Facial Expression Recognition Using Local Composition Pattern
Abu Kalam, Md. Enamul Haque, Mohammad Jashem, Mahamudul Hasan, Muhammad Musa Ibrahim, Taskeed Jabid · 2019
One or more motions or positions of the muscles under the skin of the face is a facial expression. Here, a new image feature descriptor is proposed which is more efficient than Local Binary Pattern (LBP) and Local Derivative Pattern (LDP). In the state of the artwork by thresholding the neighboring pixel values with the central pixel is leveled in each pixel of an image. In our proposed method, edge response is used to detect edges in a radial direction. The directional derivative is computed in the horizontal and vertical direction which is used to extract more discriminatory features. Using neighboring pixels, a new smart threshold is determined. Experimental results show that our method gives a better recognition rate than the existing method. The result proves that it is better than the state of the art descriptors.