Combining greyvalue invariants with local constraints for object recognition

This paper addresses the problem of recognizing objects in large image databases. The method is based on local characteristics which are invariant to simzlarity transformations in the image. These characteristics are computed at automatically detected keypoints using the greyvalue signal. The method therefore works on images such as paintings for which geometry based recognition fails. Due to the locality of the method, images can be recognized being given part of an image and in the presence of occlusions. Applying a voting algorithm and semi-local constraints makes the method robust to noise, scene clutter and small perspective deformations. Experiments show an eficient recognition for different types of images. The approach has been validated on an image database containing io20 images, some of them being very similar by structure, texture or shape.

• Type: Conference
• Year: 1996
• Where: CVPR
• Authors: Cordelia Schmid, Roger Mohr
• Keywords: Computer Vision, CVPR 1996, Geometry Based Recognition, Image Database, Large Image Databases, Method Robust, Small Perspective Deformations