Composite Sketch Recognition Using Multi-Scale HOG Features and Semantic Attributes

Composite sketch recognition belongs to heterogeneous face recognition research, which is of great importance in the field of criminal investigation. Because composite sketch and face photograph belong to different modals, robust representation of face feature across different modals is the key to recognition. Considering that composite sketch face lacks texture details in some area, using texture features only may result in low recognition accuracy, this paper proposes a composite sketch recognition algorithm based on multi-scale HOG features and semantic attributes. Firstly, the global HOG features of the face and the local HOG features of each face component are extracted to represent the structure and detail features. Then the contour and detail features are fused at score level to obtain a candidate matching list. Finally, semantic attributes are employed to reorder the matching result. The proposed algorithm is validated on PRIP-VSGC database and UoM-SGFS database, and achieves rank10 identification accuracy 88.6% and 96.7% respectively, which demonstrates that this method outperforms other state-of-the-art methods.