亚洲人一区,亚洲女人天堂成人av在线,天天草草草

OCR of Hand-written Digits

我們的目標(biāo)是構(gòu)建一個(gè)可以讀取手寫數(shù)字的應(yīng)用程序, 為此，我們需要一些train_data和test_data. OpenCV附帶一個(gè)images digits.png（在文件夾opencv\sources\samples\data\中），它有5000個(gè)手寫數(shù)字（每個(gè)數(shù)字500個(gè),每個(gè)數(shù)字是20x20圖像）.所以首先要將圖片切割成5000個(gè)不同圖片,每個(gè)數(shù)字變成一個(gè)單行400像素.前面的250個(gè)數(shù)字作為訓(xùn)練數(shù)據(jù)，后250個(gè)作為測(cè)試數(shù)據(jù).

									import numpy as np

									import cv2

									import matplotlib.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.ml.KNearest_create()

									knn.train(train, cv2.ml.ROW_SAMPLE, train_labels)

									ret,result,neighbours,dist = knn.findNearest(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 )

輸出：91.76

進(jìn)一步提高準(zhǔn)確率的方法是增加訓(xùn)練數(shù)據(jù),特別是錯(cuò)誤的數(shù)據(jù).每次訓(xùn)練時(shí)最好是保存訓(xùn)練數(shù)據(jù),以便下次使用.

									# 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

在opencv / samples / data /文件夾中附帶一個(gè)數(shù)據(jù)文件letter-recognition.data.在每一行中,第一列是一個(gè)字母表,它是我們的標(biāo)簽. 接下來的16個(gè)數(shù)字是它的不同特征.

									import numpy as np

									import cv2

									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.ml.KNearest_create()

									knn.train(trainData, cv2.ml.ROW_SAMPLE, responses)

									ret, result, neighbours, dist = knn.findNearest(testData, k=5)

									correct = np.count_nonzero(result == labels)

									accuracy = correct*100.0/10000

									print( accuracy )