从图像中提取书名

问题描述

我有很多漫画，我想使用网络摄像头提取它们的标题。我在下面做了代码：

import cv2
import numpy as np
import PyTesseract
from PIL import Image
from PyTesseract import Output


cam = cv2.VideoCapture(2)

cv2.namedWindow("test")

img_counter = 0

while True:
    ret,frame = cam.read()
    if not ret:
        print("Failed to grab frame")
        break
    cv2.imshow("test",frame)

    k = cv2.waitKey(1)
    if k%256 == 27:
        # ESC pressed
        print("Escape hit,closing...")
        break
    elif k%256 == 32:
        # SPACE pressed
        img_name = "opencv_frame_{}.png".format(img_counter)
        cv2.imwrite(img_name,frame)
        print("{} written!".format(img_name))

        image = cv2.imread(img_name)
        im = cv2.cvtColor(image,cv2.COLOR_BGR2RGB)        
        img = Image.fromarray(im)
        results = PyTesseract.image_to_data(img,lang='fra+eng',output_type=Output.DICT)

        # loop over each of the individual text localizations
        for i in range(0,len(results["text"])):
            # extract the bounding Box coordinates of the text region from
            # the current result
            x = results["left"][i]
            y = results["top"][i]
            w = results["width"][i]
            h = results["height"][i]
            text = results["text"][i]
            conf = int(results["conf"][i])


            # filter out weak confidence text localizations
            if conf > 50:
                    # display the confidence and text to our terminal
                    print("Confidence: {}".format(conf))
                    print("Text: {}".format(text))
                    print("")
                    text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
                    cv2.rectangle(image,(x,y),(x + w,y + h),(0,255,0),2)
                    cv2.putText(image,text,y - 10),cv2.FONT_HERShey_SIMPLEX,1.2,255),3)
        
        cv2.imshow("res",image)


        #####################################
        img_counter += 1

cam.release()

cv2.destroyAllWindows()

当我按“ SPACE”时，会拍下标题的照片，而tesseract会尝试提取一些文本。我做了下面的测试。

请问如何改善呢？ （除非在书中找到用好字体写的标题：-））

欢呼

Karim

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）