Probabilistic Neural Networks for Segmentation of Features in Corn Kernel Images
A method is presented for clustering of pixel color information to segment features within corn kernel images. Features for blue–eye mold, germ damage, sound germ, shadow in sound germ, hard starch, and soft starch were identified by red, green, and blue (RGB) pixel value inputs to a probabilistic neural network. A data grouping method to obtain an exemplar set for adjustment of the Probabilistic Neural Network (PNN) weights and optimization of a universal smoothing factor is described. Of the 14,427 available exemplars (RGB pixel values sampled from previously collected images), 778 were used for adjustment of the network weights, 737 were used for optimization of the PNN smoothing parameter, and 12,912 were reserved for network validation. Based on a universal PNN smoothing factor of 0.05, the network was able to provide an overall pixel classification accuracy of 86% on calibration data and 75% on unseen data. Much of the misclassification was due to overlap of pixel values among classes. When an additional network layer was added to combine similar classes (blue–eye mold and germ damage, sound germ and shadow in sound germ, and hard and soft starch), network results were significantly enhanced so that accuracy on validation data was 94.7%. Image quality was shown to be important to the success of this algorithm as lighting and camera depth of field effects caused artifacts in the segmented images.
This article is from Applied Engineering in Agriculture 17 (2001): 225–234, doi:10.13031/2013.5447. Posted with permission.