Query Initialization by Virtual Query Image and Pre-initial Query Feedback

One of the main problems in content-based image retrieval is the query initialization and so-called "page-zero problem". The early solutions range from the use of similar images to definition of a user sketch (using color, texture, or shape information). The latter implies user\´s choice of a starting point, which can be achieved in different ways. In this paper a new approach to this problem is proposed based on relevance feedback. The objective is to provide a very simple interface, where at each iteration the user should make a binary decision based on two presented images. Experimental results show that the proposed approach performs very well compared to existing methods, while providing a very simple and intuitive interaction