An image processing device and an image processing method thereof. The image processing device comprises a memory module, an object detection module and a processing module. The memory module is provided for storing a plurality of images captured by a camera module, and the image comprises at least one object. The object detection module retrieves one of the images as a reference image and compares the remaining images with the reference image to locate a region where the object with corresponding contour and color is situated. If the object detection module compares and determines that the object with the corresponding contour and color is situated in different regions of the reference image and the remaining images, the processing module will remove the corresponding object in the reference image or superimpose each corresponding object in the reference image simultaneously.