pytesseract出现的问题

Question

python运行关于pytesseract的代码出现以下错误

pytesseract.pytesseract.TesseractError: (1, "Tesseract Open Source OCR Engine v3.05.00dev with Leptonica read_params_file: Can't open 11 read_params_file: Can't open txt Warning in pixReadMemPng: work-around: writing to a temp file libpng warning: Application built with libpng-1.4.3 but running with 1.5.14 Error in pixReadStreamPng: png_ptr not made Error in pixReadMemPng: pix not read Error in pixReadMem: png: no pix returned Error during processing.")

以下为原代码

import cv2
import pytesseract
import numpy as np

# 视频捕获对象，0表示默认摄像头
cap = cv2.VideoCapture(1)

while True:
    # 读取当前帧
    ret, frame = cap.read()

    # 翻转帧以适应自然阅读顺序
    frame = cv2.flip(frame, 1)

    # 将图像转换为灰度图像
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # 对图片进行二值化处理
    ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)

    # 找到并筛选出所有轮廓
    contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    contours = sorted(contours, key=cv2.contourArea, reverse=True)[:10]

    # 遍历每一个轮廓
    for contour in contours:
        # 计算轮廓周长
        perimeter = cv2.arcLength(contour, True)

        # 近似估计轮廓的形状
        approx = cv2.approxPolyDP(contour, 0.02 * perimeter, True)

        # 如果轮廓有四个点，就认为这可能是一个文档边缘
        if len(approx) == 4:
            # 在图像上绘制文档轮廓
            cv2.drawContours(frame, [approx], -1, (0, 255, 0), 3)

            # 透视变换矫正文档，得到一个矩形的图像
            rect = cv2.minAreaRect(contour)
            box = cv2.boxPoints(rect)
            box = np.int0(box)
            height, width = frame.shape[:2]
            pts1 = np.float32(box)
            pts2 = np.float32([[0, 0], [width, 0], [0, height], [width, height]])
            M = cv2.getPerspectiveTransform(pts1, pts2)
            dst = cv2.warpPerspective(frame, M, (width, height))

            # 将矩形图像转为灰度图像并进行 OCR 文字识别
            gray_rect = cv2.cvtColor(dst, cv2.COLOR_BGR2GRAY)
            text = pytesseract.image_to_string(gray_rect, lang='eng', config='--psm 11')
            print(text)

    # 显示当前帧
    cv2.imshow('frame', frame)

    # 如果按下q键，退出循环
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放资源并关闭窗口
cap.release()
cv2.destroyAllWindows()

Answer 1

可以查看这篇：
https://blog.csdn.net/weixin_41194171/article/details/110433724