An Image Retrieval Method Based on a Genetic Algorithm Controlled by User’s Mind

We live in a world flooded with an ever rising tide of information, making information retrieval technologies more important than ever before in helping users find their way in a user-friendly and efficient manner. Since users see a variety of implications in an image when searching for images, a method for making nonsuperficial inferences regarding each user’s intentions is required, particularly when a system handles abundant and diversified images. Statistical and liner algebraic methods have been often used in conventional research on image retrieval methods, which seek to assess user intentions. One method involves entering language keys, as in the case of picture retrieval[1] based on the entry of “impressional words” and on the entry of image keys, as in the case of similar image retrieval[2][3] for trademark designs and butterfly patterns. However, those methods entail calculations of the relations between language keys and image features and a priori weighing of image features based on training images in order to reflect the user’s mind. Such approaches fare poorly when user intentions are unclear or change during image retrieval. In recent years, techniques intended to facilitate interactions between the user and the retrieval system have received increasing attention. Some reports[4][5][6][7] indicate that it is effective to directly integrate the user’s subjective valuation directly into the retrieval system; this method is not limited to just image retrieval. In particular, genetic algorithms (GA), an evolutionary interactive method, can be used to automatically provide very effective solutions by assigning a fitness value to images, based on user estimations, without requiring the definition of complex estimation functions. This technique has been explored for image retrieval applications such as photomontages of wanted crime suspects[8], nature images retrieval[9], and line drawn portrait retrieval[10]. It is regarded as an effective method for users who cannot articulate their An Image Retrieval Method Based on a Genetic Algorithm Controlled by User’s Mind