Jump to content

Pattern matching

From Simple English Wikipedia, the free encyclopedia

Pattern matchingis atoolfor finding similar objects in different sources. Inimage processing,the pattern matching is used for locating a small image (called model) in a bigger one (called target image). For searchingtext,regular expressionsare commonly used.

The simple way is to move the model in the target image and measure a similarity in each position. The position with highest value of similarity will be accepted as result. Thenormalized correlationis used as a measure of similarity.

The common way to reduce calculations is using theimage pyramid.When using the image pyramid, the search is started on the reduced target image, and results are improved in the next, more detailed one. This process is similar to the humanvision.