A New Type of ART2 Architecture and Application to Color Image Segmentation

作者：Ai Jiaoyan; Funt Brian; Shi Lilong

来源：18th International Conference on Arificial Neural Networks (ICANN 2008), 2008-09-03 to 2008-09-06.

• ART2
• similarity measurement
• unsupervised segmentation
• color image

A new neural network architecture based on adaptive resonance theory (ART) is proposed and applied to color image segmentation. A new mechanism of similarity measurement between patterns has been introduced to make sure that spatial information in feature space, including both magnitude and phase of input vector, has been taken into consideration. By these improvements, the new ART2 architecture is characterized by the advantages: (i) keeping the traits of classical ART2 network such as self-organizing learning, categorizing without need of the number of cluster, etc.; (ii) developing better performance in grouping clustering patterns; (iii) improving pattern-shifting problem of classical ART2. The new architecture is believed to achieve effective unsupervised segmentation of color image and it has been experimentally found to perform well in a modified L*u*v* color space in which the perceptuall color difference can be measured properly by spatial information.

• 出版日期2008
• 单位广西大学