Tesseract-OCR本文结构与旋转分析，识别字符白名单配置

0：3.x以前的识别引擎
1：神经网络LSTM的识别引擎
2：混合模式，传统+LSTM
3：默认，那种支持就用那种

'left', 'top', 'width', 'height' 表示位置信息
'text' 表示每个的外接矩形左上角与右下角坐标
'conf' 表示置信度，值在0~100之间，小于0的应该自动排除

0   角度与语言检测，不识别不分析文档结构
1   角度 + PSM模式

0    Orientation and script detection (OSD) only.
1    Automatic page segmentation with OSD.
2    Automatic page segmentation, but no OSD, or OCR.
3    Fully automatic page segmentation, but no OSD. (Default)
4    Assume a single column of text of variable sizes.
5    Assume a single uniform block of vertically aligned text.
6    Assume a single uniform block of text.
7    Treat the image as a single text line.
8    Treat the image as a single word.
9    Treat the image as a single word in a circle.
10    Treat the image as a single character.
11    Sparse text. Find as much text as possible in no particular order.
12    Sparse text with OSD.
13    Raw line. Treat the image as a single text line, bypassing hacks that are Tesseract-specific.

def image_to_data(
    image,
    lang=None,
    config='',
    nice=0,
    output_type=Output.STRING,
    timeout=0,
    pandas_config=None,
)

def image_to_osd(
    image,
    lang='osd',
    config='',
    nice=0,
    output_type=Output.STRING,
    timeout=0,
):

image = cv.imread("D:/images/text_xt.png")
h, w, c = image.shape

# 文档结构分析
config = ('-l chi_sim --oem 1 --psm 6')
dict = tess.image_to_data(image, config=config, output_type=tess.Output.DICT)
print(dict.keys())
print(dict['conf'])
n_boxes = len(dict['text'])

# 全部文档结构
text_img = np.copy(image)
for i in range(n_boxes):
    (x, y, w, h) = (dict['left'][i], dict['top'][i], dict['width'][i], dict['height'][i])
    cv.rectangle(text_img, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv.imwrite('D:/layout-text1.png', text_img)

# 根据conf>0过滤之后
for i in range(n_boxes):
    if int(dict['conf'][i]) > 0:
        (x, y, w, h) = (dict['left'][i], dict['top'][i], dict['width'][i], dict['height'][i])
        cv.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv.imwrite('D:/layout-text2.png', image)

# 检测倾斜角度
image = cv.imread("D:/images/text_90.png")
cv.imshow("text_90", image)
osd = tess.image_to_osd(image)
print(osd)
osd_array = osd.split("\n")
angle = int(osd_array[2].split(":")[1])
conf = float(osd_array[3].split(":")[1])
print("angle: ", angle)
print("conf: ", conf)
dst = cv.rotate(image, cv.ROTATE_90_CLOCKWISE)
cv.imshow("text_90_rotate", dst)
cv.imwrite('D:/layout-text3.png', dst)

# 只检测数字
custom_config = r'--oem 1 --psm 6 outputbase digits'
ocr_result = tess.image_to_string(dst, config=custom_config)
print(ocr_result)

# 采用白名单方式只检测数字
custom_config = r'-c tessedit_char_whitelist=0123456789 --psm 6'
ocr_result = tess.image_to_string(dst, config=custom_config)
print("白名单方式数字检测\n",ocr_result)

# 检测中文
ocr_result = tess.image_to_string(dst, lang="chi_sim")
print("\n中文检测与输出:\n", ocr_result.replace("\f", "").split("\n"))

# 检测中文情况下，只输出数字
ocr_result = tess.image_to_string(dst, lang="chi_sim", config=custom_config)
print("\n中文检测+数字输出:\n",ocr_result.replace("\f", "").split("\n"))

cv.waitKey(0)
cv.destroyAllWindows()