Auto Order Algorithm for Scanned Image Stitching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing scanner software requires user intervention to rotate and arrange scanned images of large documents into a complete image, as they often have different angles and scanning orders, which is time-consuming and inefficient.
Innovation Solution
A method that applies a gradient filter to scanned images, correlates them based on gradient values, and uses an exhaustive search to determine the optimal stitching order and rotation, automatically arranging images to achieve the best correlation values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If user manually rotates and arranges scanned images, then stitching accuracy is improved, but time consumption and operational complexity increase
Solution Approach 1:
The system automatically determines rotation angles and stitching order by computing correlation values between scanned images, eliminating the need for manual user intervention. The algorithm independently analyzes image correlations and self-configures the optimal arrangement, transforming a manual task into an autonomous process that maintains high accuracy while reducing time consumption.
Solution Approach 2:
The system changes the parameter of image arrangement from manual user control to automated algorithmic determination based on correlation values. By computing and comparing correlation parameters between multiple images, the system dynamically determines the optimal rotation and positioning parameters, achieving both speed and accuracy.
2Measurement precision
If user manually arranges scanned images in correct order, then stitching quality is improved, but ease of operation deteriorates
Solution Approach 1:
The stitching system performs self-service by automatically analyzing correlation values between scanned images and determining the correct arrangement order without requiring user knowledge or manual input. The algorithm independently evaluates all possible arrangements and selects the optimal one, making the system easy to operate while maintaining high stitching quality.
Solution Approach 2:
The manual mechanical process of dragging and dropping images into correct positions is replaced by an automated computational system that calculates correlation values and programmatically arranges images. This substitution transforms a complex manual operation into a simple automated process that achieves the same or better results.
3Measurement precision
If multiple scanned images are processed at full resolution, then image quality is maintained, but processing time and computational resources increase
Solution Approach 1:
The processing workflow is segmented into distinct stages: first, correlation analysis is performed on reduced-resolution thumbnail versions of scanned images to quickly determine the optimal arrangement order; second, once the arrangement is determined, the full-resolution images are stitched together using the pre-determined order. This segmentation allows computational-intensive correlation calculations to be performed on smaller data while preserving final output quality.
Solution Approach 2:
The system performs preliminary processing by determining the optimal stitching order and rotation angles using reduced-resolution images before committing to full-resolution processing. This preliminary arrangement determination prevents unnecessary full-resolution processing of incorrectly ordered images, significantly improving overall processing efficiency while maintaining final image quality.
Data Source
AI summary
A method is provided to automatically arrange scanned images so they can be stitched into a composite image. Initially the scanned images are reduced to low resolution and a gradient filter is applied. One scanned image is selected as a possible first image in a stitching order. The possible first image is rotated to one angle and correlated with remaining scanned images rotated to two corresponding angles. Only four scanned images that best correlate with the possible first image and pass a threshold are saved as possible second images in the order. The steps are repeated for subsequent places in the order and for the possible first image at other angles. The method is repeated for other possible first images to form other orders. At the end, a path through one of the orders that produces the best sum of correlation values is set as the correct stitching order.