📄 中文摘要
本教程详细介绍了如何利用Python和PySide6框架，结合Dynamsoft Capture Vision SDK，开发一款专业的桌面应用程序。该应用能够从护照和身份证件中读取机器可读区域（MRZ），并具备人像和证件检测功能。用户将学习构建一个跨平台的护照扫描器，实现对TD1、TD2、TD3格式证件的实时MRZ识别。此外，该扫描器还能在旅行证件上进行人像/面部检测和定位。文章还涵盖了多种输入方式，包括图像文件、文件夹、摄像头视频流等，为用户提供了灵活的数据处理能力。通过本指南，开发者可以掌握构建功能完善的图形用户界面（GUI）应用程序的关键技术，从而高效地处理和验证身份信息，提升数据采集的准确性和便捷性。
📄 English Summary
How to Build a Python Passport Scanner with Portrait, MRZ and Document Detection
This tutorial guides users through building a professional desktop application for reading Machine Readable Zones (MRZ) from passports and ID cards, incorporating portrait and document detection capabilities. The guide leverages Python, PySide6 for the GUI, and the powerful Dynamsoft Capture Vision SDK to achieve its functionalities. By following the steps outlined, developers will construct a cross-platform passport scanner capable of real-time MRZ recognition from various document formats, including TD1, TD2, and TD3. A key feature of the application is its ability to perform portrait/face detection and localization directly on travel documents, enhancing the verification process. The tutorial also details how to integrate multiple input methods, such as processing image files, entire folders of images, and live camera streams, providing flexibility for different use cases. This comprehensive resource empowers developers to create a fully functional GUI application for efficient and accurate identity document processing, significantly improving data capture and validation workflows. The resulting tool offers robust capabilities for secure and rapid identification, making it suitable for various applications requiring document scanning and data extraction.