Learning to segment texture in 2D vs. 3D : a comparative study /

Bibliographic Details
Main Author: Oh, Se Jong, 1971-
Other Authors: Choe, Yoonsuck (Thesis advisor)
Format: Thesis eBook
Language:English
Published: [College Station, Tex.] : [Texas A & M University], [2004]
Subjects:
Online Access:Link to OAK Trust copy

MARC

Tag First Indicator Second Indicator Subfields
LEADER 00000cam a2200000Ka 4500
001 in00002014921
005 20151031160832.0
006 m f d
007 cr unu||||||||
008 050106s2004 txu obm 000 0 eng d
035 |a (OCoLC)ocm57374720 
035 |a (TxCM)etd-tamu-2004B-2-CPSC-Oh 
035 |a (OCoLC)57374720 
040 |a TXA  |c TXA  |d OCLCQ  |d TXA  |d UtOrBLW 
049 |a TXAM 
099 |a 2004  |a Thesis  |a O34 
100 1 |a Oh, Se Jong,  |d 1971- 
245 1 0 |a Learning to segment texture in 2D vs. 3D :  |b a comparative study /  |c by Se Jong Oh. 
264 1 |a [College Station, Tex.] :  |b [Texas A & M University],  |c [2004] 
300 |a 1 online resource. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
500 |a Vita. 
500 |a Abstract. 
500 |a "Major Subject: Computer Science" 
500 |a Title from author supplied metadata (automated record created on Oct. 15, 2004.) 
502 |b M.S.  |c Texas A & M University  |d 2004. 
504 |a Includes bibliographical references. 
516 |a Text (Thesis). 
520 3 |a Texture boundary detection (or segmentation) is an important capability of the human visual system. Usually, texture segmentation is viewed as a 2D problem, as the definition of the problem itself assumes a 2D substrate. However, an interesting hypothesis emerges when we ask a question regarding the nature of textures: What are textures, and why did the ability to discriminate texture evolve or develop? A possible answer to this question is that textures naturally define physically distinct surfaces or objects, thus, we can hypothesize that 2D texture segmentation may be an outgrowth of the ability to discriminate surfaces in 3D. In this thesis, I investigated the relative dificulty of learning to segment textures in 2D vs. 3D configurations. It turns out that learning is faster and more accurate in 3D, very much in line with what was expected. Furthermore, I have shown that the learned ability to segment texture in 3D transfers well into 2D texture segmentation, but not the other way around, bolstering the initial hypothesis, and providing an alternative approach to the texture segmentation problem. 
538 |a System requirements: Adobe Acrobat Reader. 
500 |a Electronic resource. 
650 4 |a Major computer science. 
653 |a visual perception 
653 |a texture segmentation 
653 |a texture boundary detection 
653 |a neural network 
700 1 |a Choe, Yoonsuck,  |e thesis advisor. 
856 4 0 |u http://hdl.handle.net/1969.1/1227  |z Link to OAK Trust copy  |t 0 
948 |a cataloged  |b h  |c 2005/1/7  |d o  |e bsurratt  |f 4:12:12 pm 
949 |a updated  |b h  |c 2011/1/19  |e mwilson  |f 12:29:55 pm 
994 |a C0  |b TXA 
999 |a MARS 
999 f f |s 01725c29-d2ea-393d-b969-09c5da3d1ba8  |i 1d6974fc-3b21-3b16-ac48-9c86b7b424cf  |t 0 
952 f f |a Texas A&M University  |b College Station  |c Electronic Resources  |d Available Online  |t 0  |e 2004 Thesis O34  |g Electronic  |h Other scheme 
998 f f |a 2004 Thesis O34  |t 0  |l Available Online