### Python 实现答题卡识别 OCR 的代码示例 以下是基于 OpenCV 和 Tesseract OCR 技术的一个简单答题卡识别方案。此方法通过图像预处理提取答题区域，并利用 OCR 进行字符识别。 #### 图像预处理部分 ```python import cv2 import numpy as np def preprocess_image(image_path): # 加载图片并转换为灰度图 image = cv2.imread(image_path) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # 使用高斯模糊去噪 blurred = cv2.GaussianBlur(gray, (5, 5), 0) # 边缘检测 edged = cv2.Canny(blurred, 75, 200) return edged ``` #### 提取答题卡轮廓 ```python def find_contours(edged_image): contours, _ = cv2.findContours(edged_image.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 对轮廓按面积降序排列，选取最大的几个作为候选答题卡区域 contours = sorted(contours, key=cv2.contourArea, reverse=True)[:5] screen_cnt = None for contour in contours: peri = cv2.arcLength(contour, True) approx = cv2.approxPolyDP(contour, 0.02 * peri, True) # 如果找到四边形，则认为这是答题卡的边界框 if len(approx) == 4: screen_cnt = approx break return screen_cnt ``` #### 应用透视变换获取标准化答题卡视图 ```python def apply_perspective_transform(image, screen_cnt): pts = screen_cnt.reshape(4, 2) 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)] (tl, tr, br, bl) = rect width_a = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2)) width_b = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2)) max_width = max(int(width_a), int(width_b)) height_a = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2)) height_b = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2)) max_height = max(int(height_a), int(height_b)) dst = np.array([ [0, 0], [max_width - 1, 0], [max_width - 1, max_height - 1], [0, max_height - 1]], dtype="float32") M = cv2.getPerspectiveTransform(rect, dst) warped = cv2.warpPerspective(image, M, (max_width, max_height)) return warped ``` #### 利用 Tesseract OCR 进行文字识别 ```python from PIL import Image import pytesseract def recognize_answers(warped_image): # 将 OpenCV BGR 转换为 RGB 格式供 Pillow 处理 rgb_warped = cv2.cvtColor(warped_image, cv2.COLOR_BGR2RGB) pil_image = Image.fromarray(rgb_warped) # 配置 Tesseract 参数以优化单个字母识别效果 custom_config = r'-c tessedit_char_whitelist=ABCD --psm 6' text = pytesseract.image_to_string(pil_image, config=custom_config) answers = [] for line in text.split('\n'): stripped_line = line.strip() if stripped_line and stripped_line.isalpha(): answers.append(stripped_line.upper()) return answers ``` #### 主函数集成以上功能模块 ```python if __name__ == "__main__": input_image_path = 'path/to/your/image.jpg' # 步骤一：图像预处理 edged = preprocess_image(input_image_path)[^1] # 步骤二：查找答题卡轮廓 screen_cnt = find_contours(edged)[^1] if screen_cnt is not None: original_image = cv2.imread(input_image_path) warped = apply_perspective_transform(original_image, screen_cnt)[^1] # 步骤三：OCR 文字识别 recognized_answers = recognize_answers(warped)[^2] print("Recognized Answers:", recognized_answers) else: print("No valid answer sheet detected.") ``` --- ### 注意事项 - 上述代码依赖于 `pytesseract` 和 `opencv-python` 等库，请确保已安装这些库。 - 可能需要调整参数（如阈值、PSM 模式等），以便适应不同类型的答题卡设计[^1]。 - 若目标环境不支持本地部署 Tesseract，可考虑使用云端 API 接口替代自定义 OCR 功能[^2]。