Incorporating real-valued multiple instance learning into relevance feedback for image retrieval

This paper presents a content-based image retrieval (CBIR) system that incorporates real-valued multiple instance learning (MIL) into the user relevance feedback (RF) to learn the user´s subjective visual concepts, especially where the user´s most interested region and how to map the local feature vector of that region to the high-level concept pattern of the user. RF provides a way to obtain the subjectivity of the user´s high-level visual concepts, and MIL enables the automatic learning of the user´s high-level concepts. The user interacts with the CBIR system by relevance feedback in a way that the extent to which the image samples retrieved by the system are relevant to the user´s intention is labeled. The system in turn applies the MIL method to find user´s most interested image region from the feedback. A multilayer neural network that is trained progressively through the feedback and learning procedure is used to map the low-level image features to the high-level concepts.