TY - JOUR
T1 - Shape from Texture
T2 - Integrating Texture-Element Extraction and Surface Estimation
AU - Blostein, Dorothea
AU - Ahuja, Narendra
N1 - Funding Information:
Manuscript received September 15, 1988; revised January 30, 1989. Recommended for acceptance by A. K. Jain. This work was supported by the Air Force Office of Scientific Research under Grant AFOSR 86-0009 and by the Eastman Kodak Company.
PY - 1989/12
Y1 - 1989/12
N2 - A perspective view of a slanted textured surface shows systematic changes in the density, area, and aspect-ratio of texture elements. These apparent changes in texture element properties can be analyzed to recover information about the physical layout of the scene. However, in practice it is difficult to identify texture elements, especially in images where the texture elements are partially occluded or are themselves textured at a finer scale. To solve this problem, it is necessary to integrate the extraction of texture elements with the recognition of scene layout. We present a method for identifying texture elements while simultaneously recovering the orientation of textured surfaces. A multiscale region detector, based on measurements in a V2G (Laplacian-of-Gaussian) scale-space, is used to construct a set of candidate texture elements. True texture elements are selected from the set of candidate texture elements by finding the planar surface that best predicts the observed areas of the candidate texture elements. Results are shown for a variety of natural textures, including waves, flowers, rocks, clouds, and dirt clods.
AB - A perspective view of a slanted textured surface shows systematic changes in the density, area, and aspect-ratio of texture elements. These apparent changes in texture element properties can be analyzed to recover information about the physical layout of the scene. However, in practice it is difficult to identify texture elements, especially in images where the texture elements are partially occluded or are themselves textured at a finer scale. To solve this problem, it is necessary to integrate the extraction of texture elements with the recognition of scene layout. We present a method for identifying texture elements while simultaneously recovering the orientation of textured surfaces. A multiscale region detector, based on measurements in a V2G (Laplacian-of-Gaussian) scale-space, is used to construct a set of candidate texture elements. True texture elements are selected from the set of candidate texture elements by finding the planar surface that best predicts the observed areas of the candidate texture elements. Results are shown for a variety of natural textures, including waves, flowers, rocks, clouds, and dirt clods.
UR - http://www.scopus.com/inward/record.url?scp=0024922822&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0024922822&partnerID=8YFLogxK
U2 - 10.1109/34.41363
DO - 10.1109/34.41363
M3 - Article
AN - SCOPUS:0024922822
VL - 11
SP - 1233
EP - 1251
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 12
ER -