License Plate Character Recognition from Blurred Vehicle Video
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices mounted on vehicles struggle to obtain clear images of license plates due to motion blur caused by vehicle movement, making it difficult to identify character strings accurately.
Innovation Solution
An electronic device equipped with at least one camera, communication circuitry, memory, and a processor, which obtains video information, identifies images of designated vehicles, crops the license plate area, transmits image information to a server, receives text information, and provides the character string on the license plate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If video information is obtained through a camera mounted on a moving vehicle, then the electronic device can capture license plate images, but motion blur occurs making character string identification difficult
Solution Approach 1:
The system performs preliminary actions by capturing multiple video frames before character recognition, selecting frames with minimal motion blur, and preprocessing images to optimize character visibility. This preliminary preparation enables accurate recognition despite vehicle movement.
Solution Approach 2:
The patent introduces an intermediary processing system that includes server-based recognition models and image processing algorithms. These intermediaries transform the blurred video input into clear character string output by filtering, enhancing, and analyzing the visual data.
2Measurement precision
If a server-based recognition model is used to identify character strings, then recognition accuracy improves, but system complexity and communication requirements increase
Solution Approach 1:
The system segments the recognition task between the electronic device (capturing and preprocessing) and the server (performing final recognition). This division allows complex server-based models to be used while keeping the onboard device relatively simple.
Solution Approach 2:
The server-based recognition model serves multiple functions: it processes images from different vehicles, handles various lighting conditions, and provides centralized updates to multiple electronic devices, reducing the need for each device to have independent complex recognition capabilities.
Data Source
AI summary
According to an embodiment, an electronic device includes at least one camera, communication circuitry, memory, and at least one processor operably connected with the at least one camera, the communication circuitry, and the memory, and the processor is configured to obtain video information through the at least one camera, identify a plurality of images including a designated vehicle based on the video information, identify a designated area corresponding to a license plate of the designated vehicle within the plurality of images, based on the plurality of images, transmit image information on the designated area to a server connected to the electronic device, based on transmitting the image information on the designated area to the server, receive text information on the designated area from the server, and based on the text information, provide a character string represented on the license plate.