Application of immunological memory to the color classification of tiles

Based on mechanism that the vertebrate immune system remembers the antigen it has met before by retaining in the body some memory cells, an algorithm is proposed to search for the representative of the data set by generating its memory cells. The algorithm is first tested on a two-dimensional data set with three cluster centers to see if the memory cells built could really be representative. Then it is applied to a real world application, where the fuzzy C-means algorithm (FCM) is adopted to classify the tiles into different clusters according to the color similarity. The feature vectors extracted from the tile images act as the antigen and the memory cells generated are regarded as the initial cluster centers. Its performance was compared with that obtained with randomly initialized centers. By this algorithm, the number of clusters does not require to be pre-defined. The convergence speed and clustering accuracy of FCM are also improved.