TY - GEN
T1 - Improved stochastic modeling of shapes for content-based image retrieval
AU - Müller, Stefan
AU - Rigoll, Gerhard
N1 - Publisher Copyright:
© 1999 IEEE.
PY - 1999
Y1 - 1999
N2 - Recent advances in the stochastic modeling of shapes for content based image database retrieval are presented. These advances include an integrated approach to shape and color based retrieval, where the cues: color and shape, are both utilized in a local rather than a global way, as well as a novel deformation-tolerant method based on (pseudo-) two dimensional stochastic models. The stochastic modeling itself is based on the use of HMMs, whereas the feature extraction is a polar sampling technique which is also known as shape matrix. Previously, it was demonstrated that this combination of feature extraction and HMMs is able to perform an elastic matching, which is especially needed in sketch based image retrieval (S. Muller et al., 1998). The use of streams (sets of features that are assumed to be statistically independent) within the HMM framework allows the integration of shape and color derived features into a single model, thereby allowing one to control the influence of the different streams via stream weights. Furthermore, these stream weights can also be utilized in order to integrate weighting factors, which have been derived in the context of shape matrices, in order to achieve a more objective comparison between shapes. The weighting factors are based on the fact that the sampling density is not constant with the polar sampling raster.
AB - Recent advances in the stochastic modeling of shapes for content based image database retrieval are presented. These advances include an integrated approach to shape and color based retrieval, where the cues: color and shape, are both utilized in a local rather than a global way, as well as a novel deformation-tolerant method based on (pseudo-) two dimensional stochastic models. The stochastic modeling itself is based on the use of HMMs, whereas the feature extraction is a polar sampling technique which is also known as shape matrix. Previously, it was demonstrated that this combination of feature extraction and HMMs is able to perform an elastic matching, which is especially needed in sketch based image retrieval (S. Muller et al., 1998). The use of streams (sets of features that are assumed to be statistically independent) within the HMM framework allows the integration of shape and color derived features into a single model, thereby allowing one to control the influence of the different streams via stream weights. Furthermore, these stream weights can also be utilized in order to integrate weighting factors, which have been derived in the context of shape matrices, in order to achieve a more objective comparison between shapes. The weighting factors are based on the fact that the sampling density is not constant with the polar sampling raster.
UR - https://www.scopus.com/pages/publications/85001815961
U2 - 10.1109/IVL.1999.781118
DO - 10.1109/IVL.1999.781118
M3 - Conference contribution
AN - SCOPUS:85001815961
T3 - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 1999 - In conjunction with IEEE CVPR 1999
SP - 23
EP - 27
BT - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 1999 - In conjunction with IEEE CVPR 1999
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1999 IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 1999
Y2 - 22 June 1999
ER -