Three-Level Broad-Edge Template Matching and Its Application to Real-Time Vision System
スポンサーリンク
概要
- 論文の詳細を見る
This paper presents a new internal image representation, in which the scene is encoded into a three-intensity-level image. This representation is generated by Laplacian-Gaussian filtering followed by dual-thresholding. We refer to this image as three-level broad-edge representation. It supresses the high frequency noise and shading in the image and encodes the sign of relative intensity of a pixel compared with surrounding region. Image model search based on cross correlation using this representation is as reliable as the one based on gray normalized correlation, while it reduces the computational cost by 50 times. We examined the reliability and realtime performance of this method when it is applied to an industrial object recognition task. Our prototype system achieves 32 × 32 image model search from the 128 × 128 pixel area in 2 milli-seconds with a 9MHz pixel clock image processor. This speed is fast enough for searching and tracking a single object at video frame rate.
- 社団法人電子情報通信学会の論文
- 1995-12-25
著者
-
Hashimoto Manabu
Advanced Technology R & D Center Mitsubishi Electric Corporation
-
Hashimoto Manabu
Industrial Electronics and Systems Laboratory, Mitsubishi Electric Corp.
-
Sumi Kazuhiko
Industrial Electronics and Systems Laboratory, Mitsubishi Electric Corp.
-
Okuda Haruhisa
Industrial Electronics Lab., Mitsubishi Electric Corp.
-
Sumi Kazuhiko
Advanced Technology R & D Center Mitsubishi Electric Corporation:(present Office)school Of Infor
-
Okuda Haruhisa
Advanced Technology R & D Center Mitsubishi Electric Corporation
-
Kuroda Shin'ichi
Industrial Electronics Lab. Mitsubishi Electric Corp.
関連論文
- A Visual Inspection System Based on Trinarized Broad-Edge and Gray-Scale Hybrid Matching(Image Inspection,Machine Vision Applications)
- Vision System for Depalletizing Robot Using Genetic Labeling
- Three-Level Broad-Edge Template Matching and Its Application to Real-Time Vision System