Image processing is one of the most significant areas of computer science. Every day we have to deal with face recognition for various purposes such as security authentication systems, identification, matching images, etc. This research paper proposed a system model for recognizing human face using the combination of Principal Component Analysis (PCA) and Support Vector Machine (SVM). PCA is used to process data and extract useful features from images including reduction of dimensionality, increasing interpretability, and diminishing information loss of the given image. This model provided a comparative analysis based on the results of recognition accuracy achieved by (SVM), k-Nearest Neighbors (k-NN), Naive Bayes (NB), and Decision Tree (DT) classifier. The aim of this paper is to provide the most efficient and accurate method to recognize human face including data preprocessing using a small dataset and lower-end device. Various soft computing-based approaches have been considered in this study. The experimental result of this method reveals that the way we processed our data, the SVM technique displays robust performance and increases the efficiency of the human face recognition technique with the utmost level of accuracy than the other three.