Python+OpenCV：基于KNN手写数据OCR（OCR of Hand-written Data using kNN）

待我称王封你为后i 2022-12-25 01:55 124阅读 0赞

## Python+OpenCV：基于KNN手写数据OCR（OCR of Hand-written Data using kNN） ##

### OCR of Hand-written Digits ###

####################################################################################################
    # 基于KNN手写数据OCR(OCR of Hand-written Data using kNN)
    def lmc_cv_knn_ocr():
        """
            函数功能: 基于KNN手写数据OCR(OCR of Hand-written Data using kNN).
        """
    
        # 读取图像
        image = lmc_cv.imread('D:/99-Research/TestData/image/digits.png')
        gray_image = lmc_cv.cvtColor(image, lmc_cv.COLOR_BGR2GRAY)
    
        # Now we split the image to 2500 cells, each 20x20 size
        cells = [np.hsplit(row, 50) for row in np.vsplit(gray_image, 50)]
    
        # Make it into a Numpy array: its size will be (50,50,20,20)
        x = np.array(cells)
    
        # Now we prepare the training data and test data
        train = x[:, :25].reshape(-1, 400).astype(np.float32)  # Size = (1250,400)
        test = x[:, 25:50].reshape(-1, 400).astype(np.float32)  # Size = (1250,400)
    
        # Create labels for train and test data
        k = np.arange(10)
        train_labels = np.repeat(k, 125)[:, np.newaxis]
        test_labels = train_labels.copy()
    
        # Initiate kNN, train it on the training data, then test it with the test data with k=1
        knn = lmc_cv.ml.KNearest_create()
        knn.train(train, lmc_cv.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:  {}\n".format(accuracy))
    
        # Instead of finding this training data every time I start the application, I better save it.
        # so that the next time, I can directly read this data from a file and start classification.
        # 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:  {}\n".format(data.files))
            train = data['train']
            train_labels = data['train_labels']

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWJpbmc4NjA5_size_16_color_FFFFFF_t_70][]

【结果】
    accuracy:  88.72
    data.files:  ['train', 'train_labels']

### OCR of the English Alphabet ###

####################################################################################################
    # 基于KNN英文字母OCR(OCR of English Alphabet Data using kNN)
    def lmc_cv_knn_ocr_english_alphabet():
        """
            函数功能: 基于KNN英文字母OCR(OCR of English Alphabet Data using kNN).
        """
    
        # Load the data and convert the letters to numbers
        data = np.loadtxt('D:/99-Research/TestData/image/letter-recognition.data', dtype='float32', delimiter=',',
                          converters={0: lambda ch: ord(ch) - ord('A')})
    
        # Split the dataset in two, with 10000 samples each for training and test sets
        train, test = np.vsplit(data, 2)
    
        # Split trainData and testData into features and responses
        responses, train_data = np.hsplit(train, [1])
        labels, test_data = np.hsplit(test, [1])
    
        # Initiate the kNN, classify, measure accuracy
        knn = lmc_cv.ml.KNearest_create()
        knn.train(train_data, lmc_cv.ml.ROW_SAMPLE, responses)
        ret, result, neighbours, dist = knn.findNearest(test_data, k=5)
        correct = np.count_nonzero(result == labels)
        accuracy = correct * 100.0 / 10000
        print("accuracy:  {}\n".format(accuracy))

【结果】
    accuracy:  93.06

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWJpbmc4NjA5_size_16_color_FFFFFF_t_70]: /images/20221120/c6dbe73f229b4fd48970eccf19adb335.png