Performing effective image retrieval tasks, capable of exploiting the underlying structure of datasets still constitutes a challenge research scenario. This paper proposes a novel manifold learning approach that exploits the intrinsic dataset geometry for improving the effectiveness of image retrieval tasks. The underlying dataset manifold is modeled and analyzed in terms of a Reciprocal kNN Graph and its Connected Components. The method computes the new retrieval results on an unsupervised way, without the need of any user intervention. A large experimental evaluation was conducted, considering different image retrieval tasks, various datasets and features. The proposed method yields better effectiveness results than various methods recently proposed, achieving effectiveness gains up to +40.75%.

A lot of images are currently generated in many domains, requiring specialized knowledge of identification and analysis. From one standpoint, many advances have been accomplished in the development of image retrieval techniques based on visual image properties. However, the semantic gap between low-level features and high-level concepts still represents a challenging scenario. On another standpoint, knowledge has also been structured in many fields by ontologies. A promising solution for bridging the semantic gap consists in combining the information from low-level features with semantic knowledge. This work proposes a novel graph-based approach denominated Semantic Interactive Image Retrieval (SIIR) capable of combining Content Based Image Retrieval (CBIR), unsupervised learning, ontology techniques and interactive retrieval. To the best of our knowledge, there is no approach in the literature that combines those diverse techniques like SIIR. The proposed approach supports expert identification tasks, such as the biologist's role in plant identification of Angiosperm families. Since the system exploits information from different sources as visual content, ontology, and user interactions, the user effort s required are drastically reduced. For the semantic model, we developed a domain ontology which represents the plant properties and structures, relating features from Angiosperm families. A novel graph-based approach is proposed for combining the semantic information and the visual retrieval results. A bipartite and a discriminative attribute graph allow a semantic selection of the most discriminative attributes for plant identification tasks. The selected attributes are used for formulating a question to the user. The system updates similarity information among images based on the user's answer, thus improving the retrieval effectiveness and reducing the user's effort s required f or identification t asks. The proposed method was evaluated on the popular Oxford Flowers 17 and 102 Classes datasets, yielding highly effective results in both datasets when compared to other approaches. For example, the first five retrieved images for 17 classes achieve a retrieval precision of 97.07% and for 102 classes, 91.33%.

No abstract