MOTION & VISION   -  Vision Cards

eVision Application Libraries
 

Based on a feature point technology, EasyFind is designed to find one or more occurrences of a given pattern in a larger image, featuring fast processing and improved robustness compared to classical algorithms. EasyFind has a high tolerance to pattern degradation due to noise, blur, occlusion, missing parts, varying illumination conditions.

With an adjustable accuracy up to sub-pixel level, EasyFind provides a very precise, rotation and scaling invariant, alignment. It supports don’t care areas. This feature allows creating complex pattern shapes.

EasyFind is easily integrated into any application, requiring no knowledge of machine vision concepts.

Feature point technology
Feature-point-based means that EasyFind, instead of comparing the pattern to the sample image pixel-wise, carefully selects salient features in the pattern, so that it only matches the areas that convey information. This allows faster processing and improves robustness.

Typical performance figures
These performances are calculated finding a contrasted pattern 150x150 pixels large (interpolation enabled).

Translation: 3-sigma static repeatability: 1/75th of a pixel Linearity: 1/30th of a pixel Rotation: 3-sigma static repeatability: insignificant Linearity: 1/4 degree Scaling: 3-sigma static repeatability: insignificant Linearity: 1/2 percent