| 摘要 |
<p>The invention provides a method for actualizing a high-speed object recognition process in an object recognition which extracts feature vectors from an input image where an object is captured, the feature vectors representing the object with the large number of the feature vectors; and retrieves, among an image database, one or more images whose features are matched. The invention also provides a method for saving a memory capacity required for the image database. Suggested are methods each of the methods being capable of reducing a processing time required to perform a task which recognizes the object described by a plurality of the feature vectors with use of an approximate nearest neighbor search technique. One of the suggested methods is actualized by excluding such feature vectors that a large number of feature vectors are present in the vicinity and a large number of distance calculations, therefore, are required. Another suggested method is actualized by only performs voting using a hash table without performing any distance calculation. Moreover, another suggested method is actualized by connecting recognizers in cascaded manner each of which uses the nearest neighbor search technique, varying a degree of approximation applied to the object recognition in accordance with the input image, thereby significantly increasing efficiency.</p> |
