deletions | additions       diff --git a/To_detect_the_face_the__.tex b/To_detect_the_face_the__.tex  index 5dcee4f..e059f5d 100644  --- a/To_detect_the_face_the__.tex  +++ b/To_detect_the_face_the__.tex 
...
To detect the face, the The  face region area  obtained from the detection algorithm applied in the RGB image, we \citet{gonzalez2014kinect}  extract the same region area  from the depth image. image for the face detection.  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 Though  the face region in the depth image is fitted to with  an analytic surface (fitting data locally information mainly  to a paraboloid), it is proved confirmed  that both regions are almost identical, with the exception of the edges where there are great differences discontinuities  due to discontinuities. this there are a great differences.  Thus, the first start of the  preprocessing stage is the removal of the edges in the face region area  decreasing 30 percent of  the area of the rectangle obtained given  by the face detection. Also to decrease the make  irregularities of the surface smaller  depicted in the depth image, a first primary  smoothing is applied through a median filter, with for  which the depth value of a pixel is the median average  of the neighboring pixels. As a final as the last  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. chosen.  Following the HK classification, image pixels can could  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 3. \citet{gonzalez2014kinect} demonstrated on table 3 \cite{gonzalez2014kinect}.