coinlq / guji_repository Goto Github PK
View Code? Open in Web Editor NEW华夏文明给我们留下了浩如烟海的文献典籍,古籍的数字化可以让大众更方便更大范围的享受这一文化大餐,弥补不能接触原典的遗憾。古籍数字化中汉字分割是关键环节,诚邀您共同参与。古籍汉字切分算法研究:将古籍扫描图片上的汉字切分出来的算法研究。
License: MIT License
华夏文明给我们留下了浩如烟海的文献典籍,古籍的数字化可以让大众更方便更大范围的享受这一文化大餐,弥补不能接触原典的遗憾。古籍数字化中汉字分割是关键环节,诚邀您共同参与。古籍汉字切分算法研究:将古籍扫描图片上的汉字切分出来的算法研究。
License: MIT License
f = imread('gl_40_76.jpg'); %读原图文件
%f = imread('dh224_b.jpg');
figure(1);imshow(f); %显示原图
g = rgb2gray(f) %彩色图转换为灰度图
figure(2); imshow(g); %显示灰度图
level = graythresh(g); %设定灰度阈值
bw = ~im2bw(g,level); %灰度图转换为二值图
figure(4); imshow(bw); %显示二值图
s = size(bw); %计算矩阵大小
%求图像的列像素累加和
for i = 1:s(2)
gx(i) = 0;
for j = 1:s(1)
gx(i) = gx(i)+ bw(j,i);
end
end
x = 1:s(2);
%line(x, gx,'Color','b'); %显示求和曲线
windowSize = 15; %滤波窗宽
gy = filter(ones(1,windowSize)/windowSize,1,gx); %对曲线进行滑动平均滤波
gy = filter(ones(1,windowSize)/windowSize,1,gy); %再次滤波
gmax = find(diff(sign(diff(gy)))== -2)+1; %求极大值
%line(x, gy,'Color','r'); %绘滤波后的曲线
smax = size(gmax); %极大值点数
ly = 1:s(1) %绘切割竖线
for k = 1:smax(2)
if(k == 1) %左边第一列字两边都划线
lq(1) = gmax(k)-4*windowSize; %左边第一条竖线水平坐标
line(lq(1), ly,'Color','y'); %绘第一条竖线
lq(2) = gmax(k) + windowSize; %第二条竖线的水平坐标
line(lq(2), ly,'Color','y'); %绘第二条竖线
end
lq(k+1) = gmax(k) + windowSize; %其余竖线的水平坐标
line(lq(k+1), ly,'Color','y'); %绘其余的竖线
end
for k = 1:gmax+1 %列字条水平像素累加
for i = 1:s(1)
py(i) = 0;
for j = lq(k):lq(k+1)
py(i) = py(i)+ bw(i,j);
end
end
windowSize = 23; %滤波窗宽
py = filter(ones(1,windowSize)/windowSize,1,py); %对投影曲线滑动滤波
fpy = filter(ones(1,windowSize)/windowSize,1,py); %二次滤波
pmax = find(diff(sign(diff(fpy)))==- 2)+1; %求极大值
psmax = size(pmax); %极值点数
lx = lq(k):lq(k+1);
for m = 1:psmax(2)
hq(m) = pmax(m); %横切线的竖直坐标
line(lx, hq(m), 'Color','r'); %绘横切割线
hold on %保持绘图
end
end
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.