后台运行任务/function

Question

i wrote a program to capture the position of license plate with my webcam feed using YOLOv4. The result of the detection is then passed to easyOCR to do character identification. Right now, im calling the OCR function in the while loop everytime a detection occured. Is there a way to call the OCR function outside the loop without stopping the webcam feed? some people suggested me to use queue or sub process but im not quite familiar with the concept. Any help would be very appreciated

#detection
while 1:
    #_, pre_img = cap.read()
    #pre_img= cv2.resize(pre_img, (640, 480))
    _, img = cap.read()
    #img = cv2.flip(pre_img,1)
    hight, width, _ = img.shape
    blob = cv2.dnn.blobFromImage(img, 1 / 255, (416, 416), (0, 0, 0), swapRB=True, crop=False)

    net.setInput(blob)

    output_layers_name = net.getUnconnectedOutLayersNames()

    layerOutputs = net.forward(output_layers_name)

    boxes = []
    confidences = []
    class_ids = []

    for output in layerOutputs:
        for detection in output:
            score = detection[5:]
            class_id = np.argmax(score)
            confidence = score[class_id]
            if confidence > 0.7:
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * hight)
                w = int(detection[2] * width)
                h = int(detection[3] * hight)
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)
                boxes.append([x, y, w, h])
                confidences.append((float(confidence)))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, .5, .4)

    boxes = []
    confidences = []
    class_ids = []

    for output in layerOutputs:
        for detection in output:
            score = detection[5:]
            class_id = np.argmax(score)
            confidence = score[class_id]
            if confidence > 0.5:
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * hight)
                w = int(detection[2] * width)
                h = int(detection[3] * hight)

                x = int(center_x - w / 2)
                y = int(center_y - h / 2)

                boxes.append([x, y, w, h])
                confidences.append((float(confidence)))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, .8, .4)
    font = cv2.FONT_HERSHEY_PLAIN
    colors = np.random.uniform(0, 255, size=(len(boxes), 3))
    if len(indexes) > 0:
        for i in indexes.flatten():
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            confidence = str(round(confidences[i], 2))
            color = colors[i]
            cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
            detected_image = img[y:y+h, x:x+w]
            cv2.putText(img, label + " " + confidence, (x, y + 400), font, 2, color, 2)
            #print(detected_image)
            cv2.imshow('detection',detected_image)

            result = OCR(detected_image)
            print(result)

Function for OCR

def OCR(cropped_image):

    result = reader.readtext(cropped_image)
    text = ''
    for result in result:
        text += result[1] + ' '

    spliced = (remove(text)).upper()
    return spliced

Answer 1

You could run the OCR function on an other thread with the thread library like so:

import time  # not necessary only to simulate work time
import _thread as thread  # in python 3 the name has changed to _thread


def OCR(cropped_image):

    result = reader.readtext(cropped_image)
    text = ''
    for result in result:
        text += result[1] + ' '

    spliced = (remove(text)).upper()
    print(spliced) # you would have to print the result in the OCR function because you can't easily return stuff


while 1:
    time.sleep(5)  # simulating some work time
    print("main")

    detected_image = 1
    thread.start_new_thread(OCR, (detected_image,)) # calling the OCR function on a new thread.

I hope it will help you...