Mail Item Image Recognition Using Single Color Camera
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for recognizing and reading postal information on mail items, such as large letters and packages, are complex and costly due to the need for synchronized use of low resolution color and high resolution gray level cameras, especially when dealing with colored, patterned backgrounds that contain multiple texts.
Innovation Solution
A method using a single color camera to capture mail item surfaces, converting the color image into higher resolution gray level and lower resolution color images, allowing for object recognition and postal information reading without alignment and synchronization issues, utilizing specialized OCR units for efficient data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple cameras (color and gray level) are used to capture mail item surfaces, then the ability to recognize objects and read postal information is improved, but the device complexity and synchronization requirements increase
Solution Approach 1:
The patent combines the functions of multiple cameras into a single color camera that captures both color information and high-resolution detail. The color camera takes images in multiple color channels (R, G, B) which are then processed to create both color and gray level representations, eliminating the need for separate cameras and their synchronization systems.
Solution Approach 2:
The single color camera performs multiple functions: it captures color information for object classification, provides high-resolution images for postal information reading, and enables both functions simultaneously without requiring separate dedicated cameras for each purpose.
2Measurement precision
If high resolution gray level images are used for reading postal information, then reading accuracy is improved, but the time required for processing increases
Solution Approach 1:
The patent divides the image processing into distinct segments: color information is extracted for object classification and identification, while gray level information is used specifically for postal information reading. This segmentation allows parallel processing of different image aspects, improving overall processing speed while maintaining accuracy.
Solution Approach 2:
The system performs preliminary object recognition and classification using color information before proceeding to read postal information. This preliminary action identifies which areas require detailed reading, allowing the system to focus processing resources on relevant regions and reduce overall processing time.
Data Source
AI summary
The invention relates to a method for recognizing objects in mail items and an arrangement for carrying out the method. In the method, the color image produced in the relevant color camera is converted into a gray level image having a resolution higher than that of the color camera and suitable for reading the postal information in the automatic reading devices; the color image produced in the relevant color camera is converted into a color image having a resolution lower than the camera resolution but sufficient far recognizing objects and their positions; the objects and their position present in the relevant lower resolution color image are determined and identified, the assignment of the objects to postal information categories being performed on the basis of structural rules established in an upstream teaching phase, and the required postal information in the gray level images of the relevant identified objects are automatically read.