來自“ OpenCV-Python中的簡單數字識別OCR”的腳本錯誤

Question

我已經更新了腳本，但是無法解決一個錯誤。 這是我的腳本版本：

import sys
import numpy as np
import cv2

im = cv2.imread('test001.png')
res = cv2.resize(im,None,fx=2, fy=2, interpolation = cv2.INTER_CUBIC)
im3 = res.copy()

gray = cv2.cvtColor(res,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(48,58)]

for cnt in contours:
    if (cv2.contourArea(cnt)>50) and (cv2.contourArea(cnt)<900):

        [x,y,w,h] = cv2.boundingRect(cnt)
        if  ((h>0) and (h<35)) and ((w>0) and (w<35)):
            cv2.rectangle(res,(x,y),(x+w,y+h),(0,0,255),1)
            roi = thresh[y:y+h,x:x+w]
            roismall = cv2.resize(roi,(30,30))
            cv2.imshow('norm',res)
            key = cv2.waitKey(0) % 256
            print ("+")
            print (key)
            print ("+")

            if key == 27:  # (escape to quit)
                sys.exit()
            elif key in keys:
                print ("-")
                print (key)
                print ("-")
                responses.append(int(key))
                print (len(roismall))
                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")

np.savetxt('generalsamples.data',samples)
np.savetxt('generalresponses.data',responses)

當我運行代碼時，出現此錯誤：

追溯（最近一次調用）：文件“ file001.py”，第45行，示例中= roismall.reshape（（1,100））ValueError：新數組的總大小必須保持不變

最后一個打印“ print（len（roismall））”的值為30。

問候托馬斯

Answer 1

此錯誤是自制的：

sample = roismall.reshape((1,100))

對應於此行：

roismall = cv2.resize(roi,(30,30))

30 x 30 = 900是正確的值或10,10 =100。我將其更改回：

roismall = cv2.resize(roi,(10,10))

下面是完成腳本：

import sys

import numpy as np
import cv2

im = cv2.imread('test001.png')
res = cv2.resize(im,None,fx=2, fy=2, interpolation = cv2.INTER_CUBIC)
im3 = res.copy()

gray = cv2.cvtColor(res,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))
sample =  np.empty((0,100))
responses = []
keys = [i for i in range(48,58)]

for cnt in contours:
    if (cv2.contourArea(cnt)>10) and (cv2.contourArea(cnt)<900):

        [x,y,w,h] = cv2.boundingRect(cnt)
        if  ((h>15) and (h<30)) and ((w>8) and (w<30)):
            cv2.rectangle(res,(x,y),(x+w,y+h),(0,0,255),1)
            roi = thresh[y:y+h,x:x+w]
            roismall = cv2.resize(roi,(10,10))
            cv2.imshow('roi',roismall)
            cv2.imshow('norm',res)
            key = cv2.waitKey(0) % 256
            if key == 27:  # (escape to quit)
                sys.exit()
            elif key in keys:
                responses.append(int(key))
                sample = roismall.reshape((1,100))
                samples = np.append(samples,sample)

responses = np.array(responses,np.float32)
responses = responses.reshape((responses.size,1))
print ("training complete")

np.savetxt('generalsamples.data',samples)
np.savetxt('generalresponses.data',responses)

問候托馬斯