Similarity-based image retrieval considering artifacts by self-organizing map with refractoriness - Image segmentation by K-means algorithm

In this paper, we propose a similarity-based image retrieval considering artifacts by self-organizing map with refractoriness. In the self-organizing map with refractoriness, the plural neurons in the Map Layer corresponding to the input can fire sequentially because of the refractoriness. The proposed image retrieval system considering artifacts using the self-organizing map with refractoriness makes use of this property in order to retrieve plural similar images. In this image retrieval system, as the image feature, not only color information but also spectrum and keywords are employed. Moreover, the original image is divided into some areas by the K-means algorithm so that each divided area should not contain two or more objects. We carried out a series of computer experiments and confirmed that the effectiveness of the proposed system.