程序启动时相机打开

Question

我希望在 GUI 上按下按钮后打开相机，但不幸的是，当我运行代码时它会打开。我不知道问题出在哪里。

我是否可以将按钮放在凸轮画布旁边，以便在我实际按下按钮而不是“c”键时打印识别的文本。

import cv2
import pytesseract
import matplotlib.pyplot as plt
import numpy as np
pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'

import tkinter as tk
import cv2
from PIL import Image, ImageTk


class CamView():
    def __init__(self, parent):
        self.parent = parent
        self.window = tk.Toplevel(parent)

        self.lmain2 = tk.Label(self.window)
        self.lmain2.pack()

        self.window.protocol("WM_DELETE_WINDOW", self.close)
        self.show_frame()

    def show_frame(self):
        imgtk = ImageTk.PhotoImage(image=self.parent.img)
        self.lmain2.imgtk = imgtk
        self.lmain2.configure(image=imgtk)

    def close(self):
        self.parent.test_frame = None
        self.window.destroy()

root = tk.Tk()
root.bind('<Escape>', lambda e: root.quit())

class Main(tk.Frame):
    def __init__(self, parent):

        self.lmain = tk.Label(parent)
        self.lmain.pack()

        self.test_frame = None
        frame = tk.Frame.__init__(self,parent)
        a = tk.Label(text='hello!').pack()
        b = tk.Button(frame, text='open', command=self.load_window)
        b.pack()

        pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'

        font_scale = 2.5
        font = cv2.FONT_HERSHEY_PLAIN
        self.cap = cv2.VideoCapture(0)
        self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, 426)
        self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, 240)
        if not self.cap.isOpened():
            self.cap = cv2.VideoCapture(1)
        if not self.cap.isOpened():
            raise IOError("Cannot Open The Video Camera")

        cntr = 0
        while True:
            ret, frame = self.cap.read()
            cntr = cntr + 1
            if ((cntr % 20) == 0):
                imgH, imgW, _ = frame.shape

                x1, y1, w1, h1 = 0, 0, imgH, imgW

                imgchar = pytesseract.image_to_string(frame)
                imgboxes = pytesseract.image_to_boxes(frame)

                for boxes in imgboxes.splitlines():
                    boxes = boxes.split(' ')
                    x, y, w, h = int(boxes[1]), int(boxes[2]), int(boxes[3]), int(boxes[4])
                    cv2.rectangle(frame, (x, imgH - y), (w, imgH - h), (0, 0, 255), 3)

                cv2.putText(frame, imgchar, (x1 + int(w1 / 50), y1 + int(h1 / 50)), cv2.FONT_HERSHEY_SIMPLEX, 0.7,
                            (255, 0, 0), 2)
                font = cv2.FONT_HERSHEY_SIMPLEX

                cv2.imshow('Text detection', frame)
                if cv2.waitKey(1) & 0xFF == ord('c'):
                    print(imgchar)

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

        self.do_stuff()

    def do_stuff(self):
        _, frame = self.cap.read()
        frame = cv2.flip(frame, 1)
        cv2image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGBA)
        self.img = Image.fromarray(cv2image)
        if self.test_frame != None:
            self.test_frame.show_frame()
        self.lmain.after(10, self.do_stuff)

    def load_window(self):
        if self.test_frame == None:
            self.test_frame = CamView(self)

control = Main(root)
root.mainloop()

Answer 1

要在按下按钮后让相机运行，您必须将触发相机的cv2 代码移出Main __init__。

class Main(tk.Frame):
    def __init__(self, parent):    
        self.lmain = tk.Label(parent)
        self.lmain.pack()

        self.test_frame = None
        frame = tk.Frame.__init__(self,parent)
        a = tk.Label(text='hello!').pack()
        b = tk.Button(frame, text='open', command=self.run_cam)
        b.pack()

    def run_cam(self):
        pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'

        font_scale = 2.5
        font = cv2.FONT_HERSHEY_PLAIN
        self.cap = cv2.VideoCapture(0)
        self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, 426)
        self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, 240)
        if not self.cap.isOpened():
            self.cap = cv2.VideoCapture(1)
        if not self.cap.isOpened():
            raise IOError("Cannot Open The Video Camera")

        cntr = 0
        while True:
            ret, frame = self.cap.read()
            cntr = cntr + 1
            if ((cntr % 20) == 0):
                imgH, imgW, _ = frame.shape

                x1, y1, w1, h1 = 0, 0, imgH, imgW

                imgchar = pytesseract.image_to_string(frame)
                imgboxes = pytesseract.image_to_boxes(frame)

                for boxes in imgboxes.splitlines():
                    boxes = boxes.split(' ')
                    x, y, w, h = int(boxes[1]), int(boxes[2]), int(boxes[3]), int(boxes[4])
                    cv2.rectangle(frame, (x, imgH - y), (w, imgH - h), (0, 0, 255), 3)

                cv2.putText(frame, imgchar, (x1 + int(w1 / 50), y1 + int(h1 / 50)), cv2.FONT_HERSHEY_SIMPLEX, 0.7,
                            (255, 0, 0), 2)
                font = cv2.FONT_HERSHEY_SIMPLEX

                cv2.imshow('Text detection', frame)
                if cv2.waitKey(1) & 0xFF == ord('c'):
                    print(imgchar)

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

        self.do_stuff()