In an image processing apparatus, a shooting scene and shooting parameters for each image pickup apparatus that is to be used to pick up an image are set in accordance with a user input. A picked-up image is received from an image pickup apparatus. In accordance with the shooting scene that is set for the image pickup apparatus which has picked up the received image, a threshold of the likelihood of detecting a face region that is included in the shooting parameters for the shooting scene is obtained. A face region is detected from the picked-up image using the obtained threshold of the likelihood of detecting a face region. An image of the detected face region is highlighted and displayed on a display screen.