Market Segmentation Using Color Information of Images

10.7903/ijecs.1400

Ines Daniel；Sarah Frost；Daniel Baier

Color Space ； Image Clustering ； Market Segmentation

International Journal of Electronic Commerce Studies

6卷1期（2015 / 06 / 01）

137 - 144

英文

Market segmentation is an important area of marketing. In this field, researchers use clustering algorithms to divide customers into homogeneous groups. Traditionally, these groups are formed on the basis of survey data. In these surveys, the test persons often have to answer a variety of questions. With the increasing amount of digitalization and improved technical capabilities, new databases are now available for this purpose. For example, potential customers might provide photos that describe their activities, interests, or opinions. In the area of content-based image retrieval (CBIR) there are various methods that currently exist to analyze the similarity of such photos, e.g., using distributional descriptors of colors, textures, or shapes. In this paper we discuss which dissimilarity measures could be used to segment photos by hierarchical clustering on the basis of color. For this purpose we analyzed 2,100 images concerning three color spaces RGB, HSV and CIE L*a*b* using different distance measures as the basis for hierarchical clustering.

1. Facebook, Statistik. Retrieved on January 16, 2012, from http://www.facebook.com/press/info.php?statistics.
2. Batchelor, B.G.(2012).Machine vision for industrial applications.Machine Vision Handbook,London:
3. Daniel, I.,Baier, D.(2013).Lifestyle segmentation based on contents of uploaded images versus ratings of items.Algorithms from and for Nature and Life Studies in Classification, Data Analysis, and Knowledge Organization,Heidelberg:
4. Geman, D.,Geman, S.,Graffigne, C.,Dong, P.(1990).Boundary detection by constrained optimization.IEEE Transactions on Pattern Analysis and Machine Intelligence,12(7),609-628.
5. C. Hallerberg, and F. Koch, 20 Millionen Deutsche stellen eigene Fotos ins Internet. Retrieved on January 16, 2012, from http://www.bitkom.org/files/documents/bitkom-presseinfo_einstellen_von_videos_und_bildern_04_09_2009.pdf.
6. Hermann, A.(Ed.)(2008).Handbuch Marktforschung.Gabler:Wiesbaden.
7. Rubner, Y.,Tomasi, C.,Guibas, L.J.(2000).The earth mover's distance as a metric for image retrieval.International Journal of Computer Vision,40(2),99-121.
8. Schanda, J.(Ed.)(2007).Colorimetry.Hoboken:John Wiley & Sons.
9. Smith, W.R.(1956).Product differentiation and market segmentation as alternative marketing strategies.Journal of Marketing,21(1),3-8.
10. Swain, M.,Ballard, D.(1991).Color indexing.International Journal of Computer Vision,7(1),11-32.
11. Vinh, N.X.,Epps, J.,Bailey, J.(2009).Information theoretic measures for clusterings comparison: Is a correction for chance necessary?.Proceedings of the 26th International Conference on Machine Learning,Canada:
12. Wedel, M.,Kamakura, W.(2000).Market segmentation: Conceptual and methodological foundations.Boston:Kluwer Academic Publishers.
13. Werman, M.,Peleg, S.,Rosenfeld, A.(1985).A distance metric for multidimensional histograms.Computer Vision, Graphics, and Image Processing,32(3),328-336.
14. Wyszecki, G.,Stiles, W.(2000).Concepts and methods, quantitative data and formulae.New York:Wiley.