Region Naming Strategy for Image Parsing Using Neural Network

摘要

The object recognition problem is to determine which, if any, of a given set of objects appear in a given image or image sequence. Thus object recognition is a problem of matching models from a database with representations of those models extracted from the image luminance data. we propose a approach to the object recognition problem, motivated by the recent availability of large annotated image collections. In this approach we use the translation of image regions to words, similar to the translation of text from one language to another. The lexicon for the translation is learned from large annotated image collections, which consist of images that are associated with text. In this approach, we first segment the image into region, each of this region is represented by a token. The region are clustered in the tokens. This tokens are then match with the database to identify objects.