Image segmentation based on merging of sub-optimal segmentations

Pichel, Juan C.; Singh, David E.; Rivera, Francisco F.

doi:10.1016/j.patrec.2005.12.012

Cited by 45 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It would be preferable to have a self-tunable segmentation method that could dynamically adjust the segmentation algorithm's parameters in order to automatically determine the parameter options that generate better results. Pichel et al [71] recently proposed one such system, which uses unsupervised evaluation methods to evaluate and merge suboptimal segmentation results in order to generate the final segmentation. Supervised segmentation evaluation methods only enable this capability on images for which a manually-segmented reference image already exists.…”

Section: Introductionmentioning

confidence: 99%

Image segmentation evaluation: A survey of unsupervised methods

Hui¹,

Fritts²,

Goldman³

2008

Computer Vision and Image Understanding

836

469

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Image segmentation evaluation: A survey of unsupervised methods

Hui¹,

Fritts²,

Goldman³

2008

Computer Vision and Image Understanding

836

469

View full text Add to dashboard Cite

“…BISP3D uses Two_phase I/O in order to write its results into a file. -PSRG: It is a parallel segmentation tool that processes grey-scale images [41].…”

Section: Evaluationsmentioning

confidence: 99%

Dynamic-CoMPI: dynamic optimization techniques for MPI parallel applications

et al. 2010

Self Cite

View full text Add to dashboard Cite

This work presents an optimization of MPI communications, called Dynamic-CoMPI, which uses two techniques in order to reduce the impact of communications and non-contiguous I/O requests in parallel applications. These techniques are independent of the application and complementaries to each other. The first technique is an optimization of the Two-Phase collective I/O technique from ROMIO, called Locality aware strategy for Two-Phase I/O (LA-Two-Phase I/O). In order to increase the locality of the file accesses, LA-Two-Phase I/O employs the Linear Assignment Problem (LAP) for finding an optimal I/O data communication schedule. The main purpose of this technique is the reduction of the number of communications involved in the I/O collective operation. The second technique, calledAdaptive-CoMPI, is based on run-time compression of MPI messages exchanged by applications. Both techniques can be applied on every application, because both of them are transparent for the users. Dynamic-CoMPI has been validated by using several MPI benchmarks and real HPC applications. The results show that, for many of the considered scenarios, important reductions in the execution time are achieved by reducing the size and the number of the messages. Additional benefits of our approach are the reduction of the total communication time and the network contention, thus enhancing, not only performance, but also scalability.

show abstract

“…The over-segmentation phenomenon relates to the creation of small non-representative basins. To solve this problem, a region-merging algorithm is commonly applied after watershed segmentation (Haris et al, 1998;Patino, 2005;Pichel et al, 2006). Another way to limit the oversegmentation phenomenon is to initiate relevant basin seeds (Meyer and Beucher, 1990).…”

Section: Theorymentioning

confidence: 99%

Management zone delineation using a modified watershed algorithm

Roudier¹,

Tisseyre

Poilvé³

et al. 2008

Precision Agric

View full text Add to dashboard Cite

Site-specific management (SSM) is a common way to manage within-field variability. This concept divides fields into site-specific management zones (SSMZ) according to one or several soil or crop characteristics. This paper proposes an original methodology for SSMZ delineation which is able to manage different kinds of crop and/or soil images using a powerful segmentation tool: the watershed algorithm. This image analysis algorithm was adapted to the specific constraints of precision agriculture. The algorithm was tested on high-resolution bio-physical images of a set of fields in France.

show abstract

Image segmentation based on merging of sub-optimal segmentations

Cited by 45 publications

References 18 publications

Image segmentation evaluation: A survey of unsupervised methods

Image segmentation evaluation: A survey of unsupervised methods

Dynamic-CoMPI: dynamic optimization techniques for MPI parallel applications

Management zone delineation using a modified watershed algorithm

Contact Info

Product

Resources

About