My question is about building a simple program that detect digits inside images, i did some researches and found this topic Simple OCR digits on stack and i found it very educational, so i wanted to us it for my own need.
My training data image is like:
The code i used to build the dataset is: (i did some modifications to Abid Rahman's code so it can hundle my case)
import sys
import numpy as np
import cv2
im = cv2.imread('data_set_trans.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(48,58)]
for cnt in contours:
if cv2.contourArea(cnt)>20:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>=10:
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)
print "Begin wait"
key = cv2.waitKey(1)
key = raw_input('What is the number ?') #cv2.waitKey didnt work for me so i add this line
if key == -1: # (-1 to quit)
sys.exit()
else:
responses.append(int(key))
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)
I used the same training data image as testing part, in order to get the best results accuracy and see if i am on the right way:
import cv2
import numpy as np
import collections
####### 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.train(samples,responses)
############################# testing part #########################
im = cv2.imread('one_white_1.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)
for cnt in contours:
if cv2.contourArea(cnt)>20:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>=10:
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.find_nearest(roismall, k = 1)
string = str(int((results[0][0])))
cv2.putText(out,string,(x,y+h),1,1,(0,255,0))
cv2.imshow('im',im)
cv2.imshow('out',out)
#cv2.waitKey(0)
raw_input('Tape to exit')
The result was as like that:
As you can see it's completely wrong.
I don't know what i'm missing or if it my case is more particular and can't be handled by this digit OCR system ????
If someone could help me by any idea
I notice that i am using python 2.7 open-cv 2.4.11 numpy 1.9 and mac os 10.10.4
Thanks
