Gender Recognition from Facial Sketch Images using Local Adaptive Structural Pattern

Md Tauhid Bin Iqbal, Oksam Chae

http://doi.org/10.5626/JOK.2018.45.8.866

In this paper, we present a new edge-based local image descriptor named Local Adaptive Structural Pattern (LASP), for the recognition of gender from facial sketch images. LASP generates eight directional edge responses of a pixel by applying Kirsch compass masks and selects top two directions to represent the local texture structure. Moreover, LASP applies an adaptivelyselected threshold on the top directional response in order to filter the low response of the flat pixels producing spurious codes. The top two Kirsch directions represent the local texture structure appropriately, whereas the imposed threshold on the top Kirsch-response differentiates the spurious codes generated from the flat regions, yielding a compact description of the facial sketches. We evaluate the performance of LASP in existing facial sketch datasets for the recognition of gender and observe improved accuracies compared to existing local descriptors.