Human face recognition is distinguished by a method of identifying facts or confirmation that tests personality. The technique essentially relies on two stages, one is face identification, and another is face recognition. Facial recognition applies to a PC device with a few implementations in which human faces can be identified in pictures. Usually, facial identification is achieved by using “right” data from full-frontal facial photographs. Although there are a variety of situations in which full frontal faces are not visible, blemished faces captured by CCTV cameras are an excellent demonstration. Subsequently, the use of fractional facial data as tests is still, to a large extent, an unexplored field of research on the PC-based face recognition problem. In this research, through using incomplete facial evidence to concentrate on face recognition. By implementing critical analysis to evaluate the presentation of AI using the Haar Cascade Classifier is proposed and used to build our framework. There are three phases of the proposed face detection method such as the face data gathering (FDG) process, train the stored image (TSI) phase, face recognition using the local (FRUL) binary patterns histograms (LBPH) algorithm, and this classifier computation was tested by splitting it into four phases. In this analysis, Haar feature selection is applied to complete the detection phase, and also to generate an integral image, Adaboost preparing, Cascading Classifiers. To complete this venture's human protection facial recognition framework with face detection, local binary patterns histograms (LBPH) is used to estimate the model. In LBPH, a few parameters are used and a dataset is obtained by implementing an algorithm. By adding the LBPH operation and extracting the histograms, I got the Final computational part. “Image Processing Based Human Face Recognition Using Haar Cascade Classifier” Image Processing-Based Human Face Recognition Using Haar Cascade Classifier.