Integration of Multiple Cues in Shape from Texture

Hiroyuki UMEMURA; Toshio INUI

Integration of Multiple Cues in Shape from Texture

Hiroyuki UMEMURA, Toshio INUI

Full Text Views

0

Cite this

Summary :

Texture has been investigated as a cue for reconstructing 3-D structure. There are various textures in a natural scene. In this paper, the regularity of alignment of texture elements was manipulated to investigate its effect on human perception. The results show that the regularity affects human perception when only the texel density gradient is given as cue or the density cue is inconsistent with the compression cue. We introduce a model based on a MAP estimation to account for the result from a viewpoint of an integration of 3-D cues. The model simultaneously estimates texture properties and 3-D surface orientation by using prior knowledge about texture and 3-D surface. The performance of the model accounts for the experimental result well.

Publication: IEICE TRANSACTIONS on Information Vol.E82-D No.8 pp.1228-1236

Publication Date: 1999/08/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Medical Electronics and Medical Information

Cite this

Copy

Hiroyuki UMEMURA, Toshio INUI, "Integration of Multiple Cues in Shape from Texture" in IEICE TRANSACTIONS on Information, vol. E82-D, no. 8, pp. 1228-1236, August 1999, doi: .
Abstract: Texture has been investigated as a cue for reconstructing 3-D structure. There are various textures in a natural scene. In this paper, the regularity of alignment of texture elements was manipulated to investigate its effect on human perception. The results show that the regularity affects human perception when only the texel density gradient is given as cue or the density cue is inconsistent with the compression cue. We introduce a model based on a MAP estimation to account for the result from a viewpoint of an integration of 3-D cues. The model simultaneously estimates texture properties and 3-D surface orientation by using prior knowledge about texture and 3-D surface. The performance of the model accounts for the experimental result well.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_8_1228/_p

Copy

@ARTICLE{e82-d_8_1228,
author={Hiroyuki UMEMURA, Toshio INUI, },
journal={IEICE TRANSACTIONS on Information},
title={Integration of Multiple Cues in Shape from Texture},
year={1999},
volume={E82-D},
number={8},
pages={1228-1236},
abstract={Texture has been investigated as a cue for reconstructing 3-D structure. There are various textures in a natural scene. In this paper, the regularity of alignment of texture elements was manipulated to investigate its effect on human perception. The results show that the regularity affects human perception when only the texel density gradient is given as cue or the density cue is inconsistent with the compression cue. We introduce a model based on a MAP estimation to account for the result from a viewpoint of an integration of 3-D cues. The model simultaneously estimates texture properties and 3-D surface orientation by using prior knowledge about texture and 3-D surface. The performance of the model accounts for the experimental result well.},
keywords={},
doi={},
ISSN={},
month={August},}

Copy

TY - JOUR
TI - Integration of Multiple Cues in Shape from Texture
T2 - IEICE TRANSACTIONS on Information
SP - 1228
EP - 1236
AU - Hiroyuki UMEMURA
AU - Toshio INUI
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 1999
AB - Texture has been investigated as a cue for reconstructing 3-D structure. There are various textures in a natural scene. In this paper, the regularity of alignment of texture elements was manipulated to investigate its effect on human perception. The results show that the regularity affects human perception when only the texel density gradient is given as cue or the density cue is inconsistent with the compression cue. We introduce a model based on a MAP estimation to account for the result from a viewpoint of an integration of 3-D cues. The model simultaneously estimates texture properties and 3-D surface orientation by using prior knowledge about texture and 3-D surface. The performance of the model accounts for the experimental result well.
ER -