Abstract
In order to find better simplicity measurements for 3D object recognition, a new set of local regularities is developed and tested in a stepwise 3D reconstruction method, including localized minimizing standard deviation of angles(L-MSDA), localized minimizing standard deviation of segment magnitudes(L-MSDSM), localized minimum standard deviation of areas of child faces (L-MSDAF), localized minimum sum of segment magnitudes of common edges (L-MSSM), and localized minimum sum of areas of child face (L-MSAF). Based on their effectiveness measurements in terms of form and size distortions, it is found that when two local regularities: L-MSDA and L-MSDSM are combined together, they can produce better performance. In addition, the best weightings for them to work together are identified as 10% for L-MSDSM and 90% for L-MSDA. The test results show that the combined usage of L-MSDA and L-MSDSM with identified weightings has a potential to be applied in other optimization based 3D recognition methods to improve their efficacy and robustness.
Similar content being viewed by others
References
YANG L J, LIU J Z, TANG X O. Complex 3D general object reconstruction from line drawings[C]//IEEE international conference on computer vision(ICCV), Sydney, Australia, Dec 1–8, 2013: 1433–1440.
ZOU C Q, YANG H, LIU J Z. Separation of line drawings based on split faces for 3D object reconstruction[C]//IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, Jun 23–28, 2014: 692–699.
ZHANG J, WANG Y, TANG Z. Recovering solid geometric object from single line drawing image[J]. Multimedia Tools and Application, 2015, DOI: DOI 10.1007/s11042-015-2966-x.
QIN S F, WRIGHT D K, JORDANOY I N. On-line segmentation of freehand sketches by knowledge-based nonlinear thresholding operations[J]. Pattern Recognition, 2001, 34(10): 1885–1893.
WANG S, QIN S, GAO M. New grouping and fitting methods for interactive overtraced sketches[J]. Visual Computer International Journal of Computer Graphics, 2014, 30(3): 285–297.
MAINI R, AGGARWAL H. Study and comparison of various image edge detection techniques[J]. International Journal of Image Processing, 2009, 3(1): 1–11.
LIU J, CHEN Y X. TANG X. Decomposition of complex line drawings with hidden lines for 3d planar-faced manifold object reconstruction[J]. IEEE T-PAMI, 2011, 33(1): 3–15.
QIN S, TIAN H W. On the algorithm for reconstruction of polyhedral objects from a single line drawing[C]//International Conference on Automation and Computing, IEEE, 2015.
SUGIHARA K. Resolvable representations of polyhedral[J]. Discrete and Computational Geometry, 1999, 21(2): 243–255.
CLOWES M B. On seeing things[J]. Artificial Intelligence, 1971, 2(1): 79–116.
KANADE T. A theory of Origami world[J]. Artificial Intelligence, 1980, 13(3): 279–311.
MARILL T. Emulating the human interpretation of line-drawings as three-dimensional objects[J]. International Journal of Computer Vision, 1991, 6(2): 147–161.
LECLERC Y G, FISCHLER M A. An optimization-based approach to the interpretation of single line drawings as 3D wire frames[J]. International Journal of Computer Vision, 1992, 9(2): 113–136.
LIPSON H, SHPITALNI M. Optimization-based reconstruction of a 3D object from a single freehand line drawing[J]. Computer-Aided Design, 2012, 28(8): 651–663.
BROWN E W. Why we see three-dimensional objects: another approach[R]. Internal Report: Northeastern University, 1994.[2014-03-01]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10. 1.1.71.3308&rep=rep1&type=pdf.
VARLEY P A C, MARTIN R R. The junction catalogue for labelling line drawings of polyhedra with tetrahedral vertices[J]. International Journal of Shape Modeling, 2011, 7(1): 23–44.
PERKINS D N. Cubic corners, oblique views of pictures, the perception of line drawings of simple space form, geometry and the perception of pictures: three studies[R]. 1968, Harvard University, Reprinted in Harvard Project Zero Technical Rep. No. 5, 1971.[2014-05-23]. http://files.eric.ed.gov/fulltext/ED114328.pdf.
YONG T L, FANG F. 3D reconstruction of polyhedral objects from single parallel projections using cubic corner[J]. Computer-Aided Design, 2011, 43(8): 1025–1034.
LIU J Z, CAO L L, LI Z G, et al. Plane-based optimization for 3D object reconstruction from single line drawings[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 315–327.
SUN Y, LEE Y T, SUN J. Regularity selection for effective 3D object reconstruction from a single line drawing[J]. Pattern Recognition Letters, 2008, 29(10): 1486–1495.
BIEDEMAN I. Recognition-by-components: a theory of human image understanding[J]. Psychological Review, 1987, 94(2): 115–147.
QIN S F, WRIGHT D K, JORDANOV I N. From on-line sketching to 2D and 3D geometry: a system based on fuzzy knowledge[J]. Computer-Aided Design, 2000, 32(14): 851–866.
LAMB D, BANDOPADHAY A. Interpreting a 3D object from a rough 2D line drawing[C]//Proceedings of the 1st Conference on Visualization, 1990, San Francisco, Oct 23–26, 1990: 59–66.
COMPANY P, CONESA J, ALEIXOS N. Axonometric inflation in line drawings reconstruction[R]. 2001, Jaume I University.[2014-03-01]. http://www.regeo.uji.es/publicaciones/regeo01.pdf.
LIU J, LEE Y T. A Graph-Based Method for Face Identification from a Single 2D Line Drawing[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2001, 23(10): 1106–1119.
LIU J, LEE Y T, CHAM W K. Identifying faces in a 2D line drawing representing a manifold object[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(12): 1579–1593.
VARLEY P A C, COMPANY P. A new algorithm for finding faces in wireframes[J]. Computer-Aided Design, 2010, 42(4): 279–309.
LEONG M C, LEE Y T, FANG F. A search-and-validate method for face identification from single line drawings[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2013, 35(11): 2576–2591.
FANG F, YONG T L. Efficient decomposition of line drawings of connected manifolds without face identification[J]. Computer-Aided Design, 2014, 51(6): 18–30.
VARLEY P A C, MARTIN R R. Estimating depth from line drawings[C]//Proceedings of the seventh ACM symposium on Solid modeling and applications, Saarbrücken, Germany, Jun 17–21, 2002: 180–191.
Author information
Authors and Affiliations
Corresponding author
Additional information
TIAN Huaiwen, born in 1965, is a professor at School of Mechanical Engineering, Southwest Jiaotong University, China. His main research interests include computer graphics, CAD, and reverse engineering.
QIN Shengfeng, born in 1962, is a professor at School of Design, Northumbria University, UK. His main reserach interests include sketch-based interface and modeling, digital design and manufacturing tools.
Rights and permissions
About this article
Cite this article
Tian, H., Qin, S. Exploring local regularities for 3D object recognition. Chin. J. Mech. Eng. 29, 1104–1113 (2016). https://doi.org/10.3901/CJME.2016.0721.085
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3901/CJME.2016.0721.085