國立虎尾科技大學 |

Computational Modeling and Psychophysics in Low- and Mid-Level Vision.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Computational Modeling and Psychophysics in Low- and Mid-Level Vision./
作者:	Hou, Xiaodi.
面頁冊數:	1 online resource (125 pages)
附註:	Source: Dissertation Abstracts International, Volume: 75-10(E), Section: B.
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9781303946592

Computational Modeling and Psychophysics in Low- and Mid-Level Vision.
Hou, Xiaodi.

Computational Modeling and Psychophysics in Low- and Mid-Level Vision. - 1 online resource (125 pages)

Source: Dissertation Abstracts International, Volume: 75-10(E), Section: B.

Thesis (Ph.D.)--California Institute of Technology, 2014.

Includes bibliographical references

This thesis addresses a series of topics related to the question of how people find the foreground objects from complex scenes. With both computer vision modeling, as well as psychophysical analyses, we explore the computational principles for low- and mid-level vision.

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

Mode of access: World Wide Web

ISBN: 9781303946592Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Computational Modeling and Psychophysics in Low- and Mid-Level Vision.
LDR:03642ntm a2200361K 4500 001 913734
005 20180622095236.5
006 m o u
007 cr mn||||a|a||
008 190606s2014 xx obm 000 0 eng d
020 $a 9781303946592
035 $a (MiAaPQ)AAI3622737
035 $a (MiAaPQ)caltech:11223
035 $a AAI3622737
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Hou, Xiaodi. $3 1186689
245 1 0 $a Computational Modeling and Psychophysics in Low- and Mid-Level Vision.
264 0 $c 2014
300 $a 1 online resource (125 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: Dissertation Abstracts International, Volume: 75-10(E), Section: B.
500 $a Adviser: Christof Koch.
502 $a Thesis (Ph.D.)--California Institute of Technology, 2014.
504 $a Includes bibliographical references
520 $a This thesis addresses a series of topics related to the question of how people find the foreground objects from complex scenes. With both computer vision modeling, as well as psychophysical analyses, we explore the computational principles for low- and mid-level vision.
520 $a We first explore the computational methods of generating saliency maps from images and image sequences. We propose an extremely fast algorithm called Image Signature that detects the locations in the image that attract human eye gazes. With a series of experimental validations based on human behavioral data collected from various psychophysical experiments, we conclude that the Image Signature and its spatial-temporal extension, the Phase Discrepancy, are among the most accurate algorithms for saliency detection under various conditions.
520 $a In the second part, we bridge the gap between fixation prediction and salient object segmentation with two efforts. First, we propose a new dataset that contains both fixation and object segmentation information. By simultaneously presenting the two types of human data in the same dataset, we are able to analyze their intrinsic connection, as well as understanding the drawbacks of today's "standard" but inappropriately labeled salient object segmentation dataset. Second, we also propose an algorithm of salient object segmentation. Based on our novel discoveries on the connections of fixation data and salient object segmentation data, our model significantly outperforms all existing models on all 3 datasets with large margins.
520 $a In the third part of the thesis, we discuss topics around the human factors of boundary analysis. Closely related to salient object segmentation, boundary analysis focuses on delimiting the local contours of an object. We identify the potential pitfalls of algorithm evaluation for the problem of boundary detection. Our analysis indicates that today's popular boundary detection datasets contain significant level of noise, which may severely influence the benchmarking results. To give further insights on the labeling process, we propose a model to characterize the principles of the human factors during the labeling process. The analyses reported in this thesis offer new perspectives to a series of interrelating issues in low- and mid-level vision. It gives warning signs to some of today's "standard" procedures, while proposing new directions to encourage future research.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a California Institute of Technology. $b Computation and Neural Systems. $3 1186690
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3622737 $z click for full text (PQDT)