ABSTRACT
In this paper, we propose a new apple segmentation and recognition method based on improved Gaussian kernel combining fuzzy c-means and convolutional neural network. The importance of determining data distribution characteristics is analyzed. The convolution neural network with good self-learning ability is used to supervised learn the image and extract the image features. Meanwhile, the modified fuzzy c-means is used for feature clustering analysis. We modify the selection of radial width to improve Gaussian kernel function and use it for support vector machine, which will classify the extracted features. Finally, experiments on Fuji apple images demonstrate that the robustness stability and accuracy of the proposed algorithm is better than other state-of-the-art representative methods.