Content-Based Design Patent Image Retrieval Using Structured Features and Multiple Feature Fusion

Traditional design patent verification based on manual comparison is too labor-intensive, time-consuming and subjective to be applied efficiently in practice. Design patent image retrieval system is designed to retrieve some similar patent images with much visual similarities. Structured features and multiple feature fusion are two main technologies to ensure the retrieval accuracy in the system. Block-wise Dense SIFT (Block-DSIFT), Pyramid Histograms of Orientation Gradients (PHOG), and GIST are proposed as main structured features. A multiple feature fusion algorithm for content-based design patent image retrieval is proposed to formulate the fusion as the linear combination of different matrixes which represent different feature distances between images to improve the precision of retrieval. The weights that reflect the significance of the features are determined by quadratic programming and can be solved efficiently. Experiments on a database of real design patent images show good efficiency and robustness of the proposed method and the system can be applied to design patent copyright validation.