python-opencv实战问题解决

Question

对于opencv答题卡识别实战项目的代码问题
出现诸多错误请问怎么解决

import numpy as np
import imutils
import cv2

image_path = r"F:\pythonnotebook\123.jpg"
image = cv2.imread(image_path)

# 正确答案
ANSWER_KEY = {0: 1, 1: 2, 2: 0, 3: 2, 4: 4}


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 rect


def 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


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


def cv_show(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


# 读取命令行参数指定的图片
image = cv2.imread(r"F:\pythonnotebook\123.jpg")
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, 45, 200)
cv2.imshow('edged', edged)
cv2.waitKey(0)
cv2.destroyAllWindows()
# 锐化处理
kernel = np.array([[-1, -1, -1], [-1, 9, -1], [-1, -1, -1]])
sharpened = cv2.filter2D(gray, -1, kernel)
# 轮廓检测
contours, hierarchy = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = contours


# 打印轮廓数据类型和长度
print(type(cnts))
print(len(cnts))

# 根据轮廓大小进行排序
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

docCnt = None

# 遍历每一个轮廓
for c in cnts:
    # 近似
    peri = cv2.arcLength(c, closed=True)
    approx = cv2.approxPolyDP(c, 0.02 * peri, closed=True)

    # 准备做透视变换
    if len(approx) == 4:
        docCnt = approx
        break

# 执行透视变换
if docCnt is not None:
    warped = four_point_transform(gray, docCnt.reshape(4, 2))
    cv_show('warped', warped)
    # 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)[1]
    if len(cnts) == 0:
        print("未检测到圆圈轮廓，请检查图片或调整阈值处理参数！")
        import sys

        sys.exit(1)

    cv2.drawContours(contours_img, contours, -1, (0, 255, 0), 2)
    cv_show('thresh_contours', thresh_contours)

    questionCnts = []
    for c in cnts:
        try:
            # 强制类型转换 + 维度检查
            c = np.array(c, dtype=np.int32).reshape(-1, 1, 2)
            if len(c) < 1:  # 完全空的情况
                continue

            (x, y, w, h) = cv2.boundingRect(c)
            ar = w / float(h)

            # 你的筛选条件
            if w >= 0.5 and h >= 0.5 and 0.3 <= ar <= 1.5:
                questionCnts.append(c)

        except Exception as e:
            print(f"处理轮廓时出错: {e}")
            continue
    if len(questionCnts) == 0:
        print("警告：未检测到任何有效气泡轮廓！")
        print("请检查：")
        print("1. 阈值处理是否合适（当前阈值：Otsu自动阈值）")
        print("2. 气泡大小参数")
        print("3. 原始图像是否包含清晰的圆形气泡区域")
        cv2.imshow("Threshold Image", thresh)  # 显示二值化图像供调试
        cv2.waitKey(0)
        exit()  # 或改为跳过评分部分
    else:
        # 只有检测到气泡时才继续处理
        questionCnts = sort_contours(questionCnts, method="top-to-bottom")[0]


    # 按照从上到下进行排序
    questionCnts = sort_contours(questionCnts,
                                 method="top-to-bottom")[0]
    correct = 0

    # 每排有5个选项
    for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
        # 排序
        cnts = sort_contours(questionCnts[i:i + 5])[0]
        bubbled = None

        # 遍历每一个结果
        for (j, c) in enumerate(cnts):
            # 使用mask来判断结果
            mask = np.zeros(thresh.shape, dtype="uint8")
            cv2.drawContours(mask, [c], -1, 255, -1)  # -1表示填充
            cv_show('mask', mask)
            # 通过计算非零点数量来算是否选择这个答案
            mask = cv2.bitwise_and(thresh, thresh, mask=mask)
            total = cv2.countNonZero(mask)

            # 通过阈值判断
            if bubbled is None or total > bubbled[0]:
                bubbled = (total, j)

        # 对比正确答案
        color = (0, 0, 255)
        k = ANSWER_KEY[q]

        # 判断正确
        if k == bubbled[1]:
            color = (0, 255, 0)
            correct += 1

        # 绘图

        if k < len(cnts):
            cv2.drawContours(warped, [cnts[k]], -1, color, 3)
        else:
            print(f"警告：索引 {k} 超出轮廓列表长度 {len(cnts)}")

    score = (correct / 5.0) * 100
    print("[INFO] score: {:.2f}%".format(score))
    cv2.putText(warped, "{:.2f}%".format(score), (10, 30),
                cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
    cv2.imshow("Original", image)
    cv2.imshow("Exam", warped)
    cv2.waitKey(0)
else:
    print("未检测到答题卡轮廓，请检查图片或调整边缘检测参数！")

