问题描述
我对Python和OpenCV很陌生。我有一些屏幕截图（附有一个示例供参考），我想为其识别文本的前色和背景色。我将使用这种颜色来计算文本的颜色对比度。使用PyTesseract，我能够识别单词和文本的绘制边界矩形。谁能指导我如何检测文本的前色和底色？下面是我到目前为止所做的代码。
import cv2
import PyTesseract
import numpy as np
PyTesseract.PyTesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
imgOriginal = cv2.imread('3.png')
gray = cv2.cvtColor(imgOriginal,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray,255,cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
img = cv2.GaussianBlur(thresh,(3,3),0)
cv2.imshow("Filtered",img)
### Detecting words
hImg,wImg,_ = imgOriginal.shape
Boxes = PyTesseract.image_to_data(img,config='--psm 6') #list
for i,b in enumerate(Boxes.splitlines()):
if i!=0: #no need to extract the first row since it is the header
b=b.split()
if len(b)==12: #12th item is the word
x,y,w,h = int(b[6]),int(b[7]),int(b[8]),int(b[9])
cv2.rectangle(imgOriginal,(x,y),(x+w,y+h),(0,255),1)
cv2.imshow('Image',imgOriginal)
k = cv2.waitKey(0)
if k==ord('q'):
cv2.destroyAllWindows()
解决方法
如果您仍在寻找答案。
imgOriginal = cv2.imread('windows.png')
image = imgOriginal.copy()
image_1 = imgOriginal.copy()
gray = cv2.cvtColor(imgOriginal,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray,255,cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Removing the horizantal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(7,1))
detected_lines = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,horizontal_kernel,iterations=2)
cnts = cv2.findContours(detected_lines,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(image,[c],-1,(255,255),2)
# Removing the vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(1,7))
detected_lines = cv2.morphologyEx(thresh,vertical_kernel,2)
gray_no_lines = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
otsu = cv2.threshold(gray_no_lines,cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
### Detecting words
boxes = pytesseract.image_to_data(otsu,config='--psm 6') #list
xs = []
ys = []
ws = []
hs = []
words = []
for i,b in enumerate(boxes.splitlines()):
if i!=0: #no need to extract the first row since it is the header
b=b.split()
if len(b)==12: #12th item is the word
if b[11] != -1:
x,y,w,h = int(b[6]),int(b[7]),int(b[8]),int(b[9])
cv2.rectangle(image,(x,y),(x+w,y+h),(0,1)
xs.append(x)
ys.append(y)
ws.append(w)
hs.append(h)
words.append(b[11])
text_colors = []
bg_colors = []
for j in range(len(words)):
x,h = xs[j],ys[j],ws[j],hs[j]
roi_otsu = otsu[y:y+h,x:x+w]
roi_image = image_1[y:y+h,x:x+w]
black_coords = np.column_stack(np.where(roi_otsu == 0))
white_coords = np.column_stack(np.where(roi_otsu == 255))
blues_text = []
greens_text = []
reds_text = []
blues_bg = []
greens_bg = []
reds_bg = []
for i in range(len(black_coords)):
blue_t = roi_image.item(black_coords[i][0],black_coords[i][1],0)
green_t = roi_image.item(black_coords[i][0],1)
red_t = roi_image.item(black_coords[i][0],2)
blues_text.append(blue_t)
greens_text.append(green_t)
reds_text.append(red_t)
color_t = (int(np.mean(blues_text)),int(np.mean(greens_text)),int(np.mean(reds_text)))
for i in range(len(white_coords)):
blue_bg = roi_image.item(white_coords[i][0],white_coords[i][1],0)
green_bg = roi_image.item(white_coords[i][0],1)
red_bg = roi_image.item(white_coords[i][0],2)
blues_bg.append(blue_bg)
greens_bg.append(green_bg)
reds_bg.append(red_bg)
color_bg = (int(np.mean(blues_bg)),int(np.mean(greens_bg)),int(np.mean(reds_bg)))
text_colors.append(color_t)
bg_colors.append(color_bg)
print(text_colors)
print(bg_colors)
# print(len(text_colors),len(bg_colors))
为了更好的效果，我删除了水平线和垂直线。对图像进行二值化并收集每个文本区域的坐标。对感兴趣的区域进行切片，并收集由文本和背景组成的像素像素（来自二值化后的切片区域）。从彩色切片区域收集了这些坐标的像素值。取每种颜色的平均值，然后将颜色附加到最终列表中。
希望这可以解决您的问题。如果我错了，请纠正我。