python数字识别-训练模型

python数字识别-训练模型

简介

数字识别是计算视觉中一个重要的任务，可以用来完成老设备加装摄像头完成数据采集的工作。本文来介绍下用opencv实现数字识别训练。

代码

import sys
import numpy as np
import cv2

im = cv2.imread('train.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_EXTERNAL,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>25 and h < 29):#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)

执行代码，在训练的图片上会圈出电脑识别到的数字，然后在键盘中认为输入对应数字给电脑训练，直到识别结束，会输出两个文件generalsamples.data，generalresponses.data，到这里就完成了训练的工作。下一篇介绍使用的代码