Application of support vector machine to apple recognition using in apple harvesting robot

Abstract

In the robot vision system of the apple harvesting robot, the key is to recognize and locate the apple. To solve recognition questions such as high error rate, too much calculation and time consuming, a new recognizing method, support vector machine (SVM) is applied to improve recognition accuracy and efficiency. At first, vector median filter is used to remove the color images noise of apple fruit. Secondly, segmentation of the images based on region growing method and color properties is done. Then, color properties and shape properties of color image are extracted, and classification method of SVM for recognition of apple fruit is used. Experimental results indicate that the classification performance of support vector machine is better than that of neural networks. Recognition rate of apple fruit based on SVM of color and shape properties is higher than that of only using the color or shape properties.