Web image retrieval using self-organizing feature map

The explosive growth of digital image collections on the Web sites is calli ng for an efficient and intelligent method of browsing, searching, and retr ieving images. In this article, an artificial neural network (ANN)-based ap proach is proposed to explore a promising solution to the Web image retriev al (IR). Compared with other image retrieval methods, this new approach has the following characteristics. First of all, the Content-Based features ha ve been combined with Text-Based features to improve retrieval performance. Instead of solely relying on low-level visual features and high-level conc epts, we also take the textual features into consideration, which are autom atically extracted from image names, alternative names, page titles, surrou nding texts, URLs, etc. Secondly, the Kohonen neural network model is intro duced and led into the image retrieval process. Due to its self-organizing property, the cognitive knowledge is learned, accumulated, and solidified d uring the unsupervised training process. The architecture is presented to i llustrate the main conceptual components and mechanism of the proposed imag e retrieval system. To demonstrate the superiority of the new IR system ove r other IR systems, the retrieval result of a test example is also given in the article.