An image processing apparatus that can obtain a high-definition image by reducing an alignment mistake of a plurality of images. The image processing apparatus includes an alignment unit that performs sequential alignment that aligns adjacent images and reference alignment that aligns images other than a reference image to the reference image, and a control unit that controls the alignment unit to align a plurality of images that include a same object and are continuously picked up by an image pickup unit in time series by combining the sequential alignment and the reference alignment.