Abstract
A new machine vision approach for quantitatively estimating and monitoring the appearance and aesthetics of manufactured products is presented. The approach is composed of three steps: (1) wavelet-based textural feature extraction from product images, (2) estimation of measures of the product appearance through subspace projection of the textural features, and (3) monitoring of the appearance in the latent variable subspace of the textural features. The methodology is specifically designed to treat the stochastic nature of the visual appearance of many manufactured products. This nondeterministic aspect of product appearance has been an obstacle for the success of machine vision in many industries. The emphasis of this approach is on the consistent and quantitative estimation of continuous variations in visual appearance rather than on classification into discrete classes. This allows for the on-line monitoring and the eventual feedback control of product appearance. This approach is successfully applied to the estimation and monitoring of the aesthetic quality of manufactured stone countertops.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities, 2nd edn. Academic Press, San Diego, CA (1997)
Marshall, A.D., Martin, R.R.: Computer Vision, Models and Inspection. World Scientific Publishing, Singapore (1992)
Hyper Dictionary: http://www.hyperdictionary.com/search.aspx?define=computer±vision
Liu, J., MacGregor, J.F., Duchesne, C., Bartolacci, G.: Monitoring of flotation processes using multiresolutional multivariate image analysis. Miner. Eng. 18(1), 65–76 (2005)
Liu, J., MacGregor, J.F.: Modeling and optimization of product appearance: application to injection-molded plastic panels. Ind. Eng. Chem. Res. 44, 4687–4696 (2005)
Bharati, M., Liu, J., MacGregor, J.F.: Image texture analysis: methods and comparisons. Chemometrics Intell. Lab. Syst. 72(1), 57–71 (2004)
Honglu, Y., MacGregor, J.F., Haarsma, G., Bourg, W.: Digital imaging for on-line monitoring and control of industrial snack food processes. Ind. Eng. Chem. Res. 42(13), 3036–3044 (2003)
Honglu, Y., MacGregor, J.F.: Monitoring flames in an industrial boiler using multivariate image analysis. AIChE J. 50(7), 1474–1483 (2004)
Liu, J., MacGregor, J.F.: On the extraction of spectral and spatial information for image analysis. Chemometrics Intell. Lab. Syst. (2004)
Mallat, S.G.: A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 674–693 (1989)
Rioul, O., Duhamel, P.: Fast algorithms for discrete and continuous wavelet transforms. IEEE Trans. Inform. Theory 38(2), 569–586 (1992)
Daubechies, I.: Ten lectures on wavelets. In: Proceedings of the CBMS-NSF Reg. Conf. Series in Applied Math. no. 61. SIAM, Philadelphia, PA (1992)
Vetterli, M., Kovaević, J.: Wavelets and Subband Coding. Prentice Hall, Englewood Cliffs, NJ (1995)
Randen, T., Husoy, J.H.: Filtering for texture classification: a comparative study. IEEE Trans. Pattern Anal. Mach. Intell. 21(4), 291–310 (1999)
Tuceryan, M., Jain, A.K.: Texture analysis. In: Chen, C.H., et al., (eds.) Handbook of Pattern Recognition and Computer Vision, 2nd edn., pp. 235–276. World Scientific Publishing, New Jersey (1993)
Chang, T., Kuo, C.C.J.: Texture analysis and classification with tree-structured wavelet transform. IEEE Trans. Image Process. 2(4), 429–441 (1993)
Etdmad, K., Chellappa, R.: Separability-based multiscale basis selection and feature extraction for signal and image classification. IEEE Trans. Image Process. 7(10), 1453–1465 (1998)
Laine, A., Fan, J.: Texture classification by wavelet packet signatures. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1186–1191 (1993)
Hotelling, H.: Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24, 417–441 (1933)
Karhunen, K.: Uber lineare methoden in der Wahrsccheilichkeitsrechnung. Ann. Acad. Sci. Fenn., Ser. A1: Math.-Phys. 37, 3–79 (1947)
Loéve, M.: Probability Theory. Van Nostrand, New York (1963)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(Part II), 179–188 (1936)
Bell, A.J., Sejnoski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7, 1129–1159 (1995)
Friedman, J.H., Tukey, J.W.: A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. 23(9), 881–890 (1974)
Kresta, J.V., MacGregor, J.F., Marlin, T.E.: Multivariate statistical monitoring of process operating performance. Can. J. Chem. Eng. 69, 35–47 (1991)
Kourti, T., MacGregor, J.F.: Multivariate statistical process control methods for monitoring and diagnosing process and product performance. J. Qual. Technol. 28, 409–428 (1996)
Jackson, J.E.: A User's Guide to Principal Components. Wiley-Interscience, New York (1991)
Lee, J.-.M, Yoo, C., Lee, I.B.: Statistical process monitoring using independent component analysis. J. Process Control 14(5), 467–485 (2004)
Mojsilović, A., Popović, M.V., Rackkov, D.M.: On the selection of an optimal wavelet basis for texture characterization. IEEE Trans. Image Process. 9(12), 2043–2050 (2000)
Besse, P., de Falguerolles, A.: Application of resampling methods to the choice of dimension in principal component analysis. In: Härdle, W., Simar, L. (eds.) Computer Intensive Methods in Statistics, pp. 167–174. Physica-Verlag, Heidelberg, Germany (1993)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Addison-Wesley, Reading, MA (1993)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Liu, J.J., MacGregor, J.F. Estimation and monitoring of product aesthetics: application to manufacturing of “engineered stone” countertops. Machine Vision and Applications 16, 374–383 (2006). https://doi.org/10.1007/s00138-005-0009-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-005-0009-8