deletions | additions       diff --git a/To_detect_the_face_the__.tex b/To_detect_the_face_the__.tex  index 15b99a5..5dcee4f 100644  --- a/To_detect_the_face_the__.tex  +++ b/To_detect_the_face_the__.tex 
...
To detect the face, the face region obtained from the detection algorithm applied in the RGB image, we extract the same region from the depth image. Four preprocessing stages were applied before the facial feature detection. These preprocessing stages are: edge removal, depth increase, median filter, and low-pass filter. If the face region in the depth image is fitted to an analytic surface (fitting data locally to a paraboloid), it is proved that both regions are almost identical, with the exception of the edges where there are great differences due to discontinuities. Thus, the first preprocessing stage is the removal of the edges in the face region decreasing 30 percent the area of the rectangle obtained by the face detection. Also to decrease the irregularities of the surface depicted in the depth image, a first smoothing is applied through a median filter, with which the depth value of a pixel is the median of the neighboring pixels. As a final stage of the preprocessing, a low-pass filter is applied to smooth the image. A 3 x 3 convolution mask with weights equals to 1/9 was selected. Following the HK classification, image pixels can be labeled as belonging to a viewpoint-independent surface class type based on the combination of the signs from the mean and Gaussian curvatures as shown in Table 1. 3.  \citet{gonzalez2014kinect}