Image segmentation: Difference between revisions

Revision as of 05:44, 18 July 2022

Revision as of 20:40, 27 August 2022

Line 5:

The result of image segmentation is a set of segments that collectively cover the entire image, or a set of [[Contour line|contour]]s extracted from the image (see [[edge detection]]). Each of the pixels in a region are similar with respect to some characteristic or computed property<ref>{{cite conference | last1=Nielsen | first1=Frank | last2=Nock | first2=Richard

| title=2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. |

|

titlechapter=On region merging: The statistical soundness of fast sorting, with applications |

publisher=IEEE | year=2003 | volume=2 | doi=10.1109/CVPR.2003.1211447 | pages=II:19–26 | isbn=0-7695-1900-8 }}</ref>

, such as [[color]], [[luminous intensity|intensity]], or [[Image texture|texture]]. Adjacent regions are significantly different color respect to the same characteristic(s).<ref name="computervision" /> When applied to a stack of images, typical in [[medical imaging]], the resulting contours after image segmentation can be used to create [[3D reconstruction]]s with the help of interpolation algorithms like [[marching cubes]].<ref>Zachow, Stefan, Michael Zilske, and Hans-Christian Hege. "[https://opus4.kobv.de/opus4-zib/files/1044/ZR_07_41.pdf 3D reconstruction of individual anatomy from medical image data: Segmentation and geometry processing]." (2007).</ref>

Line 19:

* [[Medical imaging]],<ref>{{cite journal | last1 = Pham | first1 = Dzung L. | last2 = Xu | first2 = Chenyang | last3 = Prince | first3 = Jerry L. | year = 2000 | title = Current Methods in Medical Image Segmentation | journal = Annual Review of Biomedical Engineering | volume = 2 | pages = 315–337 | pmid = 11701515 | doi = 10.1146/annurev.bioeng.2.1.315 }}</ref><ref>{{cite journal | last1 = Forghani| first1 = M. | last2 = Forouzanfar | first2 = M.| last3 = Teshnehlab| first3 = M. | year = 2010 | title = Parameter optimization of improved fuzzy c-means clustering algorithm for brain MR image segmentation | journal = Engineering Applications of Artificial Intelligence | volume = 23 | issue = 2 | pages = 160–168 | doi = 10.1016/j.engappai.2009.10.002 }}</ref> including [[volume rendering|volume rendered]] images from [[CT scan|computed tomography]] and [[magnetic resonance imaging]].

** Locate tumors and other pathologies<ref>W. Wu, A. Y. C. Chen, L. Zhao and J. J. Corso (2014): "[https://link.springer.com/article/10.1007/s11548-013-0922-7 Brain Tumor detection and segmentation in a CRF framework with pixel-pairwise affinity and super pixel-level features]", International Journal of Computer Aided Radiology and Surgery, pp. 241–253, Vol. 9.</ref><ref>E. B. George and M. Karnan (2012): "[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.411.7411&rep=rep1&type=pdf MR Brain image segmentation using Bacteria Foraging Optimization Algorithm]", ''International Journal of Engineering and Technology'', Vol. 4.</ref>

** Measure tissue volumes<ref>{{Cite journal |lastlast1=Ye |firstfirst1=Run Zhou |last2=Noll |first2=Christophe |last3=Richard |first3=Gabriel |last4=Lepage |first4=Martin |last5=Turcotte |first5=Éric E. |last6=Carpentier |first6=André C. |date=February 2022 |title=DeepImageTranslator: A free, user-friendly graphical interface for image translation using deep-learning and its applications in 3D CT image analysis |url=https://doi.org/10.1016/j.slast.2021.10.014 |journal=SLAS Technology |volume=27 |issue=1 |pages=76–84 |doi=10.1016/j.slast.2021.10.014 |pmid=35058205 |issn=2472-6303}}</ref><ref>{{Cite journal |lastlast1=Ye |firstfirst1=En Zhou |last2=Ye |first2=En Hui |last3=Bouthillier |first3=Maxime |last4=Ye |first4=Run Zhou |date=2022-02-18 |title=DeepImageTranslator V2: analysis of multimodal medical images using semantic segmentation maps generated through deep learning |url=https://www.biorxiv.org/content/10.1101/2021.10.12.464160v2 |language=en |pages=2021.10.12.464160 |doi=10.1101/2021.10.12.464160|s2cid=239012446 }}</ref>

