论文信息 - An approach to apple surface feature detection by machine vision

An approach to apple surface feature detection by machine vision

Abstract This paper presents a new technique for the detection of surface features in apple images. By introducing the concept of topographic representation for these images, the detection of the patch-like features is treated as one of catchment basin detection in apple grey-level landscapes. A flooding algorithm is adopted and modified to detect the catchment basins, i.e. the features. The implementation of the algorithm is explained in detail. After the flooding process, the catchment basins become lakes for which geometric parameters such as area and perimeter can easily be extracted. The test results of the proposed technique on Golden Delicious and Granny Smith apples are presented. A comparison with the existing background subtraction method has been made to show the advantages of the new approach. In a more general way, the proposed method is applicable to feature detection for other types of produce which have relatively uniform skin colour.

Q. Yang | Q. Yang

[1] Jean Serra,et al. Image Analysis and Mathematical Morphology , 1983 .

[2] Valenciano García. Estimate of quality losses of fruit and vegetables in packinghouses with special reference to mechanical damages. , 1990 .

[3] G. E. Rehkugler,et al. Apple Sorting with Machine Vision , 1985 .

[4] Q. Yang,et al. The potential for applying machine vision to defect detection in fruit and vegetable grading , 1992 .

[5] Luc Vincent,et al. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[6] J. Dozier,et al. Automated basin delineation from digital elevation data , 1984 .

[7] Jan-Olof Eklundh,et al. On the computation of a scale-space primal sketch , 1991, J. Vis. Commun. Image Represent..

[8] Q. Yang,et al. Classification of apple surface features using machine vision and neural networks , 1993 .

[9] F. Sevila,et al. Automatic detection of surface defects on fruit by using a vision system , 1988 .

[10] Harold Lorin,et al. Sorting and sort systems , 1975 .

[11] P. Soille,et al. Automated basin delineation from digital elevation models using mathematical morphology , 1990 .

[12] J. Kampp,et al. Quality of imported and domestic fruits and vegetables in the Danish retail trade with special reference to mechanical damages. , 1990 .