In a computer vision application, images are normally ingested from their source, such as cameras, files stored on a computer disk, or streams from another application. In most cases, these input images are converted from one form into another. For example, we may need to resize, rotate, or change their colors. In some cases, we may need to remove the background pixels or merge two images. In other cases, we may need to find the boundaries around certain objects within an image.
This chapter explores various techniques of image transformation ...
