OpenCV VideoCapture 和错误:(-215:Assertion failed) !_src.empty() in function 'cv::cvtColor' [英] OpenCV VideoCapture and error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'

问题描述

目前使用 Windows 10 和 Python 3.7我尝试使用此代码运行以使网络摄像头能够用于数字识别

Currently using Windows 10 with Python 3.7 I tried running with this code in order to get the webcam to function for use in number recognition

def get_img_contour_thresh(img):
   x, y, w, h = 0, 0, 300, 300
   gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
   blur = cv2.GaussianBlur(gray, (5, 5), 0)
   ret, thresh1 = cv2.threshold(blur, 175, 255, cv2.THRESH_BINARY_INV + 
     cv2.THRESH_OTSU)
   thresh1 = thresh1[y:y + h, x:x + w]
   contours, hierarchy = cv2.findContours(thresh1, cv2.RETR_TREE, 
     cv2.CHAIN_APPROX_SIMPLE)[-2:]
   return img, contours, thresh1

def show_webcam(mirror=False):
   # load json and create model
   json_file = open('model.json', 'r')
   loaded_model_json = json_file.read()
   json_file.close()
   model = model_from_json(loaded_model_json)
   # load weights into new model
   model.load_weights("model.h5")
   print("Loaded model from disk")

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

cap = cv2.VideoCapture(0)
while True:
    ret, img = cap.read()
    img, contours, thresh = get_img_contour_thresh(img)
    ans = ''


    if len(contours) > 0:
        contour = max(contours, key=cv2.contourArea)
        if cv2.contourArea(contour) > 500:
            x, y, w, h = cv2.boundingRect(contour)
            newImage = thresh[y:y + h, x:x + w]
            newImage = cv2.resize(newImage, (28, 28))
            newImage = np.array(newImage)
            newImage = newImage.astype('float32')
            newImage /= 255

            if K.image_data_format() == 'channels_first':
                newImage = newImage.reshape(1, 28, 28)
            else:
                newImage = newImage.reshape(28, 28, 1)
            newImage = np.expand_dims(newImage, axis=0)
            ans = model.predict(newImage).argmax()


    x, y, w, h = 0, 0, 300, 300
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
    cv2.putText(img, "CNN : " + str(ans), (10, 320),
                cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
    cv2.imshow("Frame", img)
    cv2.imshow("Contours", thresh)     


    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()


def main():
   show_webcam(mirror=True)


if __name__ == '__main__':
   main()

我收到此错误

 File "cam.py", line 75, in <module>
   main()
 File "cam.py", line 71, in main
   show_webcam(mirror=True)
 File "cam.py", line 34, in show_webcam
   img, contours, thresh = get_img_contour_thresh(img)
 File "cam.py", line 10, in get_img_contour_thresh
   gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 cv2.error: OpenCV(3.4.4) C:projectsopencv- 
   pythonopencvmodulesimgprocsrccolor.cpp:181: error: (-215:Assertion 
   failed) !_src.empty() in function 'cv::cvtColor'

我一直在寻找解决方案，但一直没有找到解决方案，尝试环顾四周，但无法弄清楚，你们怎么看?感谢给予的帮助

Iv been looking for a solution for a while but havent had any luck in figuring this out, tried looking around but just cant figure it out, what do you guys think? Appreciate the help given

推荐答案

您看到的错误是在 None 传递给 cv2.cvtColor 时发生的错误.

The error you're seeing is one that happens if None gets passed on cv2.cvtColor.

之后

ret, img = cap.read()

在继续之前检查 img 不是 None 是个好主意.根据您的输入源，cap.read() 可能会失败.在我的一台笔记本电脑上，它在开始返回有效图像之前至少失败了一次.

it's a good idea to check that img is not None before proceeding. Depending on your input source, cap.read() can fail. On one my laptops, it fails at least once before starting to return valid images.

这篇关于OpenCV VideoCapture 和错误:(-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！