A local feature-based facial expression recognition system from depth video - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 341

3.1 LDP Features
The LDP assigns an 8-bit binary code to each pixel of an input depth image. This patern is
then calculated by comparing the relative edge response values of a pixel in eight different dir-
ections. Kirsch, Prewit, and Sobel edge detector are some of the diferent representative edge
detectors that can be used. Amongst which, the Kirsch edge detector [ 20 ] detects the edges
more accurately than the others as it considers all eight neighbors. Given a central pixel in the
image, the eight directional edge response values { m k }, k = 0, 1, …, 7 are computed by Kirsch
masks M k in eight different orientations centered on its position [ 18 ] . Figure 4 shows these
masks.
FIGURE 4 Kirsch edge masks in eight directions.
The presence of a corner or an edge represents high response values in some particular dir-
ections and therefore, it is interesting to know the p most prominent directions in order to gen-
erate the LDP. Here, the top- p directional bit responses b k are set to 1. The remaining bits of
8-bit LDP patern are set to 0. Finally, the LDP code is derived in Equation (1) . Figure 5 shows
the mask response as well as LDP bit positions and Figure 6 an exemplary LDP code consid-
ering five top positions, that is, p = 5.
(1)
where m p is the p th most significant directional response.
FIGURE 5 (a) Edge response to eight directions and (b) LDP binary bit positions.
FIGURE 6 LDP code.
Thus, an image is transformed to the LDP map using LDP code. The image textual feature
is presented by the histogram of the LDP map of which the q th bin can be defined as