2D Code Identification via Global Feature Positioning and Focus Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Two-dimensional code identification systems face low decoding accuracy in complex scenarios due to low image resolution, particularly in long-distance scanning applications such as parking charging and expressway toll charging.
Innovation Solution
A method and device that utilize a pre-established two-dimensional code positioning and identification model for global feature positioning detection, followed by focus adjustment based on a predetermined image resolution, using auto-focusing or zooming techniques to enhance image resolution, and deep learning for model training with sample codes and identifier information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If long-distance scanning is used in complex scenarios, then scanning convenience is improved, but image resolution deteriorates leading to low decoding accuracy
Solution Approach 1:
The system performs preliminary global feature positioning detection using a pre-established deep learning model to identify code locations and characteristics before decoding. This preliminary action enables the system to handle low-resolution images by pre-characterizing the code structure, thereby maintaining decoding accuracy even when image resolution deteriorates due to long-distance scanning.
Solution Approach 2:
The system dynamically adjusts processing parameters based on image resolution characteristics. When low resolution is detected, the system changes decoding parameters and applies focus adjustment techniques to optimize the balance between scanning convenience and decoding accuracy, resolving the contradiction between ease of operation and measurement precision.
2Measurement precision
If image resolution is increased through focus adjustment, then decoding accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary positioning detection using a pre-trained deep learning model that can quickly identify code features without requiring high-resolution images. This preliminary action reduces the need for extensive focus adjustment and subsequent decoding processing, thereby improving decoding accuracy while minimizing time loss.
Solution Approach 2:
The system creates a virtual copy of the positioning and identification model that can be rapidly applied to different images. This copied model enables quick prediction of code characteristics without reprocessing the entire image at high resolution, thus improving accuracy while reducing processing time.
3Measurement precision
If deep learning model training is performed with extensive sample data, then positioning and identification accuracy is improved, but model complexity increases
Solution Approach 1:
The system optimizes model parameters by training with diverse sample data representing different environments and conditions. This parameter optimization enables the model to achieve high positioning and identification accuracy without requiring excessive model complexity, as the trained parameters capture essential features efficiently.
Solution Approach 2:
The deep learning model performs self-learning during the training phase, automatically extracting relevant features and patterns from sample data. This self-service capability enables the model to achieve high accuracy without requiring complex manual feature engineering or overly complex architecture, thus resolving the contradiction between precision and complexity.
Data Source
AI summary
The present specification provides a two-dimensional code identification method and device, and a two-dimensional code positioning and identification model establishment method and device. The two-dimensional code identification method includes: obtaining a to-be-identified two-dimensional code, and performing global feature positioning detection on the to-be-identified two-dimensional code by using a pre-established two-dimensional code positioning and identification model; performing focus adjustment, based on a predetermined image resolution, on the to-be-identified two-dimensional code on which positioning detection is performed; and decoding the to-be-identified two-dimensional code on which focus adjustment is performed. The present specification can improve the identification accuracy of two-dimensional codes shot in complex scenarios.