Object detection deals with detecting the presence of objects such as human face, car, buildings, road symbol, etc.,. For surveillance and security based applications, automatic object detection is efficient than manual operation. Existing object detection techniques are limited to small sized images, and detect the human face at lesser frames per second. This paper focus on face objects detection of independent image size using Adaptive Boost algorithm. Adaptive Boost algorithm is a machine learning algorithm. It consists of a training phase, where the required threshold values are estimated from training images. In the training phase the rectangular sum of features is calculated to obtain an integral image. The use of the integral image is to compute the sum of the rectangular features rapidly. This is followed by a testing phase, where the estimated threshold values are used in the detection of face objects. It passes to many stages to detect the object. If the object in the image is larger than search window size and feature size, it will not detect the object. So the image is scaled and then the object is found. The algorithm has been extended to detect faces in videos as well. The algorithm is simulated in MatLab 7 to detect objects in any image with a frame rate that can vary for various applications and input image frame sizes.