJCSIS), Vol. 15, No. 11, November 2017 150 https://sites.google.com/site/ijcsis/ ISSN 1947-5500