Answer 1

让【宝码香车】来帮你解答，本回答参考DeepSeek编写，并整理提供。
如果还有疑问可以点击头像关注私信或评论。如果答案让您满意，请采纳、点赞、关注，非常感谢！

OpenCV答题卡识别项目问题分析与解决方案

根据您提供的代码，我发现了几个潜在的问题点并提供解决方案：

主要问题分析

1. 图像路径问题：代码中两次定义了image_path，可能导致混淆
2. 轮廓处理问题：在检测气泡轮廓时可能存在类型转换和维度问题
3. 重复排序操作：questionCnts被排序了两次
4. 索引越界风险：在绘制正确答案时没有充分检查索引范围

解决方案代码

import numpy as np
import cv2

# 正确答案
ANSWER_KEY = {0: 1, 1: 2, 2: 0, 3: 2, 4: 4}

def order_points(pts):
    rect = np.zeros((4, 2), dtype="float32")
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]
    diff = np.diff(pts, axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]
    return rect

def four_point_transform(image, pts):
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    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))

    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    return 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

def cv_show(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

# 读取图片
image_path = r"F:\pythonnotebook\123.jpg"  # 确保路径正确
image = cv2.imread(image_path)
if image is None:
    print(f"无法读取图片，请检查路径: {image_path}")
    exit()

# 预处理
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(blurred, 45, 200)

# 轮廓检测
contours = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
cnts = sorted(contours, key=cv2.contourArea, reverse=True)

docCnt = None
for c in cnts:
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.02 * peri, True)
    if len(approx) == 4:
        docCnt = approx
        break

if docCnt is None:
    print("未检测到答题卡轮廓，请检查图片或调整边缘检测参数！")
    exit()

# 透视变换
warped = four_point_transform(gray, docCnt.reshape(4, 2))
thresh = cv2.threshold(warped, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]

# 检测气泡轮廓
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
questionCnts = []

for c in cnts:
    (x, y, w, h) = cv2.boundingRect(c)
    ar = w / float(h)
    if w >= 20 and h >= 20 and 0.7 <= ar <= 1.3:  # 调整参数以适应实际气泡大小
        questionCnts.append(c)

if len(questionCnts) == 0:
    print("未检测到任何气泡，请调整参数或检查图片质量")
    exit()

# 排序气泡轮廓
questionCnts = sort_contours(questionCnts, method="top-to-bottom")[0]
correct = 0

# 评分
for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
    cnts = sort_contours(questionCnts[i:i + 5])[0]
    bubbled = None

    for (j, c) in enumerate(cnts):
        mask = np.zeros(thresh.shape, dtype="uint8")
        cv2.drawContours(mask, [c], -1, 255, -1)
        mask = cv2.bitwise_and(thresh, thresh, mask=mask)
        total = cv2.countNonZero(mask)

        if bubbled is None or total > bubbled[0]:
            bubbled = (total, j)

    color = (0, 0, 255)
    k = ANSWER_KEY.get(q, -1)
    
    if k != -1 and k < len(cnts):
        if k == bubbled[1]:
            color = (0, 255, 0)
            correct += 1
        cv2.drawContours(warped, [cnts[k]], -1, color, 3)

score = (correct / 5.0) * 100
print(f"得分: {score:.2f}%")
cv2.putText(warped, f"{score:.2f}%", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
cv2.imshow("Original", image)
cv2.imshow("Exam", warped)
cv2.waitKey(0)

关键改进点

1. 图像路径检查：添加了图像读取成功检查
2. 轮廓处理优化：
   • 使用imutils.grab_contours确保轮廓格式一致
   • 调整了气泡检测的参数（w和h的阈值）
3. 错误处理增强：
   • 添加了对ANSWER_KEY中索引的检查
   • 更完善的轮廓存在性检查
4. 性能优化：
   • 移除了重复的排序操作
   • 简化了部分逻辑

调试建议

1. 在关键步骤后添加图像显示，检查中间结果
2. 调整Canny边缘检测的阈值(45, 200)以适应不同图片
3. 根据实际气泡大小调整检测参数(w >= 20, h >= 20)
4. 确保答题卡图片质量足够高，光照均匀

如果问题仍然存在，建议提供具体的错误信息和中间处理结果的图像，以便更精准地定位问题。