Visual Recommendation Use Case for an Online Marketplace Platform: allegro.pl

In this paper we describe a small content-based visual recommendation project built as part of the Allegro online marketplace platform. We extracted relevant data only from images, as they are inherently better at capturing visual attributes than textual offer descriptions. We used several image descriptors to extract color and texture information in order to find visually similar items. We tested our results against available textual offer tags and also asked human users to subjectively assess the precision. Finally, we deployed the solution to our platform.

[1]  Jeff Donahue,et al.  Visual Search at Pinterest , 2015, KDD.

[2]  Robinson Piramuthu,et al.  Palette power: enabling visual search through colors , 2013, KDD.

[3]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  C. Won,et al.  Efficient Use of MPEG‐7 Edge Histogram Descriptor , 2002 .

[5]  Leonidas J. Guibas,et al.  A metric for distributions with applications to image databases , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[6]  Jen-Hao Hsiao,et al.  On visual similarity based interactive product recommendation for online shopping , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[7]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[8]  M. Hazewinkel.  Encyclopaedia of mathematics , 1987 .

[9]  D J Rogers,et al.  A Computer Program for Classifying Plants. , 1960, Science.

[10]  Mathias Lux,et al.  Content based image retrieval with LIRe , 2011, ACM Multimedia.