From Content-Based Image Retrieval by Shape to Image Annotation

In many areas such as commerce, medical investigations, and others, large collections of digital images are being created. Search operations inside these collections of images are usually based on low-level features of objects contained in an image: color, shape, texture. Although such techniques of content-based image retrieval are useful, they are strongly limited by their inability to consider the meaning of images. Moreover, specifying a query in terms of low level features may not be very simple. Image annotation, in which images are associated with keywords describing their semantics, is a more effective way of image retrieval and queries can be naturally specified by the user. The paper presents a combined set of methods for image retrieval, in which both low level features and semantic properties are taken into account when retrieving images. First, it describes some methods for image representation and retrieval based on shape, and proposes a new such method, which overcomes some of the existing limitations. Then, it describes a new method for image semantic annotation based on a genetic algorithm, which is further improved from two points of view: the obtained solution value - using an anticipatory genetic algorithm, and the execution time - using a parallel genetic algorithm.