我有一张包含文本（数字和字母）的图像。我想获取图像中所有文本和数字的位置，并且还想提取所有的文本内容。
如何获取图像中所有文本（数字和字母）的坐标以及文本内容？例如10B、44、16、38、22B等
回答：
这里是一种可能的方法，使用形态学操作来过滤掉非文本轮廓。思路是这样的：
-
移除水平和垂直线条。 使用水平和垂直核通过
cv2.getStructuringElement()创建，然后使用cv2.drawContours()移除线条 -
移除对角线、圆形物体和曲线轮廓。 使用轮廓面积
cv2.contourArea()和轮廓近似cv2.approxPolyDP()过滤以隔离非文本轮廓 -
提取文本ROI并进行OCR识别。 查找轮廓并过滤ROI，然后使用Pytesseract进行OCR识别。
移除的水平线以绿色高亮显示
移除的垂直线
移除的各种非文本轮廓（对角线、圆形物体和曲线）
检测到的文本区域
import cv2import numpy as npimport pytesseractpytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"# Load image, grayscale, Otsu's thresholdimage = cv2.imread('1.jpg')gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]clean = thresh.copy()# Remove horizontal lineshorizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,1))detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)cnts = cnts[0] if len(cnts) == 2 else cnts[1]for c in cnts: cv2.drawContours(clean, [c], -1, 0, 3)# Remove vertical linesvertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,30))detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)cnts = cnts[0] if len(cnts) == 2 else cnts[1]for c in cnts: cv2.drawContours(clean, [c], -1, 0, 3)cnts = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)cnts = cnts[0] if len(cnts) == 2 else cnts[1]for c in cnts: # Remove diagonal lines area = cv2.contourArea(c) if area < 100: cv2.drawContours(clean, [c], -1, 0, 3) # Remove circle objects elif area > 1000: cv2.drawContours(clean, [c], -1, 0, -1) # Remove curve stuff peri = cv2.arcLength(c, True) approx = cv2.approxPolyDP(c, 0.02 * peri, True) x,y,w,h = cv2.boundingRect(c) if len(approx) == 4: cv2.rectangle(clean, (x, y), (x + w, y + h), 0, -1)open_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,2))opening = cv2.morphologyEx(clean, cv2.MORPH_OPEN, open_kernel, iterations=2)close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,2))close = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, close_kernel, iterations=4)cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)cnts = cnts[0] if len(cnts) == 2 else cnts[1]for c in cnts: x,y,w,h = cv2.boundingRect(c) area = cv2.contourArea(c) if area > 500: ROI = image[y:y+h, x:x+w] ROI = cv2.GaussianBlur(ROI, (3,3), 0) data = pytesseract.image_to_string(ROI, lang='eng',config='--psm 6') if data.isalnum(): cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2) print(data)cv2.imwrite('image.png', image)cv2.imwrite('clean.png', clean)cv2.imwrite('close.png', close)cv2.imwrite('opening.png', opening)cv2.waitKey()