A new approach to similarity retrieval of 2-D graphic objects based on dominant shapes

Abstract This new approach to content-based retrieval describes the contour of complex 2-D graphic object by recursively decomposing its shape into dominant and auxiliary components. One of the key ideas is extrapolation of fragments with associated primitive shapes into complete primitives in order to maximally preserve their semantics. The spatial relationships among these primitive shapes are represented via two set operators, i.e., spatial addition and subtraction . A multi-layer retrieval mechanism was devised to exploit the semantics captured in the resulting graph representation of a complex shape, thereby achieving greater efficiency and superior content-based recognition capabilities.

[1]  Shi-Kuo Chang,et al.  Iconic Indexing by 2-D Strings , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Benoit M. Macq,et al.  Morphological shape and region description , 1991, Signal Process..

[3]  P.W. Huang,et al.  Spatial reasoning and similarity retrieval for image database systems based on RS-strings , 1996, Pattern Recognit..

[4]  Wen-Hsiang Tsai,et al.  Attributed String Matching with Merging for Shape Recognition , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Karl Tombre,et al.  Celesstin: CAD conversion of mechanical drawings , 1992, Computer.

[6]  Maurice Maes,et al.  Polygonal shape recognition using string-matching techniques , 1991, Pattern Recognit..

[7]  Michael J. Pratt,et al.  Automated feature recognition from 2D drawings , 1993, Comput. Aided Des..

[8]  Theodosios Pavlidis,et al.  A review of algorithms for shape analysis , 1978 .

[9]  Suh-Yin Lee,et al.  Retrieval of similar pictures on pictorial databases , 1991, Pattern Recognit..

[10]  최종호,et al.  다중스캔 모드를 이용한 형태론적인 형상분해 ( Morphological Shape Decomposition using Multiscan Mode ) , 2000 .

[11]  Horst Bunke,et al.  Applications of approximate string matching to 2D shape recognition , 1993, Pattern Recognit..

[12]  Theodosios Pavlidis,et al.  Decomposition of Polygons into Simpler Components: Feature Generation for Syntactic Pattern Recognition , 1975, IEEE Transactions on Computers.

[13]  Jin-Jang Leou,et al.  New polygonal approximation schemes for object shape representation , 1993, Pattern Recognit..

[14]  Yuan Chen,et al.  Perfecting Vectorized Mechanical Drawings , 1996, Comput. Vis. Image Underst..

[15]  Aristides A. G. Requicha,et al.  Feature Recognition from CAD Models , 1998, IEEE Computer Graphics and Applications.

[16]  Joseph Ronsin,et al.  Shape decomposition and representation using a recursive morphological operation , 1995, Pattern Recognit..

[17]  SUH-YIN LEE,et al.  Spatial reasoning and similarity retrieval of images using 2D C-string knowledge representation , 1992, Pattern Recognit..