Description

A fast novel algorithm that requires minimal strokes and parameter tuning from users, segments the desired selection, and produces an adaptive feathered matte. Our approach consists of two steps: first, the algorithm extracts color similarities using radial basis functions; second, the algorithm segments the region the user selects to respect locality. Because of the linear complexity and simplicity in required user-input, the approach is suitable for multiple applications including mobile devices. In our beautification framework, a portrait is decomposed into smoothness, lighting, and color layers by an edge-preserving operator. Next, facial landmarks and significant features are extracted as input constraints for mask generation. After three region-aware masks have been obtained, a user can perform facial beautification simply by adjusting the skin parameters. Furthermore, the combinations of parameters can be optimized automatically, depending on the data priors and psychological knowledge . To polish selected skin region, we apply bilateral filter to smooth the facial flaw. Last, we use Poisson image cloning to integrate the beautified parts into the original input. Experimental results show that the proposed method can be applied in varied light source environment. In addition, this method can naturally beautify the portrait skin