本文共 3318 字,大约阅读时间需要 11 分钟。
Fu Xianjun. All Rights Reserved
OpenCV是一个用于图像处理、分析、机器视觉方面的开源函数库.
代码如下:
import cv2import numpy as np
代码如下:
1.预处理、轮廓检测
# 正确答案ANSWER_KEY = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}def cv_show(name,img): cv2.imshow(name, img) cv2.waitKey(0) cv2.destroyAllWindows() # 读取输入image = cv2.imread("test_01.png")contours_img = image.copy()gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)blurred = cv2.GaussianBlur(gray, (5, 5), 0)cv_show('blurred',blurred)edged = cv2.Canny(blurred, 75, 200)cv_show('edged',edged)# 轮廓检测cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,\ cv2.CHAIN_APPROX_SIMPLE)[0]cv2.drawContours(contours_img,cnts,-1,(0,0,255),3) cv_show('contours_img',contours_img)
2.轮廓排序,透视变换
def order_points(pts): # 一共4个坐标点 rect = np.zeros((4, 2), dtype = "float32") # 按顺序找到对应坐标0123分别是 左上,右上,右下,左下 # 计算左上,右下 s = pts.sum(axis = 1) rect[0] = pts[np.argmin(s)] rect[2] = pts[np.argmax(s)] # 计算右上和左下 diff = np.diff(pts, axis = 1) rect[1] = pts[np.argmin(diff)] rect[3] = pts[np.argmax(diff)] return rectdef four_point_transform(image, pts): # 获取输入坐标点 rect = order_points(pts) (tl, tr, br, bl) = rect # 计算输入的w和h值 widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2)) widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2)) maxWidth = max(int(widthA), int(widthB)) heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2)) heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2)) maxHeight = max(int(heightA), int(heightB)) # 变换后对应坐标位置 dst = np.array([ [0, 0], [maxWidth - 1, 0], [maxWidth - 1, maxHeight - 1], [0, maxHeight - 1]], dtype = "float32") # 计算变换矩阵 M = cv2.getPerspectiveTransform(rect, dst) warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight)) # 返回变换后结果 return warped
# 确保检测到了docCnt = Noneif len(cnts) > 0: # 根据轮廓大小进行排序 cnts = sorted(cnts, key=cv2.contourArea, reverse=True) # 遍历每一个轮廓 for c in cnts: # 近似 peri = cv2.arcLength(c, True) approx = cv2.approxPolyDP(c, 0.02 * peri, True) # 准备做透视变换 if len(approx) == 4: docCnt = approx break# 执行透视变换warped = four_point_transform(gray, docCnt.reshape(4, 2))cv_show('warped',warped)
def sort_contours(cnts, method="left-to-right"): reverse = False i = 0 if method == "right-to-left" or method == "bottom-to-top": reverse = True if method == "top-to-bottom" or method == "bottom-to-top": i = 1 boundingBoxes = [cv2.boundingRect(c) for c in cnts] (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes), key=lambda b: b[1][i], reverse=reverse)) return cnts, boundingBoxes
# Otsu's 阈值处理thresh = cv2.threshold(warped, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1] cv_show('thresh',thresh)thresh_Contours = thresh.copy()# 找到每一个圆圈轮廓cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]cv2.drawContours(thresh_Contours,cnts,-1,(0,0,255),3) cv_show('thresh_Contours',thresh_Contours)questionCnts = []
以上就是今天要讲的内容,本文仅仅简单介绍了答题卡识别的使用,而python提供了大量能使我们快速便捷地处理数据的函数和方法。
转载地址:http://wuusi.baihongyu.com/