A Comparison of Text and Shape Matching for Retrieval of Online 3 D Models with statistical significance testing

Because of recent advances in graphics hard- and software, both the production and use of 3D models are increasing at a rapid pace. As a result, a large number of 3D models have become available on the web, and new research is being done on 3D model retrieval methods. Query and retrieval can be done solely based on associated text, as in image retrieval, for example (e.g. Google Image Search [1] and [2,3]). Other research focuses on shape-based retrieval, based on methods that measure shape similarity between 3D models (e.g., [4]). The goal of our work is to take current text- and shape-based matching methods, see which ones perform best, and compare those. We compared four text matching methods and four shape matching methods, by running classification tests using a large database of 3D models downloaded from the web [5]. In addition, we investigated several methods to combine the results of text and shape matching. We found that shape matching outperforms text matching in all our experiments. The main reason is that publishers of online 3D models simply do not provide enough descriptive text of sufficient quality: 3D models generally appear in lists on web pages, annotated only with cryptic filenames or thumbnail images. Combining the results of text and shape matching further improved performance. The results of this paper provide added incentive to continue research in shape-based retrieval methods for 3D models, as well as retrieval based on other attributes.

[1]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Gerard Salton,et al.  Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer , 1989 .

[3]  Gerard Salton,et al.  The SMART Retrieval System , 1971 .

[4]  C. J. van Rijsbergen,et al.  Information Retrieval , 1979, Encyclopedia of GIS.

[5]  Remco C. Veltkamp,et al.  A Survey of Content Based 3D Shape Retrieval Methods , 2004, SMI.

[6]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[7]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[8]  M. T. Suzuki,et al.  A Web-based retrieval system for 3D polygonal models , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[9]  J. Filliben.  The Probability Plot Correlation Coefficient Test for Normality , 1975 .

[10]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[11]  Manuel de Buenaga Rodríguez,et al.  Using WordNet to Complement Training Information in Text Categorization , 1997, ArXiv.

[12]  Ming Ouhyoung,et al.  On Visual Similarity Based 3D Model Retrieval , 2003, Comput. Graph. Forum.

[13]  Steven Salzberg,et al.  On Comparing Classifiers: Pitfalls to Avoid and a Recommended Approach , 1997, Data Mining and Knowledge Discovery.

[14]  Rohini K. Srihari,et al.  Automatic Indexing and Content-Based Retrieval of Captioned Images , 1995, Computer.

[15]  Thomas R. Knapp,et al.  Comments on the Statistical Significance Testing Articles , 1998 .

[16]  John R. Smith,et al.  Searching for Images and Videos on the World-Wide Web , 1999 .

[17]  T. M. Murali,et al.  Consistent solid and boundary representations from arbitrary polygonal data , 1997, SI3D.

[18]  Marcel Worring,et al.  Multimodal Video Indexing : A Review of the State-ofthe-art , 2001 .

[19]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[20]  Sven J. Dickinson,et al.  Skeleton based shape matching and retrieval , 2003, 2003 Shape Modeling International..

[21]  Kenneth Ward Church,et al.  NLP Found Helpful (at least for one Text Categorization Task) , 2002, EMNLP.

[22]  Kathleen R. McKeown,et al.  Robust statistical techniques for the categorization of images using associated text , 2003 .

[23]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR '00.

[24]  G. Taubin,et al.  Object recognition based on moment (or algebraic) invariants , 1992 .

[25]  B. Kimia,et al.  3D object recognition using shape similiarity-based aspect graph , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[26]  Shih-Fu Chang,et al.  Semantic knowledge construction from annotated image collections , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[27]  J. I.  The Design of Experiments , 1936, Nature.

[28]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[29]  Sven Loncaric,et al.  A survey of shape analysis techniques , 1998, Pattern Recognit..

[30]  Dejan V. VraniC.  An improvement of rotation invariant 3D-shape based on functions on concentric spheres , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[31]  David P. Dobkin,et al.  A search engine for 3D models , 2003, TOGS.

[32]  Stan Matwin,et al.  Text Classification Using WordNet Hypernyms , 1998, WordNet@ACL/COLING.

[33]  Thomas A. Funkhouser,et al.  Early experiences with a 3D model search engine , 2003, Web3D '03.

[34]  Neil A. Thacker,et al.  Robust Recognition of Scaled Shapes using Pairwise Geometric Histograms , 1995, BMVC.

[35]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[36]  Shih-Fu Chang,et al.  Integration of Visual and Text-Based Approaches for the Content Labeling and Classification of Photographs , 1999, SIGIR 1999.

[37]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark (Figures 1 and 2) , 2004, Shape Modeling International Conference.

[38]  Ming Ouhyoung,et al.  A 3D Object Retrieval System Based on Multi-Resolution Reeb Graph , 2002 .

[39]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[40]  Vasileios Hatzivassiloglou,et al.  Text-Based Approaches for the Categorization of Images , 1999, ECDL.

[41]  Benjamin B. Kimia,et al.  3D Object Recognition Using Shape Similarity-Based Aspect Graph , 2001, ICCV.

[42]  David A. Hull.  Using statistical testing in the evaluation of retrieval experiments , 1993, SIGIR.

[43]  Gabriel Taubin,et al.  Converting sets of polygons to manifold surfaces by cutting and stitching , 1998, Proceedings Visualization '98 (Cat. No.98CB36276).

[44]  Nicu Sebe,et al.  How to complete performance graphs in content-based image retrieval: add generality and normalize scope , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Szymon Rusinkiewicz,et al.  Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[46]  Emanuele Trucco,et al.  Geometric Invariance in Computer Vision , 1995 .

[47]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[48]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[49]  John M. Chambers,et al.  Graphical Methods for Data Analysis , 1983 .

[50]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[51]  Marco La Cascia,et al.  Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web , 1999, Comput. Vis. Image Underst..

[52]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.