def main(img):
"""
主程序
"""
# 二值化: 基于迭代法获取二值化阈值
print("Processing: 二值化...")
k, img_bin = binaryzation(img)
print("阈值:", k)
cv2.imwrite("bin.png", img_bin)
# 基于腐蚀和开运算的骨架提取
print("Processing: 基于腐蚀和开运算的骨架提取...")
img_sk_morph = sk_morph(img_bin)
cv2.imwrite("morph.png", img_sk_morph)
# 基于单纯细化的骨架提取
print("Processing: 基于单纯细化的骨架提取...")
img_sk_thin = sk_thin(img_bin)
cv2.imwrite("morph_thin.png", img_sk_thin)
# 基于距离变换的骨架提取
print("Processing: 基于距离变换的骨架提取...")
img_sk_dist = sk_distTrans(img_bin)
cv2.imwrite("dist.png", img_sk_dist)
# 裁剪:以细化所得骨架为例
print("Processing: 裁剪:以细化所得骨架为例...")
img_result = tailor(img_sk_thin)
cv2.imwrite("tailor.png", img_result)
def read(img):
result = ""
img = binaryzation(img)
#img.show()
imgArray = split(img)
if not imgArray:
return "文本粘连，分割失败"
for singImg in imgArray:
result += compleModel(singImg)
return result
for i in range(h-1,-1,-1):
for j in range(w-1,-1,-1):
temp0=distance[i+2][j+2]+4
temp1=min(temp0,distance[i+2][j+1]+3)
temp2=min(temp1,distance[i+1][j+2]+3)
temp3=min(temp2,distance[i+2][j]+4)
distance[i+1][j+1]=min(temp3,distance[i+1][j+1])
return distance
if __name__=='__main__':
start=time.clock()
img=cv2.imread('in\\fingerPrint.jpg',0)
img=binaryzation.binaryzation(img,100)
plt.subplot(1,2,1)
plt.imshow(img,'gray')
skeleton=dis_ske(img)
plt.subplot(1,2,2)
plt.imshow(skeleton, 'gray')
plt.show()
end=time.clock()
print(end-start)