Abstract:

Accurate segmentation and localization of apple objects in natural scenes is an important part of wisdom agriculture research for information perception and acquisition. In order to solve the problem that apples recognition and positioning are susceptible to occlusion of leaves in natural scenes, based on the K-means clustering segmentation algorithm, the object recognition algorithm based on convex hull theory was proposed. And the algorithm was compared with the object recognition algorithm based on removing false contours and the full-contour points fitting object recognition algorithm. The object recognition algorithm based on convex hull theory utilized that apples were like circle, combining K-means algorithm with Otsu algorithm to separate fruit from background. The convex polygon was obtained by convex hull theory and fit it circle to determine the position of the fruit. To verify the effectiveness of the algorithm, 157 apple images in natural scenes were tested. The average overlap rates of the object recognition algorithm based on convex hull theory, the object recognition algorithm based on removing false contour points and the full-contour points fitting object recognition algorithm were 83.7%, 79.5% and 70.3% respectively, the average false positive rates were 2.9%, 1.7% and 1.2% respectively, and the average false negative rates were 16.3%, 20.5% and 29.7% respectively. The experimental results showed that the object recognition algorithm based on convex hull theory had better localization performance and environmental adaptability compared to the other two algorithms and had no recognition error, which can provide reference for occluded fruits segmentation and localization in the natural scenes.

Key words: apple recognition, occluded object, convex hull theory, false contour points, K-means clustering algorithm