Standard test image

Actual test image of jelly beans from the USC-SIPI image database.

A standard test image is a digital image file used across different institutions to test image processing and image compression algorithms. By using the same standard test images, different labs are able to compare results, both visually and quantitatively. The images are in many cases chosen to represent natural or typical images that a class of processing techniques would need to deal with. Other test images are chosen because they present a range of challenges to image reconstruction algorithms, such as the reproduction of fine detail and textures, sharp transitions and edges, and uniform regions.

Common test images

The standard size of the images are usually 512×512 or 720×576. Most of these images are available as TIFF files from the University of Southern California's Signal and Image Processing Institute. Kodak has released a set of 24 768×512 images, available as PNGs, that are widely used for comparing image compression techniques.

See also

• FERET database (DARPA/NIST face recognition database)
• Lenna

External links

• The USC-SIPI Image Database — A large collection of standard test images
• Computer Vision website — A large collection of links to various test images
• A Few Test Images — Collection of various test images
• Vision @ Reading — University of Reading's set of popular test images
• CIPR still images — Some sets of test images at Rensselaer Polytechnic Institute (including the Kodak set)
• True-color Kodak test images — The Kodak set in PNG format
• Compression Database — The superset of all available (as well as taken down) corpora used for image compression, segmentation and classification, contains most of the images of the mentioned standard corpora with detailed information about relevant quantities (entropy, statistics, etc.)
• TESTIMAGES — Large database of free images for testing image processing methods. The archive includes reference images for standard interpolation (enlargement) methods, testing scripts and calculated metrics(CC BY-NC-SA 3.0).