39.ocr.py

#Our goal is to build an application which can read the handwritten digits. For this we need some train_data and
#test_data. OpenCV comes with an image digits.png (in the folder opencv/samples/python2/data/) which
#has 5000 handwritten digits (500 for each digit). Each digit is a 20x20 image. So our first step is to split this image
#into 5000 different digits. For each digit, we flatten it into a single row with 400 pixels. That is our feature set, ie
#intensity values of all pixels. It is the simplest feature set we can create.
#use first 250 as train set and next 250 as test set



import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('digits.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Now we split the image to 5000 cells, each 20x20 size
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]
# Make it into a Numpy array. It size will be (50,100,20,20)
x = np.array(cells)
# Now we prepare train_data and test_data.
train = x[:,:50].reshape(-1,400).astype(np.float32) # Size = (2500,400)
test = x[:,50:100].reshape(-1,400).astype(np.float32) # Size = (2500,400)
# Create labels for train and test data
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
test_labels = train_labels.copy()
# Initiate kNN, train the data, then test it with test data for k=1
knn = cv2.KNearest()
knn.train(train,train_labels)
ret,result,neighbours,dist = knn.find_nearest(test,k=5)
# Now we check the accuracy of classification
# For that, compare the result with test_labels and check which are wrong
matches = result==test_labels
correct = np.count_nonzero(matches)
accuracy = correct*100.0/result.size
print accuracy


#So instead of finding this training data everytime I start
#application, I better save it, so that next time, I directly read this data from a file and start classification. You can do it
#with the help of some Numpy functions like np.savetxt, np.savez, np.load etc.

# save the data
np.savez('knn_data.npz',train=train, train_labels=train_labels)
# Now load the data
with np.load('knn_data.npz') as data:
	print data.files
	train = data['train']
	train_labels = data['train_labels']


#OCR of English Alphabets

#There are 20000 samples available, so we take first 10000 data as training samples and remaining 10000 as test
#samples. We should change the alphabets to ascii characters because we can’t work with alphabets directly.


import cv2
import numpy as np
import matplotlib.pyplot as plt
# Load the data, converters convert the letter to a number
data= np.loadtxt('letter-recognition.data', dtype= 'float32', delimiter = ',',converters= {0: lambda ch: ord(ch)-ord('A')})
# split the data to two, 10000 each for train and test
train, test = np.vsplit(data,2)
# split trainData and testData to features and responses
responses, trainData = np.hsplit(train,[1])
labels, testData = np.hsplit(test,[1])
# Initiate the kNN, classify, measure accuracy.
knn = cv2.KNearest()
knn.train(trainData, responses)
ret, result, neighbours, dist = knn.find_nearest(testData, k=5)
correct = np.count_nonzero(result == labels)
accuracy = correct*100.0/10000
print accuracy