國立虎尾科技大學 |

Compassionately Conservative Normalized Cuts for Image Segmentation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Compassionately Conservative Normalized Cuts for Image Segmentation./
作者:	Hayes, Tyler L.
面頁冊數:	1 online resource (54 pages)
附註:	Source: Masters Abstracts International, Volume: 56-04.
Contained By:	Masters Abstracts International56-04(E).
標題:	Applied mathematics. -
電子資源:	click for full text (PQDT)
ISBN:	9781369770148

Compassionately Conservative Normalized Cuts for Image Segmentation.
Hayes, Tyler L.

Compassionately Conservative Normalized Cuts for Image Segmentation. - 1 online resource (54 pages)

Source: Masters Abstracts International, Volume: 56-04.

Thesis (M.S.)

Includes bibliographical references

This item is not available from ProQuest Dissertations & Theses.

Image segmentation is a process used in computer vision to partition an image into regions with similar characteristics. One category of image segmentation algorithms is graph-based, where pixels in an image are represented by vertices in a graph and the similarity between pixels is represented by weighted edges. A segmentation of the image can be found by cutting edges between dissimilar groups of pixels in the graph, leaving different clusters or partitions of the data.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369770148Subjects--Topical Terms:

1069907
Applied mathematics.
Index Terms--Genre/Form:

554714
Electronic books.

Compassionately Conservative Normalized Cuts for Image Segmentation.
LDR:03295ntm a2200397Ki 4500 001 910753
005 20180517112609.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369770148
035 $a (MiAaPQ)AAI10275700
035 $a (MiAaPQ)rit:12618
035 $a AAI10275700
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Hayes, Tyler L. $3 1182202
245 1 0 $a Compassionately Conservative Normalized Cuts for Image Segmentation.
264 0 $c 2017
300 $a 1 online resource (54 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 56-04.
500 $a Adviser: Nathan Cahill.
502 $a Thesis (M.S.) $c Rochester Institute of Technology $d 2017.
504 $a Includes bibliographical references
506 $a This item is not available from ProQuest Dissertations & Theses.
520 $a Image segmentation is a process used in computer vision to partition an image into regions with similar characteristics. One category of image segmentation algorithms is graph-based, where pixels in an image are represented by vertices in a graph and the similarity between pixels is represented by weighted edges. A segmentation of the image can be found by cutting edges between dissimilar groups of pixels in the graph, leaving different clusters or partitions of the data.
520 $a A popular graph-based method for segmenting images is the Normalized Cuts (NCuts) algorithm, which quantifies the cost for graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than unbalanced partitionings. This bias is so strong, however, that the NCuts algorithm avoids any singleton partitions, even when vertices are weakly connected to the rest of the graph. For this reason, we propose the Compassionately Conservative Normalized Cut (CCNCut) objective function, which strikes a better compromise between the desire to avoid too many singleton partitions and the notion that all partitions should be balanced.
520 $a We demonstrate how CCNCut minimization can be relaxed into the problem of computing Piecewise Flat Embeddings (PFE) and provide an overview of, as well as two efficiency improvements to, the Splitting Orthogonality Constraint (SOC) algorithm previously used to approximate PFE. We then present a new algorithm for computing PFE based on iteratively minimizing a sequence of reweighted Rayleigh quotients (IRRQ) and run a series of experiments to compare CCNCut-based image segmentation via SOC and IRRQ to NCut-based image segmentation on the BSDS500 dataset. Our results indicate that CCNCut-based image segmentation yields more accurate results with respect to ground truth than NCut-based segmentation, and IRRQ is less sensitive to initialization than SOC.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Applied mathematics. $3 1069907
650 4 $a Mathematics. $3 527692
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0364
690 $a 0405
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Rochester Institute of Technology. $b Applied Mathematics. $3 1182203
773 0 $t Masters Abstracts International $g 56-04(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10275700 $z click for full text (PQDT)