Question

因此，我尝试使用OpenCV扫描此表单，并从本质上为所标记的问题制定密钥。现在，我尝试列举一些在网上找到的示例，并将其转换为二进制图像，但是在检测问题标记时遇到了问题。我通过在线上找到的一本教程做了一些介绍，但是他们使用了另一种格式的表单，该表单上的材料比示例中显示的要多得多，我可以使用更熟悉OpenCV的人的一些意见。帮助不一定是对我的代码甚至是工作代码的改进，它可能是指向更有用的文档，材料或教程的链接和参考。

def analyzeKey(self):
    keypix = self.doc.getPagePixmap(0, alpha=False)
    keyim = self.pixel2np(keypix)
    cv2.imwrite("keyimage.jpg",keyim)
    key = cv2.imread("keyimage.jpg")

    grayscale = cv2.cvtColor(key, cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(grayscale, (5, 5), 0)
    edged = cv2.Canny(blurred, 75, 200)
    cv2.imshow("Key", edged)


    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
                            cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if imutils.is_cv2() else cnts[1]
    docCnt = None

    # ensure that at least one contour was found
    if len(cnts) > 0:
        # sort the contours according to their size in
        # descending order
        cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

        # loop over the sorted contours
        for c in cnts:
            # approximate the contour
            peri = cv2.arcLength(c, True)
            approx = cv2.approxPolyDP(c, 0.02 * peri, True)
    # if our approximated contour has four points,
            if len(approx) == 4:
                docCnt = approx
                break

    #originalkey = four_point_transform(key, docCnt.reshape(4, 2))
    #newkey = four_point_transform(grayscale, docCnt.reshape(4, 2))
    keyim[:,:,2] = 0
    cv2.imshow("Split",keyim)
    thresh = cv2.threshold(grayscale, 0,255,
                           cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
    cv2.imshow("Otsu", thresh)
    cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
                            cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if imutils.is_cv2() else cnts[1]
    questionCnts = []

    for cntrs in cnts:
        (x, y, w, h) = cv2.boundingRect(c)
        ar = w / float(h)

        if w>= 20 and h>=20 and ar>=0.9 and ar<=1.1:
            questionCnts.append(c)

    cv2.imshow("cnts", questionCnts[0])

Answer 1

要获取铅笔标记的轮廓而不是阈值，可以使用cv2.inRange来区分灰色/黑色铅笔标记和橙色文本。您可以为允许的颜色选择上下限。在这里，我仅选择黑色作为下限，并选择灰色（180,180,180）作为上限，然后将其应用于您给出的彩色图像。这些值之间的任何像素都在下面显示的输出掩码中指示。

img = cv2.imread('keyimage.jpg')
lower_bound = (0,0,0)
upper_bound = (180,180,180)
mask = cv2.inRange(img, lower_bound, upper_bound)
plt.imshow(mask, cmap='gray')
plt.show()

我正在尝试分析Scantron表单并为OMR项目创建密钥

1 个答案: