Color Image Segmentation of Seed Images Based on Self-Organizing Maps (SOM) Neural Network

J. M. Barrón Adame, M. S. Acosta Navarrete, J. Quintanilla Domínguez, R. Guzmán Cabrera, M. Cano Contreras, B. Ojeda Magaña, E. García Sánchez


This paper presents a threshold color image segmentation methodology based on Self-Organizing Maps (SOM) Neural Network. The objective of segmentation methodology is to determine the minimum number of color features in six seed lines ("nh1", "nh2", "nh3", "nh4", "nh5" y "nh6") of seed castor (Ricinus comunnis L.) images for future seed characterization. Seed castor lines are characterized for pigmentation regions that not allow an optimum segmentation process. In some cases, seed pigmentation regions are similar to background make difficult their segmentation characterization. Methodology proposes to segment the seed image in a SOM-based idea in an increasing way until to some of SOM neuron not have allocated none of the image pixels. Several experiments were carried out with others two standard test images ("House" and "Girl") and results are presented both visual and numerical way.


Image segmentatio, neural networks, self-organizing maps

Full Text: PDF