opencv 字符识别(OCR)

本项目是为了实现数字识别（ocr），包括训练模型代码和识别代码

训练模型：

import sys
import numpy as np
import cv2

im = cv2.imread('test6.png')
im3 = im.copy()

gray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),0)
thresh = cv2.adaptiveThreshold(blur,255,1,1,11,2)

#################      Now finding Contours         ###################

contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)

samples =  np.empty((0,100))
responses = []
keys = [i for i in range(44,58)]

for cnt in contours:
    if cv2.contourArea(cnt)>5: #大于像素点的区域
        [x,y,w,h] = cv2.boundingRect(cnt)
        print([x,y,w,h])#对应的区域的坐标
        if  (h>13 and h < 20) or (h>2 and h < 7 and w > 4):#筛选不需要的区域
            cv2.rectangle(im,(x,y),(x+w,y+h),(0,0,255),2)
            roi = thresh[y:y+h,x:x+w]
            roismall = cv2.resize(roi,(10,10))
            cv2.imshow('norm',im)
            key = cv2.waitKey(0)
            print(key)

            if key == 27:  # (escape to quit)
                sys.exit()
            elif key in keys:
                key = str(key)
                print(key)
                responses.append(int(key))#保存ascii码
                sample = roismall.reshape((1,100))
                samples = np.append(samples,sample,0)

responses = np.array(responses,np.float32)
responses = responses.reshape((responses.size,1))
print ("training complete")
print(samples)
print(responses)
#
np.savetxt('generalsamples.data',samples)
np.savetxt('generalresponses.data',responses)

图片识别代码：

import cv2
import numpy as np

#######   training part    ###############
samples = np.loadtxt('generalsamples.data',np.float32)
responses = np.loadtxt('generalresponses.data',np.float32)
responses = responses.reshape((responses.size,1))

# model = cv2.KNearest()
model = cv2.ml.KNearest_create()
# model.train(samples,responses)
model.train(samples, cv2.ml.ROW_SAMPLE, responses)

############################# testing part  #########################

im = cv2.imread('test7.png')
out = np.zeros(im.shape,np.uint8)
gray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)

contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)

list = []

for cnt in contours:
    if cv2.contourArea(cnt)>5:
        [x,y,w,h] = cv2.boundingRect(cnt)
        print([x,y,w,h])
        if  (h>13 and h < 16) or (h>3 and h < 7 and w > 3 ):
            cv2.rectangle(im,(x,y),(x+w,y+h),(0,255,0),2)
            roi = thresh[y:y+h,x:x+w]
            roismall = cv2.resize(roi,(10,10))
            roismall = roismall.reshape((1,100))
            roismall = np.float32(roismall)
            retval, results, neigh_resp, dists = model.findNearest(roismall, k = 1)
            string = str(int((results[0][0])))
            print(type(string))
            print(chr(int(string)))

            list.append([x,chr(int(string))])
            cv2.putText(out,chr(int(string)),(x,y+h),0,1,(0,255,0))

num = np.asarray(list)

data = num[num[:,0].argsort()] #通过x轴排序
# data = data[:,data[2].argsort()]
print(data)
data = data[:,1]
list = data.tolist()
string = ''.join(list)
print(string) #识别后的字符

cv2.imshow('im',im)
cv2.imshow('out',out)
cv2.waitKey(0)