1. [Publications](/publications)
2. Adaptive Segmentation based on a Learned Quality Metric
 
 # Adaptive Segmentation based on a Learned Quality Metric

  ![](/sites/default/files/styles/wide/public/pubs/2015-03_Adaptive-Segmentation-based/I.%20Frosio%20-%20Adaptive%20Segmentation%20Based%20on%20a%20Learned%20Quality%20Metric%20-%20Final.png?itok=gvXq_uN6)

 We introduce a model to evaluate the segmentation quality of a color image. The model parameters were learned from a set of examples. To this aim, we first segmented a set of images using a traditional graph-cut algorithm, for different values of the scale parameter. A human observer classified these images into three classes: under-, well- and over-segmented. We used such classification to learn the parameters of the segmentation quality model, that was then employed to automatically and adaptively optimize the scale parameter of the graph-cut segmentation algorithm. Experimental results show an improved segmentation quality for our algorithm based on the proposed segmentation quality model, which can be easily applied to a wide class of segmentation algorithms.



 ## Authors



[Iuri Frosio](/person/iuri-frosio)

Ed Ratner (Lyrical Labs)

 

 

 ## Publication Date



Sunday, March 1, 2015

 

 ## Published in



[Proceedings of the 10th International Conference on Computer Vision Theory and …](http://www.visapp.visigrapp.org/)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

 

 

 ## Uploaded Files



[VISAPP\_2015\_24\_CR.pdf](https://research.nvidia.com/sites/default/files/pubs/2015-03_Adaptive-Segmentation-based/VISAPP_2015_24_CR.pdf "Open file in new window")6.16 MB

[I. Frosio - Adaptive Segmentation Based on a Learned Quality Metric - VISAPP 2015.pptx](https://research.nvidia.com/sites/default/files/pubs/2015-03_Adaptive-Segmentation-based/I.%20Frosio%20-%20Adaptive%20Segmentation%20Based%20on%20a%20Learned%20Quality%20Metric%20-%20VISAPP%202015.pptx "Open file in new window")9.52 MB