deletions | additions       diff --git a/The_depth_images_acquired_by__.tex b/The_depth_images_acquired_by__.tex  index cb63559..149dad0 100644  --- a/The_depth_images_acquired_by__.tex  +++ b/The_depth_images_acquired_by__.tex 
...
The depth images acquired by the Kinect sensor usually need to be pre-processed to overcome the noisy and low-quality nature of the images. The are pre-processed same as GONZALES’s study. Then, the face point cloud is smoothed and re-sample to a grid of 96 x 96. Examples of cropped 2D and 3D face images are shown in Fig Figure  16. \citet{boutellaa2015use}