this is for holding javascript data
Miguel Tuazon edited To_detect_the_face_the__.tex
about 8 years ago
Commit id: c4d13af312331ef8f94ab7066dcbdbf41cb622a8
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}.