** Diagnosis, study of anatomical structure<ref>{{cite journal|last1=Kamalakannan|first1=Sridharan|last2=Gururajan|first2=Arunkumar|last3=Sari-Sarraf|first3=Hamed|last4=Rodney|first4=Long|last5=Antani|first5=Sameer|title=Double-Edge Detection of Radiographic Lumbar Vertebrae Images Using Pressurized Open DGVF Snakes|journal=IEEE Transactions on Biomedical Engineering|date=17 February 2010|volume=57|issue=6|pages=1325–1334|doi=10.1109/tbme.2010.2040082|pmid=20172792|s2cid=12766600}}</ref>

** Surgery planning

Line 171:

\operatorname{argmin}_u \gamma \| \nabla u \|_0 + \int (u - f)^2 \, dx.

</math>

A minimizer <math>u^*</math> is a piecewise constant image which has an optimal tradeoff between the squared L2 distance to the given image <math>f</math> and the total length of its jump set. The jump set of <math>u^*</math> defines a segmentation. The relative weight of the energies is tuned by the parameter <math>\gamma >0 </math>. The binary variant of the Potts model, i.e., if the range of <math>u</math> is restricted to two values, is often called Chan-[[Luminița Vese|Vese]] model.<ref>{{cite journal | last1 = Chan | first1 = T.F. | last2 = Vese | first2 = L. | author2-link= Luminița Vese | year = 2001 | title = Active contours without edges | journal = IEEE Transactions on Image Processing | volume = 10 | issue = 2| pages = 266–277 | doi=10.1109/83.902291| pmid = 18249617 | bibcode = 2001ITIP...10..266C | s2cid = 7602622 }}</ref> An important generalization is the [[Mumford–Shah functional|Mumford-Shah model]]<ref>[[David Mumford]] and Jayant Shah (1989): [https://dash.harvard.edu/bitstream/handle/1/3637121/Mumford_OptimalApproxPiece.pdf?sequence=1 Optimal approximations by piecewise smooth functions and associated variational problems], ''Communications on Pure and Applied Mathematics'', pp 577–685, Vol. 42, No. 5</ref> given by

:<math>

\operatorname{argmin}_{u, K} \gamma |K| +

Line 325:

{{main|Object co-segmentation}}

Related images such as a photo album or a sequence of video frames often contain semantically similar objects and scenes, therefore it is often beneficial to exploit such correlations.<ref name="Vicente Rother Kolmogorov 2011 p. ">{{cite conference | last1=Vicente | first1=Sara | last2=Rother | first2=Carsten | last3=Kolmogorov | first3=Vladimir | title=CVPR 2011 | chapter=Object cosegmentation | publisher=IEEE | year=2011 | pages=2217–2224 | isbn=978-1-4577-0394-2 | doi=10.1109/cvpr.2011.5995530 }}</ref> The task of simultaneously segmenting scenes from related images or video frames is termed [[Object co-segmentation|co-segmentation]],<ref name="Liu Wang Hua Zhang 2018 pp. 5840–5853"/> which is typically used in [[Activity recognition|human action localization]]. Unlike conventional [[Minimum bounding box|bounding box]]-based [[object detection]], human action localization methods provide finer-grained results, typically per-image segmentation masks delineating the human object of interest and its action category (e.g., ''Segment-Tube''<ref name="Wang Duan Zhang Niu p=1657"/>). Techniques such as dynamic [[Markov random field|Markov Networks]], [[Convolutional neural network|CNN]] and [[Long short-term memory|LSTM]] are often employed to exploit the inter-frame correlations.

== Other methods ==