Automatic visual inspection of wood surfaces

Author

Alapuranen, Pertti ; Westman, Tapani

Author_Institution

Dept. of Electr. Eng., Oulu Univ., Finland

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

371

Lastpage

374

Abstract

A prototype software system for visual inspection of wood defects has been developed. The system uses a hierarchical vector connected components (HVCC) segmentation which can be described as a multistage region-growing type of segmentation. The HVCC version used in experiments uses RGB color vector differences and Euclidean metrics. The HVCC segmentation seems to be very suitable for wood surface image segmentation. Geometrical, color and structural features are used in classification. Possible defects are classified using combined tree-kNN classifier and pure kNN-classifier. The system has been tested using plywood boards. Preliminary classification accuracy is 85-90% depending on the type of defect

Keywords

automatic optical inspection; computerised pattern recognition; computerised picture processing; flaw detection; wood; Euclidean metrics; RGB color vector differences; automatic visual inspection; color features; geometrical features; hierarchical vector connected components segmentation; k-nearest-neighbours classifier; multistage region-growing segmentation; plywood boards; structural features; tree-kNN classifier; wood defects; wood surface image segmentation; Algorithm design and analysis; Humans; Image color analysis; Image segmentation; Inspection; Iterative algorithms; Merging; Prototypes; Robustness; Surface morphology;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.I. Conference A: Computer Vision and Applications, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2910-X

Type

conf

DOI

10.1109/ICPR.1992.201578

Filename

201578