algorithm based on Mask technique. The background image
is obtained based on the definitions of different image
regions. In this way, it can reflect the lightness trend of the
image more accurately. In addition, stretching the image after
subtraction with different linear transformation models
improves the uneven contrast phenomenon in the original
image.
Through the experiment, the correctness and validity of this
algorithm are proved, but this algorithm still needs to be
improved in the following aspects:
(1)How to set the size of the image blocks more
appropriately is a difficulty. If the size is too big, the filtering
method based on the definition can't achieve the expected
effect. If the size is too small, this will make the lightness of
the different image regions be approximately the same,
which means dodging is excessive.
(2)How should we set the values of some parameters, such as
the maximum and minimum cut-off frequency automatically?
The selection of these parameters will directly influence the
final dodging effect.
(3)In order to remove more detailed information from the
background image, we can obtain the background image
using the filters with different cut-off frequencies based on
classification of ground objects. This is a recommended topic
for a proposed follow-on study.
REFERENCES
Blohm W.,1997. Lightness Determination at Curved
Surfaces with Application to Dynamic Range Compression
and Model-Based Coding of Facial Images. IEEE
Transactions on Image Processing, 6(8), pp. 1129-1138.
Chandelier L., Martinot G., 2009. A Radiometric Aerial
Triangulation for the Equalization of Digital Aerial Images
and Orthoimages. Photogrammetric Engineering and Remote
Sensing, 75(2), pp. 193-200.
Gasparini F.,Schettini R.,2004. Color Balancing of Digital
Photos Using Simple Image Statistics. Pattern Recognition,
27(6), pp. 1201-1217.
Hu Q.W., Li Q.Q., 2004. Image Restoration Based on Mask
Technique. Geomatics and Information Science of Wuhan
University, 29(4), pp. 317-323.
Jin S.Y., Bao G.S., Ma H.C., ShenTu H.G., 2000. Removing
Non-uniform Illumination of Deep-sea Floor Pictures.
Journal of Wuhan Technical University of Surveying and
Mapping, 25(6), pp. 134-136.
Li D.R., Wang M., Pan J.,2006. Auto-dodging Processing
and Its Application for Optical RS Images. Geomatics and
Information Science of W uhan University, 31(9), pp. 753-
756.
Li J.W., 1995. A Heuristic Image Preprocessing Approach in
Automatic Visual Inspection. Opto-Electronic Engineering,
22(3), pp. 36-42.
Li Z.J., 2005. Theory and Practice on Tone Reproduction of
Color Photos, Ph.D. Dissertation. Wuhan University, Wuhan,
China.
Russ J.C.,1999. The image processing handbook, Third
edition, CRC Press LLC, New York, USA.
Sun M.W., 2008. Research on Key Technology of
Automatical and Fast DOM Generation, Ph.D. Dissertation,
Wuhan University, Wuhan, China.
Wang M., Pan J., 2004. A Method of Removing the Uneven
Illumination for Digital Aerial Image. Journal of Image and
Graphics, 9(6), pp. 744-748.
Zhou S.T., Xuan J.B.,1999, Restoration Technique Based on
Image Features. Journal of Wuhan Technical University of
Surveying and Mapping,24(3), pp. 230-234.
Zhang Z.X., Li Z.j., Zhang J.Q., Zheng L., 2003. Use discrete
chromatic space to tune the image tone in color image
mosaic. The Third International Symposium on Multispectral
Image Processing and Pattern Recogniton(MIPPR '03),
Beijing, China.
Zhen J., Xu C.G., Xiao D.G., Li H., Huang H., 2003. The
Technique of Digit Image's Illumination Uneven Elimination.
Transactions of Beijing Institute of Technology, 23(3), pp.
285-289.
KEY W
ABSTR.
A metho
color coi
urban ae
algorithr
Finally, :
experime
image sh
should n
Shadows
inevitabl
contrast
shadows
image. S
for a met
by high-
shadows
recogniti
especiall
shadow
sensing 1
There is
most cor
Scene im
include:
domain c
the shad
(Fredemt
calculatii
get the ;
(Arbel et
calculatic
are comp
Shor et a
it needs
process i
inpaintin
seamless
regions. '
the effec
is not an
Compare
images h
* Corre