190 likes | 371 Views
Feng Ge Computer Science and Engineering, USC. Edge Detection Evaluation in Boundary Detection Framework. Edge Detection Error. Edge detection Detect pixels with strong gradient of “gray-level” Error False negative(Missing ): Not detected Edges False positive: detected false edges
E N D
Feng Ge Computer Science and Engineering, USC Edge Detection Evaluation in Boundary Detection Framework
Edge Detection Error • Edge detection Detect pixels with strong gradient of “gray-level” • Error • False negative(Missing ): Not detected Edges • False positive: detected false edges • Orientation error: shift from real position • Dislocation error: shift from real direction • How to evaluate these errors?
Evaluation Criteria • Ground Truth • Human or predefined results? • Quantificaition • Measuring and expressing in number means good. • Generality • Real images in large number Combined 3 criteria are good evaluation methods!
Overview • Subjective vs Objective • Human vision checking • Quantitative measurement • With ground truth vs Without • Standard for evaluation • Some characters,e.g, continuation,coherence. • Synthetic vs Real images • Simple structure • Complicated structures
Motive—in boundary detection framework • Problem: Boundary detection algorithms work well in synthetic data, while poorly in real images • This gap,we believe, is largely introduced by edge detection
Experiment Settings: Image Database • Large: 1030 images • Generality • Unambiguous • Manually extracted ground truth
Experiment Settings: Detectors • Edge & Line Detector: Canny & Line Approximation • Boundary detector: Ratio-Contour
Experiment • Original imagesimage->edge->fragments->bounday->evaluation • Synthetic imagestexture images->fragments --->bounday->evaluation ground truth->adding noise • Semi-synthetic images original images->background -->bounday->evaluation ground truth->adding noise
Experiment --Synthetic images • Result • Much better than original images • Problem • Background correlation changed • Irregular background in texture images
Experiment –Semi-synthetic images • Edge-map error analysis • Model simulation
Result-1 Procedure: Sample ground truth, random delete some percentage of fragments • Simulate edge missing
Result-2 • Simulate edge detection error: missing & dislocation • Fix dislocation error, vary missing rate (a) • Fix missing error, vary dislocation error (b) (a) (b)
Conclusion • Our noise model is close to real edge error, as regarding to the simulated result • Edge missing and dislocation are mainly encountered errors in edge detection. • Edge dislocation is more crucial in edge error compared with missing error
Discussion-1 • Error introduced by line detection
Discussion-2 • Model error • Gaussian distribution assumption • Based on boundary detection • Globally, not locally • Introduce some error, but statistically, reasonable • Image database • Low resolution • Ground truth error
Future work • Distinguish errors introduced by line approximation from edge detection • Noise model refinement • Substitute line with curve in edge-map approximation • Data base improvement