Content-based image retrieval is a technique which uses visual contents to search images from large scale image databases according to users' interests. Given a query face image, content-based face image retrieval tries to find similar face images from a large image database. Initially face of the image is detected from the query image. After the removal of noise present in the image, it is separated as patches. For each patch, the Local binary pattern (LBP) is extracted which improves the detection performance. LBP is a type of feature used for classification in computer vision. The LBP operator assigns a label to every pixel of a gray level image. The label mapping to a pixel is affected by the relationship between this pixel and its eight neighbors. Support Vector Machine (SVM) is used then which will produce a model (based on the training data) that predicts the target values of the test data given only the test data attributes. When the feature values are provided to the SVM classifier, it will train about the feature. Finally it will classify about the result. SVM maps input vectors to a higher dimensional vector space where an optimal hyper plane is constructed. Among the available hyper planes, there is one hyper plane alone that maximizes the distance between itself and the nearest data vectors of each category. The Euclidean distance between the query image and database image is calculated and the index of the Euclidean distance is sorted.The indexing scheme used for this purpose provides an efficient way to search the image. Then the corresponding image from the database is retrieved based upon the index. This SVM classifier mainly improves the detection performance and the rate of accuracy.