python - 实时网络摄像头源上的 OCR：图像高度为零，IHDR 数据无效

问题描述

所以我对 openCV 和谷歌视觉还是很陌生，但我正在尝试使用边缘检测来识别标签特定区域中的数字。当标签在相机视野中时，代码运行并正常工作，但是当标签不在视野中时，我收到 libpng 警告：IDHR 和 libpng 中的图像高度为零错误：IHDR 数据无效

我试过检查框架是否不是 Nonetype 并且 ret 是 True 但我不知道如何让它不输出任何东西，直到框架中的标签。

下面是示例帧的图像和我的边缘检测的输出 https://i.stack.imgur.com/tVHFm.jpg https://i.stack.imgur.com/Mb3Z5.jpg

import io
import cv2
from PIL import Image
import numpy as np
import re

from imutils.perspective import four_point_transform 
import imutils

# Imports the Google Cloud client library
from google.cloud import vision
from google.cloud.vision import types

# Instantiates a client
client = vision.ImageAnnotatorClient()
def detect_text(path):
    global lotid
    """Detects text in the file."""
    with io.open(path, 'rb') as image_file:
        content = image_file.read()

    image = types.Image(content=content)
    response = client.text_detection(image=image)
    texts = response.text_annotations
    string = ''

    for text in texts:
        string+=' ' + text.description
        string = string[0:9]
    return string

cap = cv2.VideoCapture(0)

while(True):  
# cap.isOpened()

    # Capture frame-by-frame
    ret, frame = cap.read()

    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(blurred, 50, 200, 255)

    # find contours in the edge map, then sort them by their size in descending order
    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnts = imutils.grab_contours(cnts)
    cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
    displayCnt = None

    for c in cnts:
        peri = cv2.arcLength(c,True)
        approx = cv2.approxPolyDP(c,.02 * peri, True)
        if len(approx) == 4:
            displayCnt = approx
            break

    # extract the display, apply a perspective transform to it
    warped = four_point_transform(gray, displayCnt.reshape(4, 2))
    output = four_point_transform(frame, displayCnt.reshape(4, 2))

    (h,w) = warped.shape
    (dX,dY) = (int(w*.8),int(h*.45))
    crop = warped[20:dY,w-dX:w-20]


    file = 'live.png'
    cv2.imwrite(file,crop)

    # print OCR text
    print(detect_text(file))

    # Display the resulting frame
    cv2.imshow('frame',crop)

    k = cv2.waitKey(30) &0xff
    if k == 27:
        break

    # print('Confidence: {}'.format(detect_text.confidence))

# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()

标签： pythonopencvcomputer-vision

python - 实时网络摄像头源上的 OCR：图像高度为零，IHDR 数据无效

问题描述

解决方案

推荐阅读