使用Tesseract OCR和python进行数字识别

Question

我使用Tesseract和python来读取数字（来自能量计）。 一切都很好，除了数字“1”。 Tesseract无法读取“1”数字。

这是我发给tesseract的图片：

tesseract读取“0000027”。

我怎么能告诉Tesseract垂直杆是“1”？

这是我的tesseract初始化：

import tesseract

TESSERACT_LIBRARY_PATH = "C:\\Program Files (x86)\\Tesseract-OCR"
LANGUAGE = "eng"
CHARACTERS = "0123456789"
FALSE = "0"
TRUE = "1"

def init_ocr():
    """ 
    .. py:function:: init_ocr()

        Utilize the Tesseract-OCR library to create an tesseract_ocr that 
        predicts the numbers to be read off of the meter. 

        :return: tesseract_ocr Tesseracts OCR API.
        :rtype: Class
    """
    # Initialize the tesseract_ocr with the english language package.
    tesseract_ocr = tesseract.TessBaseAPI()
    tesseract_ocr.Init(TESSERACT_LIBRARY_PATH, LANGUAGE, 
                       tesseract.OEM_DEFAULT)


    # Limit the characters being seached for to numerics.
    tesseract_ocr.SetVariable("tessedit_char_whitelist", CHARACTERS)

    # Set the tesseract_ocr to predict for only one character.
    tesseract_ocr.SetPageSegMode(tesseract.PSM_AUTO)

    # Tesseract's Directed Acyclic Graph.
    # Not necessary for number recognition.
    tesseract_ocr.SetVariable("load_system_dawg", FALSE)
    tesseract_ocr.SetVariable("load_freq_dawg", FALSE)
    tesseract_ocr.SetVariable("load_number_dawg", TRUE)

    tesseract_ocr.SetVariable("classify_enable_learning", FALSE)
    tesseract_ocr.SetVariable("classify_enable_adaptive_matcher", FALSE)

    return tesseract_ocr

Answer 1

稍微不相关的答案，虽然可能符合您的原始目标。

我和tesseract有类似的问题，我也有非常严格的性能要求。 我在SO上找到了这个简单的解决方案，并使用OpenCV制作了简单的识别器。

它归结为在您拥有的非常清晰的图像上找到边界矩形（来自边缘），然后尝试匹配找到的对象与模板。 我相信您的案例中的解决方案既简单又精确，但需要的代码比现在多一些。

我会关注这个问题，因为有了tesseract的工作解决方案会很好。

我的时间有限，但似乎是一个有效的解决方案：

import os
import cv2
import numpy
KNN_SQUARE_SIDE = 50  # Square 50 x 50 px.


def resize(cv_image, factor):
    new_size = tuple(map(lambda x: x * factor, cv_image.shape[::-1]))
    return cv2.resize(cv_image, new_size)


def crop(cv_image, box):
    x0, y0, x1, y1 = box
    return cv_image[y0:y1, x0:x1]


def draw_box(cv_image, box):
    x0, y0, x1, y1 = box
    cv2.rectangle(cv_image, (x0, y0), (x1, y1), (0, 0, 255), 2)


def draw_boxes_and_show(cv_image, boxes, title='N'):
    temp_image = cv2.cvtColor(cv_image, cv2.COLOR_GRAY2RGB)
    for box in boxes:
        draw_box(temp_image, box)
    cv2.imshow(title, temp_image)
    cv2.waitKey(0)


class BaseKnnMatcher(object):
    distance_threshold = 0

    def __init__(self, source_dir):
        self.model, self.label_map = self.get_model_and_label_map(source_dir)

    @staticmethod
    def get_model_and_label_map(source_dir):
        responses = []
        label_map = []
        samples = numpy.empty((0, KNN_SQUARE_SIDE * KNN_SQUARE_SIDE), numpy.float32)
        for label_idx, filename in enumerate(os.listdir(source_dir)):

            label = filename[:filename.index('.png')]
            label_map.append(label)
            responses.append(label_idx)

            image = cv2.imread(os.path.join(source_dir, filename), 0)

            suit_image_standard_size = cv2.resize(image, (KNN_SQUARE_SIDE, KNN_SQUARE_SIDE))
            sample = suit_image_standard_size.reshape((1, KNN_SQUARE_SIDE * KNN_SQUARE_SIDE))
            samples = numpy.append(samples, sample, 0)

        responses = numpy.array(responses, numpy.float32)
        responses = responses.reshape((responses.size, 1))
        model = cv2.KNearest()
        model.train(samples, responses)

        return model, label_map

    def predict(self, image):
        image_standard_size = cv2.resize(image, (KNN_SQUARE_SIDE, KNN_SQUARE_SIDE))
        image_standard_size = numpy.float32(image_standard_size.reshape((1, KNN_SQUARE_SIDE * KNN_SQUARE_SIDE)))
        closest_class, results, neigh_resp, distance = self.model.find_nearest(image_standard_size, k=1)

        if distance[0][0] > self.distance_threshold:
            return None

        return self.label_map[int(closest_class)]


class DigitKnnMatcher(BaseKnnMatcher):
    distance_threshold = 10 ** 10


class MeterValueReader(object):
    def __init__(self):
        self.digit_knn_matcher = DigitKnnMatcher(source_dir='templates')

    @classmethod
    def get_symbol_boxes(cls, cv_image):
        ret, thresh = cv2.threshold(cv_image.copy(), 150, 255, cv2.THRESH_BINARY)
        contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

        symbol_boxes = []
        for contour in contours:
            x, y, width, height = cv2.boundingRect(contour)

            # You can test here for box size, though not required in your example:
            # if cls.is_size_of_digit(width, height):
            #     symbol_boxes.append((x, y, x+width, y+height))

            symbol_boxes.append((x, y, x+width, y+height))
        return symbol_boxes

    def get_value(self, meter_cv2_image):
        symbol_boxes = self.get_symbol_boxes(meter_cv2_image)
        symbol_boxes.sort()  # x is first in tuple
        symbols = []
        for box in symbol_boxes:
            symbol = self.digit_knn_matcher.predict(crop(meter_cv2_image, box))
            symbols.append(symbol)
        return symbols


if __name__ == '__main__':
    # If you want to see how boxes detection works, uncomment these:
    # img_bw = cv2.imread(os.path.join('original.png'), 0)
    # boxes = MeterValueReader.get_symbol_boxes(img_bw)
    # draw_boxes_and_show(img_bw, boxes)

    # Uncomment to generate templates from image
    # import random
    # TEMPLATE_DIR = 'templates'
    # img_bw = cv2.imread(os.path.join('original.png'), 0)
    # boxes = MeterValueReader.get_symbol_boxes(img_bw)
    # for box in boxes:
    #     # You need to label templates manually after extraction
    #     cv2.imwrite(os.path.join(TEMPLATE_DIR, '%s.png' % random.randint(0, 1000)), crop(img_bw, box))

    img_bw = cv2.imread(os.path.join('original.png'), 0)
    vr = MeterValueReader()
    print vr.get_value(img_bw)