Generalizing the Active Shape Model by Integrating Structural Knowledge to Recognize Hand Drawn Sketches

We propose a new deformable shape model Active Shape Structural Model (ASSM) for recognition and reconstruction. The main features of ASSM are: (1) It describes variations of shape not only statistically as Active shape/Appearance model but also by structural variations. (2) Statistical and structural prior knowledge is integrated resulting in a multi-resolution shape description such that the statistical variation becomes more constrained as structural information is added. Experiments on hand drawn sketches of mechanical systems using electronic ink demonstrate the ability of the deformable model to recognize objects structurally and reconstruct them statistically.

[1]  Josef Kittler,et al.  Robust and Efficient Shape Indexing through Curvature Scale Space , 1996, BMVC.

[2]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Joaquim A. Jorge,et al.  Using fuzzy logic to recognize geometric shapes interactively , 2000, Ninth IEEE International Conference on Fuzzy Systems. FUZZ- IEEE 2000 (Cat. No.00CH37063).

[4]  Richard Szeliski,et al.  Modeling surfaces of arbitrary topology with dynamic particles , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Dimitris N. Metaxas,et al.  Shape Evolution With Structural and Topological Changes Using Blending , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Takeo Kanade,et al.  3-D Deformable Registration of Medical Images Using a Statistical Atlas , 1999, MICCAI.

[7]  Daniel P. Lopresti,et al.  Feature-based approach for image retrieval by sketch , 1997, Other Conferences.

[8]  Sethuraman Panchanathan,et al.  Multimedia Storage and Archiving Systems III , 1998 .

[9]  Mark W. Newman,et al.  DENIM: finding a tighter fit between tools and practice for Web site design , 2000, CHI.

[10]  Computer-Assisted Intervention,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI’99 , 1999, Lecture Notes in Computer Science.

[11]  Takeo Kanade,et al.  3-d deformable registration using a statistical atlas with applications in medicine , 1999 .

[12]  Demetri Terzopoulos,et al.  Topology adaptive deformable surfaces for medical image volume segmentation , 1999, IEEE Transactions on Medical Imaging.

[13]  Klaus D. Tönnies,et al.  Extending Active Shape Models to Incorporate a-priori Knowledge about Structural Variability , 2002, DAGM-Symposium.

[14]  Milan Sonka,et al.  Time-continuous segmentation of cardiac MR image sequences using active appearance motion models , 2001, SPIE Medical Imaging.

[15]  Martin D. Levine,et al.  Segmenting 3D Objects into Geons , 1995, ICIAP.

[16]  Kaleem Siddiqi,et al.  A shock grammar for recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[18]  Remco C. Veltkamp,et al.  Content-based image retrieval systems: A survey , 2000 .