Plate Character Segmentation Algorithm Based on Projection Feature and Prior Knowledge

2013 ◽  
Vol 790 ◽  
pp. 677-681
Author(s):  
Jun Liu ◽  
Jun Xiang ◽  
Chun Long Xu

nfluenced by factors like mud, frame, rivet, space mark and plate slant, plate character segmentation tends to be inaccurate and even results in mistakes. In order to tackle these problems, this paper puts forward a plate character segmentation algorithm based on projection feature and prior knowledge. That is, firstly of all, to carry out horizontal coarse segmentation by horizontal projection, then use both vertical projection and prior knowledge to conduct vertical segmentation. At last, to carry out horizontal fine segmentation by local projection. The experiment demonstrates that such algorithm can solve the above mentioned problems accurately and practically with high-efficiency.

2012 ◽  
Vol 546-547 ◽  
pp. 1345-1350
Author(s):  
Lian Huan Li

Character Segmentation is the key step for image text recognition. This paper presents a text tilt correction algorithm using tracked characteristics rectangle contour to extract angle, using line scan method based on the number of transitions to determine the character on the bottom. In order to meet the requirements of real-time and reliability, takes improved secondary single-character segmentation algorithm based on vertical projection method.


2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J Jouan ◽  
I Masari ◽  
V Bliah ◽  
G Soulat ◽  
D Craiem ◽  
...  

Abstract Introduction In order to improve knowledge of the tricuspid valve (TV) function and its coupling with the right atrio-ventricular junction (RAVJ) and right ventricle (RV), new four-dimensional high-definition imagery methods are mandatory (3D+t). Purpose Using an innovative reconstruction method based on multiphase cardiac computed tomography imaging (4D-MCCTI), we finely analyzed the morphological & dynamical features of tricuspid annulus (TA) and RAVJ components in order to assess new functional parameters of TV and RV functions. Methods Volume imaging data sets through time were obtained from 4D-MCCTI of 30 subjects (sex ratio 1, mean age 57±11y.) with no rhythm, valvular or ventricular abnormalities on echocardiography and implemented in a custom software for 3D semi-automated delineation of 18 points around TA perimeter. Coordinates of these points in each of the 10 time-phases within an RR interval were used to calculate specific geometrical features of TA such as 3D/2D areas, perimeters, 360°-diameters and vertical deformation. Subsequently, RV and Right Atrium (RA) inner contours were also delineated (Figure). Results TA shape was elliptical in horizontal projection with a mean eccentricity index (EcI) of 0.58±0.12; and saddle-shapped in vertical projection with a horn nearby the antero-septal commissure. This feature remained throughout the cardiac cycle but TA was more planar (minimal TA-height: 4.47±1.04 mm) and circular (minimal EcI=0.44±0.14) in mid-diastole when TA-3Darea and TA-3Dperimeter reached a maximum of 6.98±1.21 cm2/m2 and 7.41±0.91 cm, respectively. Correlation between TA-3Darea, TA-2Darea and latero-septal diameter (LSD) were R2=0.99 and R2=0.73, respectively. LSD was minimal in early-systole (18.83±3.04 mm/m2) and maximal in mid-diastole (20.04±3.05 mm/m2). Correlation of TA-3Darea with RV and RA cross-sectional areas were R2=0.82 and R2=0.71, respectively. Conversely, there was no significant correlation between TA, RV and RA concentric contractions. Conclusions Our method for 4D-MTCCI analysis has allowed confirming the shape and dynamics function of RAVJ throughout the cardiac cycle in healthy subjects, and giving new reference parameters for TV and RV evaluation. Software multiplanar view of TA Funding Acknowledgement Type of funding source: None


1985 ◽  
Vol 16 (4) ◽  
pp. 66-75 ◽  
Author(s):  
Osamu Nakamura ◽  
Makoto Ujiie ◽  
Noriyoshi Okamoto ◽  
Toshi Minami

2019 ◽  
Vol 16 (5) ◽  
pp. 831-835
Author(s):  
Dingsheng Hu ◽  
Anthony P. Doulgeris ◽  
Xiaolan Qiu ◽  
Bin Lei ◽  
Yan Jin

Sign in / Sign up

Export Citation Format

Share Document