Python利用wxPython实现ocr识别图片汉字程序

pip install pytesseract

import wx
import pytesseract
import cv2
class MyFrame(wx.Frame):
    def __init__(self, parent, title):
        super(MyFrame, self).__init__(parent, title=title, size=(400, 300))
        panel = wx.Panel(self)
        self.text_ctrl = wx.TextCtrl(panel, style=wx.TE_MULTILINE)
        self.button = wx.Button(panel, label="Select Image")
        self.button.Bind(wx.EVT_BUTTON, self.on_select_image)
        sizer = wx.BoxSizer(wx.VERTICAL)
        sizer.Add(self.text_ctrl, proportion=1, flag=wx.EXPAND | wx.ALL, border=10)
        sizer.Add(self.button, flag=wx.ALIGN_CENTER | wx.ALL, border=10)
        panel.SetSizer(sizer)
    def on_select_image(self, event):
        wildcard = "JPEG files (*.jpg)|*.jpg|PNG files (*.png)|*.png"
        dialog = wx.FileDialog(self, "Select Image", wildcard=wildcard, style=wx.FD_OPEN | wx.FD_FILE_MUST_EXIST)
        if dialog.ShowModal() == wx.ID_CANCEL:
            return
        image_path = dialog.GetPath()
        dialog.Destroy()
        # Perform OCR on the selected image
        text = self.perform_ocr(image_path)
        # Display the recognized text in the text control
        self.text_ctrl.SetValue(text)
    def perform_ocr(self, image_path):
        # Load the image using OpenCV
        image = cv2.imread(image_path)
        # Preprocess the image (you may need to modify this based on your requirements)
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
        # Perform OCR using pytesseract
        text = pytesseract.image_to_string(gray)
        return text
if __name__ == "__main__":
    app = wx.App()
    frame = MyFrame(None, "OCR with wxPython")
    frame.Show()
    app.MainLoop()