Smartphone Document Aspect Ratio Detection via Focal Length Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately detect page aspect ratios from smartphone photographs due to varying camera view angles, focal lengths, and obstructions, especially in complex scenes with multiple documents or damaged images.
Innovation Solution
The system employs a Support Vector Regression model trained on a variety of document pages to estimate focal lengths and determine aspect ratios by identifying convex quadrangles, using linear projective mapping and generating additional quadrangles to account for camera distortions and view angles, with a tolerance-based acceptance mechanism for quad verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to detect page aspect ratios from smartphone photographs, then the detection process is simple, but the detection precision deteriorates due to varying camera view angles, focal lengths, and obstructions
Solution Approach 1:
The system performs preliminary actions by generating multiple candidate quadrangles in advance before final detection. It creates a set of potential page boundary quadrangles by varying vertex positions within tolerance ranges, then evaluates each candidate using projective mapping consistency checks. This preliminary generation and filtering approach enables accurate aspect ratio detection despite camera distortions, while maintaining computational efficiency through pre-computed reference quadrangles.
2Reliability
If multiple additional quadrangles are generated to account for camera distortions, then the detection reliability improves, but the computational complexity increases
Solution Approach 1:
The system applies parameter changes by systematically varying quadrangle vertex positions within predefined tolerance ranges to generate multiple candidate quadrangles. It changes the geometric parameters (vertex coordinates) to account for camera view angle variations and focal length differences. By evaluating projective mapping consistency across these parameter variations, the system achieves reliable detection while controlling computational load through bounded search spaces.
3Reliability
If a tolerance-based acceptance mechanism is used for quad verification, then the detection robustness improves against distorted images, but the processing time increases
Solution Approach 1:
The system applies local quality by implementing tolerance-based verification at critical decision points in the detection pipeline. It checks whether candidate quadrangles satisfy geometric consistency criteria within locally defined tolerance ranges, rather than applying uniform strict criteria throughout. This localized quality control approach maintains robustness against distortions while minimizing unnecessary processing of clearly invalid candidates, thus balancing reliability and processing efficiency.
Data Source
AI summary
Detecting an aspect ratio of an image captured with a smartphone includes detecting at least one convex quadrangle of arbitrary shape on the image and generating a plurality of additional convex quadrangles having vertices in a pre-determined vicinity of vertices of the quadrangle on the image. A linear projective mapping matrix is generated for mapping each of the quadrangle and the plurality of additional quadrangles onto a unit square. A plurality of estimated focal lengths of the camera of the smartphone is determined according to matrixes corresponding to the linear projective mappings onto a unit square of the quadrangle and each of the plurality of additional quadrangles. The quadrangle is used to determine the aspect ratio of the image in response to a range of the plurality of estimated focal lengths including a true value of the focal length of the camera of the smartphone.