Retrieval of similar objects in simulation data using machine learning techniques

Comparing the output of a physics simulation with an experiment is often done by visually comparing the two outputs. In order to determine which simulation is a closer match to the experiment, more quantitative measures are needed. This paper describes our early experiences with this problem by considering the slightly simpler problem of finding objects in a image that are similar to a given query object. Focusing on a dataset from a fluid mixing problem, we report on our experiments using classification techniques from machine learning to retrieve the objects of interest in the simulation data. The early results reported in this paper suggest that machine learning techniques can retrieve more objects that are similar to the query than distance-based similarity methods.

[1]  John R. Smith,et al.  Comparing texture feature sets for retrieving core images in petroleum applications , 1998, Electronic Imaging.

[2]  George Karypis,et al.  Data Mining for Turbulent Flows , 2001 .

[3]  Vittorio Castelli,et al.  Image Databases: Search and Retrieval of Digital Imagery , 2002 .

[4]  R. Mukundan,et al.  Moment Functions in Image Analysis: Theory and Applications , 1998 .

[5]  Patty Kostkova,et al.  Special Issue on Digital Libraries , 2006, Health Informatics J..

[6]  Lambertus Hesselink,et al.  Representation and display of vector field topology in fluid flow data sets , 1989, Computer.

[7]  Chung-Sheng Li,et al.  Deriving texture feature set for content-based retrieval of satellite image database , 1997, Proceedings of International Conference on Image Processing.

[8]  Raghu Machiraju,et al.  A Novel Approach To Vortex Core Region Detection , 2002, VisSym.

[9]  D. Forsyth,et al.  Searching for Digital Pictures , 1997 .

[10]  Serge J. Belongie,et al.  Region-based image querying , 1997, 1997 Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries.

[11]  B. S. Manjunath,et al.  Introduction to MPEG-7: Multimedia Content Description Interface , 2002 .

[12]  Kwan-Liu Ma,et al.  3D shock wave visualization on unstructured grids , 1996, Proceedings of 1996 Symposium on Volume Visualization.

[13]  Hans-Peter Kriegel,et al.  State-of-the-Art in Content-Based Image and Video Retrieval , 2001, Computational Imaging and Vision.

[14]  B. S. Manjunath.  Image processing in the Alexandria Digital Library project , 1998, Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98-.

[15]  Christos Faloutsos,et al.  Searching Multimedia Databases by Content , 1996, Advances in Database Systems.

[16]  R. D. Richtmyer.  Taylor instability in shock acceleration of compressible fluids , 1960 .

[17]  Rainer Lienhart,et al.  Guest Editorial: Special Section on Storage, Processing, and Retrieval of Digital Media , 2001, J. Electronic Imaging.

[18]  Vittorio Castelli,et al.  Multidimensional Indexing Structures for Content‐Based Retrieval , 2002 .

[19]  E. Meshkov.  Instability of the interface of two gases accelerated by a shock wave , 1969 .

[20]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[21]  B. C. Curtis,et al.  Very High Resolution Simulation of Compressible Turbulence on the IBM-SP System , 1999, ACM/IEEE SC 1999 Conference (SC'99).

[22]  Bob Laramee.  Feature Extraction and Visualization of Flow Fields , 2002 .

[23]  HesselinkLambertus,et al.  Representation and Display of Vector Field Topology in Fluid Flow Data Sets , 1989 .

[24]  Azriel Rosenfeld,et al.  Content-Based Access to Multimedia Information: From Technology Trends to State of the Art , 1999 .

[25]  C. A. Zoldi.  A Numerical and Experimental Study of a Shock-Accelerated Heavy Gas Cylinder , 2002 .