Barcode ROI Extraction Using Downsampling and Edge Detection

Solution Overview

Problem

Existing image processing systems for extracting computer readable codes from captured images of mailpieces or parcels are inefficient and resource-intensive, requiring significant computing power and memory to analyze entire images, which can be time-consuming and costly.

Innovation Solution

A system and method that utilizes downsampling and edge detection to identify and extract only the region of interest (ROI) containing the computer readable code, reducing image resolution and pixel size to simplify processing and reduce memory requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the entire captured image is processed to extract the computer readable code, then the code extraction is comprehensive and accurate, but the processing time and resource consumption increase significantly

Engineering Contradiction:

Improvecode extraction accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the image processing task into two phases: first, downsample the entire image to quickly locate the code region; second, process only the extracted code region at full resolution. This segmentation allows comprehensive code detection while minimizing processing time by avoiding full-resolution analysis of the entire image.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary downsampling and edge detection on the full image to identify and extract the code region before conducting the actual code extraction. This preliminary action reduces the subsequent processing scope to only the necessary code area, significantly reducing overall processing time while maintaining extraction accuracy.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If the entire captured image is processed to extract the computer readable code, then the code extraction is comprehensive and accurate, but the memory and computing resources required increase significantly

Engineering Contradiction:

Improvecode extraction accuracyVSAvoidcomputing resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the image processing task into two phases: first, downsample the entire image to quickly locate the code region; second, process only the extracted code region at full resolution. This segmentation allows comprehensive code detection while minimizing processing time by avoiding full-resolution analysis of the entire image.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary downsampling and edge detection on the full image to identify and extract the code region before conducting the actual code extraction. This preliminary action reduces the subsequent processing scope to only the necessary code area, significantly reducing overall processing time while maintaining extraction accuracy.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If the image resolution is reduced through downsampling, then the processing speed and resource efficiency improve, but the detection precision of the code edges may decrease

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidedge detection precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the image processing task into two phases: first, downsample the entire image to quickly locate the code region; second, process only the extracted code region at full resolution. This segmentation allows comprehensive code detection while minimizing processing time by avoiding full-resolution analysis of the entire image.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary downsampling and edge detection on the full image to identify and extract the code region before conducting the actual code extraction. This preliminary action reduces the subsequent processing scope to only the necessary code area, significantly reducing overall processing time while maintaining extraction accuracy.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12585905B2System and method for extracting a computer readable code from a captured image of a distribution item

Publication Date: 2026.03.24 US POSTAL SERVICE

AI summary

The present disclosure relates to a system and a method for extracting a computer readable code from a captured image of a mailpiece or parcel using downsampling and edge detection. The system can include a reader configured to capture an image of an item having a computer readable code positioned thereon and a processor in data communication with the reader. The processor can generate captured image data of the item including the computer readable code, downconvert the captured image data to generate a downconverted image data and detect an edge of the computer readable code. The processor can also identify a position of the computer readable code in the downconverted image data and store or process only the identified computer readable code.