基于知识库的手写体数字识别(2)

参考文献

[1]钱谡. 基于图像处理的字符识别系统研究[M]. 河北农业大学，2007.

[2]范艳峰，肖乐，甄彤.自由手写体数字识别技术研究[J]. 计算机工程，2005. [3]阮秋琦. 数字图像处理[M]. 北京:电子工业出版社，2001.

[4]杨丹，赵海滨，龙哲. MATLAB图像处理实例详解. 北京：清华大学出版社，2012. [5] Sahel Ba-Karait NO，ShamsuddinS M．HandwriRendigits recognition using

particleswarmoptimization[C]．Modeling&Simulation，2008．AICMS08．Second AsiaInternational Conference on．IEEE，2008：6 1 5．6 1 9．

6

源代码

本程序采用模块化编程的思想进行设计，不同的函数模块实现各自的一个功能，然后由功能模块对各函数模块进行整合与调用。最后，再在主函数模块中调用功能模块，实现程序的最终功能。 二值化模块：

function bw = Bw_Img(I) if ndims(I) == 3 I = rgb2gray(I); end

bw = im2bw(I, graythresh(I)); bw = ~bw;

归一化模块

function I1 = Normalize_Img(I) if ndims(I) == 3 I = rgb2gray(I);

end

I1 = imresize(I, [24 24], 'bicubic');

特征提取模块

function num= Main_Process(I, flag) if nargin < 2 flag = 1; end

I1 = Normalize_Img(I); bw1 = Bw_Img(I1); bw2 = Thin_Img(bw1); bw = bw2; sz = size(bw);

[r, c] = find(bw==1);

rect = [min(c) min(r) max(c)-min(c) max(r)-min(r)]; vs = rect(1)+rect(3)*[5/12 1/2 7/12]; hs = rect(2)+rect(4)*[1/3 1/2 2/3]; pt1 = [rect(1:2); rect(1:2)+rect(3:4)];

pt2 = [rect(1)+rect(3) rect(2); rect(1) rect(2)+rect(4)]; k1 = (pt1(1,2)-pt1(2,2)) / (pt1(1,1)-pt1(2,1)); x1 = 1:sz(2);

y1 = k1*(x1-pt1(1,1)) + pt1(1,2);

k2 = (pt2(1,2)-pt2(2,2)) / (pt2(1,1)-pt2(2,1)); x2 = 1:sz(2);

y2 = k2*(x2-pt2(1,1)) + pt2(1,2); if flag

figure('Name', '数字识别', 'NumberTitle', 'Off', 'Units', 'Normalized', 'Position', [0.2 0.45

7

0.5 0.3]);

subplot(2, 2, 1); imshow(I, []); title('原图像', 'FontWeight', 'Bold');src=I;

subplot(2, 2, 2); imshow(I1, []); title('归一化图像', 'FontWeight', 'Bold');guiYi=I1; hold on;

h = rectangle('Position', [rect(1:2)-1 rect(3:4)+2], 'EdgeColor', 'r', 'LineWidth', 2); legend(h, '数字区域标记', 'Location', 'BestOutside');

subplot(2, 2, 3); imshow(bw1, []); title('二值化图像', 'FontWeight', 'Bold');erZh=bw1; subplot(2, 2, 4); imshow(bw, [], 'Border', 'Loose'); title('细化图像', 'FontWeight', 'Bold');xiHua=bw; hold on; h = [];

for i = 1 : length(hs)

h = [h plot([1 sz(2)], [hs(i) hs(i)], 'r-')]; end

for i = 1 : length(vs)

h = [h plot([vs(i) vs(i)], [1 sz(1)], 'g-')]; end

h = [h plot(x1, y1, 'y-')]; h = [h plot(x2, y2, 'm-')];

legend([h(1) h(4) h(7) h(8)], {'水平线', '竖直线', '左对角线', '右对角线'}, 'Location', 'BestOutside'); hold off; end

v{1} = [1:sz(2); repmat(hs(1), 1, sz(2))]'; v{2} = [1:sz(2); repmat(hs(2), 1, sz(2))]'; v{3} = [1:sz(2); repmat(hs(3), 1, sz(2))]'; v{4} = [repmat(vs(1), 1, sz(1)); 1:sz(1)]'; v{5} = [repmat(vs(2), 1, sz(1)); 1:sz(1)]'; v{6} = [repmat(vs(3), 1, sz(1)); 1:sz(1)]'; v{7} = [x1; y1]'; v{8} = [x2; y2]'; for i = 1 : 8

num(i) = GetImgLinePts(bw, round(v{i})-1); end

num(9) = sum(sum(endpoints(bw)));

计算交点函数：

function num = GetImgLinePts(bw, v) num = 0;

for i = 1 : size(v, 1)

if v(i, 2)>1 && v(i, 2)1 && v(i, 1)

num = num + 1; end

8

end

计算端点函数：

function num = GetImgEndPts(bw)

num = 0;

for i = 1 : size(bw, 1)

for j = 1 : size(bw, 2)

if i>2 && i2 && j

&& sum(sum(bw(i-1:i+1, j-1:j+1)))==1 num = num + 1; end end end 匹配识别模块：

function result = MaskRecon(Data, v) for i = 1 : size(Data, 1)

dis(i) = norm(v-Data(i, :)); end

[mindis, ind] = min(dis); if ind < 11

result = ind-1; else

result = ind-11; end

主函数模块

function res = ShowNum( img ) load Data.mat

v=Main_Process(img,0); res=MaskRecon(Datas,v);

msgbox(sprintf('识别结果:%d',res),'提示信息','modal'); end

9