Professional Documents
Culture Documents
Iiyong-Ho ~ i i r n l Sung-I1
, ~ h i e n 2 Yong-Bum
, ~ e e 3 Iiwang-Soo
,
1Dept. of Image Processing, System Engineering Research Institute, Iiorea.
2 ~ t.e of Elec. Eng., Kyungpook National Univ., Korea
gKliorea Atomic Energy Research Institute, Korea
m e angle of
8
needle
Figure 2: illlalog nietcr txt.raction a.nd
8 the lunction name needle detection
and function name and distribution ter takes a significant part. We can
8 Unll of meter ol scalc
identify meter by recognizing function
name printed on it. For recognizing
function name, each character composing
0
0 i na
+I+
Recopnltlon Module
'TrueMeter Va/uem
function name should be segmented out
successfully[5]. But some difficulties are
expected in extracting characters. First,
the meter image nlay have slant due to
the leveling error of camera. Second, the
Figure 1: Strategies for the automatic ana- gradient in illumination cause the shade
log meter recognition system drawn on the meter surface. These llave
characters touched toghether after blna-
rization. To segment out each characters
2.1 Meter area extraction successfully, region labeling and threshold-
ing technique are applied as well as simple
To extract the meter area from the im- projection algorithm. Each character seg-
age taken by camera installed in mobile mented out is recognized through neural
robot, thresholding is performed as a first network classifier. We used mesh features
step. After binarizing the image, region extracted from 25 characters and a sym-
labeling is applied t o extract the image el- bol('/') as input t o classifier. The specifi-
ements. Using spatial constraints such as cation of neural network is shown in table
area ratio and aspect ratio of region, we 1.
can extract the meter area.