A classification-driven partially occluded object segmentation (CPOOS) method with application to chromosome analysis
Boaz Lerner, Hugo Guterman, Its'Hak Dinstein · IEEE Transactions on Signal Processing · 1998
Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modeling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analyzed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images.
Cited by 46 works. doi:10.1109/78.720391
Authors
References
- Neural networks for pattern recognition
- Neural Networks for Pattern Recognition
- On the Recognition of Printed Characters of Any Font and Size
- Partial shape recognition: a landmark-based approach
- Toward a completely automatic neural-network-based human chromosome analysis
- Geometric separation of partially overlapping nonrigid objects applied to automatic chromosome classification
- Fully automatic chromosome segmentation