A Neurocomputational Approach to the Correspondence Problem in Computer Vision (Special Issue on Neurocomputing)

スポンサーリンク

概要

• 論文の詳細を見る

• A problem which often arises in computer vision is that of matching corresponding points of images. In the case of object recognition, for example, the computer compares new images to templates from a library of known objects. A common way to perform this comparison is to extract feature points from the images and compare these points with the template points. Another common example is the case of motion detection, where feature points of a video image are compared to those of the previous frame. Note that in both of these examples, the point correspondence is complicated by the fact that the point sets are not only randomly ordered but have also been distorted by an unknown transformation and having quite different coordinates. In the case of object recognition, there exists a transformation from the object being viewed, to its projection onto the camera's imaging plane, while in the motion detection case, this transformation represents the motion (translation and rotation) of the object. If the parameters of the transformation are completely unknown, then all n! permutations must be compared (n: number of feature points). For each permutation, the ensuing transformation is computed using the least-squared projection method. The exponentially large computation required for this is prohibitive. A neural computational method is proposed to solve these combinatorial problems. This method obtains the best correspondence matching and also finds the associated transform parameters. The method was applied to two dimensional point correspondence and three-to-two dimensional correspondence. Finally, this connectionist approach extends readily to a Boltzmann machine implementation. This implementation is desirable when the transformation is unknown, as it is less sensitive to local minima regardless of initial conditions.

• 社団法人電子情報通信学会の論文
• 1994-04-25

著者

• Sako Hiroshi

  Hitachi Ltd. Kokubunji‐shi Jpn

• Sako H

  Hitachi Dublin Laboratory Research &amp Development Centre Hitachi Europe Ltd.

• Sako Hiroshi

  Hitachi Dublin Laboratory Research &amp Development Centre Hitachi Europe Ltd. O'reilly Ins

• Avi-Itzhak Hadar

  Department of Electrical Engineering, Stanford University

• Avi-itzhak Hadar

  Department Of Electrical Engineering Stanford University

関連論文

• Handwritten Numeral String Recognition : Effects of Character Normalization and Feature Extraction(String Recognition, Document Image Understanding and Digital Documents)
• A Hardware Implementation of a Neural Network Using the Parallel Propageted Targets Algorithm (Special Issue on Neurocomputing)
• A Hierarchical Classification Method for US Bank-Notes(Pattern Discrimination and Classification,Machine Vision Applications)
• A Neurocomputational Approach to the Correspondence Problem in Computer Vision (Special Issue on Neurocomputing)

スポンサーリンク