HMS Core machine learning service ID card recognition function to realize efficient information entry

At the moment when all kinds of apps have to implement the real-name system, it is inevitable to carry out identity authentication. Usually buying train tickets, plane tickets, staying in hotels, playing games, etc. all require identity authentication. If you have to enter the 18-digit ID number every time, it is very troublesome, and you will make mistakes when you shake your hand. Therefore, it is quite convenient to use the ID card recognition function of Huawei Machine Service to scan the ID card and enter the ID information.

1. Business Introduction

The ID card recognition function of HMS Core Machine Learning Service is based on OCR Optical Character Recognition (Optical Character Recognition) technology, which recognizes formatted text information from images or video streams with ID card information. By calling the OCR ID card recognition ability, the key information in the ID card image, such as name, gender, ID number, etc., is extracted and output in json form, thereby helping users to quickly enter ID information, eliminating the need for users to manually enter the information. Lots of trouble.

ID card identification deployment details

DEMO demo

2. Scenario introduction

At present, many applications need to verify the customer's identity. Payment apps, travel apps, and hotel apps all require users to upload their ID photos. The ID card recognition function of HMS Core machine learning service can perform structured identification and entry of ID card information. It is widely used in insurance, finance, e-commerce and other industries that require real-name authentication. It can not only reduce the risk of user ID card information input errors, but also It can also improve the user experience with convenient operation. For example, using this service in financial apps can automatically and accurately identify and enter important information in the ID card, effectively reducing business risks caused by users entering wrong information.

3. Features

• Full field identification : Accurately identify all 8 fields on both sides of the second-generation resident ID card, fully meeting the identification requirements of any field in the ID card usage scenario.

• Fast identification : Under normal circumstances, the ID card identification delay is only 545.9ms. Through fast identification, business efficiency and user experience can be improved to the greatest extent.

• High robustness : It supports a wide range of scenarios, and can still ensure high recognition accuracy in the presence of complex lighting, complex backgrounds and other disturbances, especially the recognition accuracy of key fields is as high as 99.53%.

Huawei's machine learning service (ML Kit) ID card recognition function draws on Huawei's latest research results in OCR. In the future, it will continue to improve user interaction experience, continue to iterate and improve the accuracy and efficiency of recognition, and strive to provide developers with better usability. Strong and better experience of high-quality service experience.

How to access Huawei Machine Learning Service?

The machine learning service official website provides you with detailed documentation guidance .

Learn more details>>

Visit the official website of Huawei Developer Alliance
Get development guidance documents
Huawei Mobile Services Open Source Warehouse Address: GitHub , Gitee

Follow us to know the latest technical information of HMS Core for the first time~