Image Classification
- a core task of computer vision
- refers to the task of extracting information classes from a multiband raster image
Image Classification - Challenges
- semantic gap - an image is a tensor of integers between [0, 255] (i.e. 800x600x3 3 channels RGB)
- viewpoint variation - all pixels change when the camera moves
- illumination - all pixels change when the light source changes
- background clutter - some pixels changes when the background of the subject changes
- occlusion - parts of the subject are covered
- deformation - the subject can take various forms
- intraclass variation - the subject contains many subclasses
- context - the environment may modify the subject