代码之家 › 专栏 › 技术社区 › Yohan D

改进图片以检测区域内的字符

ocr computer-vision opencv python

Yohan D · 技术社区 · 6 年前

旋转图像使蓝色矩形水平[需要帮助]
根据蓝色矩形裁剪图像[需要帮助]
应用阈值过滤器和高斯模糊

使用Tesseract检测字符

img = Image.open('grid.jpg')
image = np.array(img.convert("RGB"))[:, :, ::-1].copy()


# Need to rotate the image here and fill the blanks
# Need to crop the image here

# Gray  the image
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Otsu's thresholding
ret3, th3 = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

# Gaussian Blur
blur = cv2.GaussianBlur(th3, (5, 5), 0)

# Save the image
cv2.imwrite("preproccessed.jpg", blur)

# Apply the OCR
pytesseract.pytesseract.tesseract_cmd = r'C:/Program Files (x86)/Tesseract-OCR/tesseract.exe'
tessdata_dir_config = r'--tessdata-dir "C:/Program Files (x86)/Tesseract-OCR/tessdata" --psm 6'

preprocessed = Image.open('preproccessed.jpg')
boxes = pytesseract.image_to_data(preprocessed, config=tessdata_dir_config)

OCR问题:

有时,Tesseract会将一行中的字符识别为一个单词(gcvdrteuqcebursidec),有时也会识别为单个字母。我希望它永远是一个词。
右下角的小金字塔被认为是一个字符

欢迎提出任何其他提高认可度的建议

4 回复 | 直到 6 年前

Mark Setchell 6 年前

这里有一个方法来继续。。。

转换为HSV,然后从每个角开始,向图片的中间方向前进,寻找距离每个角最近的像素,该像素有些饱和,色调与周围的蓝色矩形相匹配。这将给你4个红色标记:

现在使用透视变换将每个点移动到角点,使图像直线化。我使用了ImageMagick,但是您应该可以看到,我将坐标(210,51)处的左上角红点转换为新图像左上角的(0,0)。同样地,右上角的红点(1754,19)被移到(2064,0)。终端中的ImageMagick命令是:

convert wordsearch.jpg \
  -distort perspective '210,51,0,0 1754,19,2064,0 238,1137,0,1161 1776,1107,2064,1161' result.jpg

下一个问题是光线不均匀-也就是说左下角比图像的其余部分暗。为了抵消这一点,我克隆图像并对其进行模糊处理以去除高频(只是框模糊,或者框平均值很好),因此它现在代表缓慢变化的照明。然后我从中减去图像,这样我就能有效地去除背景变化,只留下高频的东西——比如你的信。然后我将结果标准化,使白色和黑色分别为白色和黑色,阈值为50%。

convert result.jpg -colorspace gray \( +clone -blur 50x50 \) \
   -compose difference -composite  -negate -normalize -threshold 50% final.jpg

Kinght é 6 年前

以下是我识别字符的步骤:

(1) detect the blue in hsv space, approx the inner blur contour and sort the corner points:
(2) find persprctive transform matrix and do perspective transform
(3) threshold it (and find characters)
(4) use `mnist` algorithms to recognize the chars

step (1) find the corners of the blur rect

Choosing the correct upper and lower HSV boundaries for color detection with`cv::inRange` (OpenCV)

step (2) crop

step (3) threshold (and find the chars)

step (4) on working...

jcupitt 6 年前

pyvips .

如果图像只是旋转的(即很少或没有透视),你可以用FFT来找到旋转角度。漂亮、规则的字符网格将在变换上生成一组清晰的线条。它应该非常坚固。这是在整个图像上执行FFT,但是如果您想要更高的速度,可以先将其缩小一点。

import sys
import pyvips

image = pyvips.Image.new_from_file(sys.argv[1])

# to monochrome, take the fft, wrap the origin to the centre, get magnitude
fft = image.colourspace('b-w').fwfft().wrap().abs()

def to_rectangular(image):
    xy = pyvips.Image.xyz(image.width, image.height)
    xy *= [1, 360.0 / image.height]
    index = xy.rect()
    scale = min(image.width, image.height) / float(image.width)
    index *= scale / 2.0
    index += [image.width / 2.0, image.height / 2.0]
    return image.mapim(index)

# sum of columns, sum of rows
cols, rows = to_rectangular(fft).project()

制作:

投影为:

然后寻找峰值并旋转:

# blur the rows projection a bit, then get the maxpos
v, x, y = rows.gaussblur(10).maxpos()

# and turn to an angle in degrees we should counter-rotate by
angle = 270 - 360 * y / rows.height

image = image.rotate(angle)

cols, rows = image.project() 

h = (cols[2] - cols[1]) > 10000
v = (rows[2] - rows[1]) > 10000

# search in from the edges for the first non-zero value
cols, rows = h.profile()
left = rows.avg()

cols, rows = h.fliphor().profile()
right = h.width - rows.avg()
width = right - left

cols, rows = v.profile()
top = cols.avg()

cols, rows = v.flipver().profile()
bottom = v.height - cols.avg()
height = bottom - top

# move the crop in by a margin
margin = 10
left += margin
top += margin
width -= 2 * margin
height -= 2 * margin

# and crop!
image = image.crop(left, top, width, height)

使:

image = image.colourspace('b-w').gaussblur(70) - image

使:

ARR 6 年前

python - opencv morphologyEx remove specific color