Tree Representation and Feature Fusion Based Method for Multi-object Binary Image Retrieval

摘要

The images with multi-objects are common in multimedia information, such as trademark, symbol and medical image. However state of the art image retrieval systems designed specially for multi-object images are rare. This paper proposes an effective solution for multi-object binary images retrieval by fusing several features. We first employ a Tree Representation Model (TRM) to describe the topology-structure of multi-object binary images. Secondly, we propose two new descriptors to describe the density and the spatial location feature of the objects, respectively. In addition, we combine two descriptors and shape feature to distinguish the difference of the image objects. Finally, the similar matching algorithm based on TRM is given and applied to trademark database retrieval. Experiment shows our method is superior to previous methods in search similar binary images with multi-objects.