MSER and SIMSER Regions
Autor: | Andrzej Śluzek |
---|---|
Rok vydání: | 2017 |
Předmět: |
Segmentation-based object categorization
Machine vision business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation 020206 networking & telecommunications Pattern recognition 02 engineering and technology Image segmentation 020303 mechanical engineering & transports Geography 0203 mechanical engineering Salient 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Segmentation Computer vision Artificial intelligence Focus (optics) business |
Zdroj: | Proceedings of the 2017 International Conference on Computer Graphics and Digital Image Processing. |
Popis: | In this paper, the concept of using salient regions (MSER and SIMSER features) for image segmentation is revised and evaluated. Although we focus on the foreground-background segmentation (which plays an important role of many machine vision problems) the presented results and conclusions are also applicable to more general tasks of segmentation. It is shown that standard MSER features do not provide satisfactory performances in typical segmentation problems, while SIMSER features (which are fully scale-invariant modifications of MSERs) are a more promising tool, with only marginally higher computational costs than MSERs. The presented conclusions are illustrated by exemplary results on a challenging benchmark dataset. |
Databáze: | OpenAIRE |
Externí odkaz: |