Finding the position and area of an object in a visual inspection system

Author

Da Silva, Ernany ParanaguÁ ; Gonzaga, Adilson

Author_Institution

Inst. de Fisica de Sao Carlos, Brazil

fYear

1996

fDate

9-11 Dec 1996

Firstpage

93

Lastpage

98

Abstract

The aim of this work, is the application of the Hough transform (HT) method for automated visual inspection of rectangular boards. Filtering the accumulator array we can extract features such as position (mass center), perimeter and area, despite object translation and rotation. The results reached by this methods are evaluated by comparing them with the method of moments (MM), a largely used method to determine the area and center of mass for bi-directional images. Statistical analysis shows the robustness of Hough transform for noisy images in visual inspection

Keywords

Hough transforms; automatic optical inspection; feature extraction; filtering theory; statistical analysis; Hough transform; accumulator array; area finding; automated visual inspection; bi-directional images; feature extraction; filtering; noisy images; position finding; rectangular boards; rotation independence; statistical analysis; translation independence; visual inspection system; Detectors; Feature extraction; Filtering; Image analysis; Image edge detection; Image segmentation; Inspection; Moment methods; Noise robustness; Statistical analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Cybernetic Vision, 1996. Proceedings., Second Workshop on

Conference_Location

Sao Carlos

Print_ISBN

0-8186-8058-X

Type

conf

DOI

10.1109/CYBVIS.1996.629446

Filename

629446