Polygon Detection via Side Length Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting polygons from images face difficulties in accurately identifying polygons resembling a reference polygon due to the large number of combinations of feature points, especially when similar features exist, making it challenging to distinguish the intended polygon.
Innovation Solution
A polygon detection device that acquires the ratio of side lengths of a reference polygon, detects line segments from an image, forms polygons based on these segments, and identifies the corresponding polygon by comparing the similarity in side length ratios, using techniques such as grouping line segments by angle and weighting similarity scores to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional feature point extraction methods are used, then all feature points are detected from the image, but the number of combinations of polygon vertex candidates becomes enormous making it difficult to detect the target polygon
Solution Approach 1:
The patent segments the polygon detection process into distinct stages: line segment detection from the image, grouping line segments by angle, forming candidate polygons from grouped segments, and finally identifying the target polygon through ratio comparison. This segmentation reduces the computational complexity by breaking down the overwhelming task of evaluating all feature point combinations into manageable sequential steps.
Solution Approach 2:
The patent performs preliminary actions by detecting line segments and grouping them by angle before forming candidate polygons. By pre-organizing line segments into angle groups and calculating their ratios in advance, the system reduces the computational burden during the final polygon identification stage, avoiding the need to evaluate all possible feature point combinations.
2Reliability
If all combinations of feature points are evaluated, then no polygon is missed, but the detection time becomes excessively long
Solution Approach 1:
The patent applies local quality by focusing computational resources on specific regions and patterns that are more likely to contain the target polygon. By grouping line segments by angle and forming candidate polygons only from these grouped segments, the system concentrates computation on promising candidates rather than uniformly evaluating all feature point combinations, thus reducing detection time while maintaining reliability.
Solution Approach 2:
The patent changes parameters by using angle as a grouping criterion for line segments and by utilizing the ratio of lengths of two sides as a discriminative parameter for identifying the target polygon. These parameter changes enable the system to efficiently filter candidate polygons and identify the target without evaluating all possible combinations, significantly reducing detection time while maintaining high reliability.
3Adaptability or versatility
If similar feature points exist in the image, then more candidate polygons are generated, but it becomes difficult to distinguish the intended polygon from others
Solution Approach 1:
The patent changes the discriminative parameter from simple geometric properties to the ratio of lengths of two sides of the polygon. This parameter change enables effective distinction between similar polygons, as the ratio provides a unique characteristic that can differentiate the target polygon from other candidates even when they have similar overall shapes and sizes.
Solution Approach 2:
The patent implements feedback by comparing the ratio of line segment lengths against the ratio of polygon side lengths to identify the target polygon. This feedback mechanism allows the system to iteratively refine its identification by checking whether candidate polygons match the expected ratio characteristics, enabling accurate distinction among similar feature points.
Data Source
AI summary
An object is to provide a polygon detection device, a polygon detection method, and a polygon detection program to accurately detect a polygon resembling a reference polygon from an image.The polygon detection device acquires a ratio among lengths of sides of a reference polygon included in an appearance of a predetermined object. The polygon detection device acquires a photographic image of the predetermined object. The polygon detection device detects line segments from the acquired photographic image. The polygon detection device forms at least one polygon based on the detected line segments. The polygon detection device identifies, from the formed polygon, a polygon corresponding to the reference polygon based on a degree of similarity between a ratio among lengths of sides of the formed polygon and the acquired ratio among the lengths of sides of the reference polygon, among from the formed polygon.