Learning to segment texture in 2D vs. 3D : A comparative study
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 de?nition 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 de?ne 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 di?culty of learning to segment textures in 2D vs. 3D con?gurations. 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.
Advisor:Choe, Yoonsuck; Gutierrez-Osuna, Ricardo; Yamauchi, Takashi
School:Texas A&M University
School Location:USA - Texas
Source Type:Master's Thesis
Keywords:visual perception texture segmentation boundary detection neural network
Date of Publication:08/01/2004