An Image-based Recommender System Based on Image Annotation

Abstract

Recommender system is a software that analyzes available data to make recommendations about various products and services to their users might be interested in. These systems must perform efficient  for both users and the e-commerce sites benefiting  from such systems. Ensuring proper and reliable recommendations increases user satisfaction that results selling more products and services. Collaborative filtering, content-based, and hybrid techniques are type of methods for recommender systems. Content-based recommender systems are usually text-based systems, but image-based recommender systems have become increasingly in favour for the content-based recommender systems in recent years.   

The process of an image based recommender system is to match a users’ image with the most similar image and recommend it. The recommendation images are the most likely images uploaded and widely acclaimed from the users. The most challenging problem in image-based recommneder systems is to match an image with the most similar visual words or classes based on the image’s visual content.  In this study, we are planning to solve this problem using Bag of words model, which is an effective model in computer vision, and also features are extracted with commonly used descriptors.

Keywords

• Bag of words model,descriptor,cosine similarity,Image-based recommender system

References

1. [1]. K. Pliakos, and C. Kotropoulos, “Building an image annotation and tourism recommender system”, Int. J. Artif. Intell. Tools, 24 (5), 2015.
2. [2]. A. Sasa, M. Krisper, Y. Kiyoki, and X. Chen, “A personalized recommender system model using colour-impression-based image retrieval and ranking method”, ICIW 2011 : The Sixth International Conference on Internet and Web Applications and Services, 124-130, 2011.
3. [3]. J. Fan, D.A. Keim, Y. Gao, H. Luo, and Z. Li, “JustClick: Personalized image recommendation via exploratory search from large-scale flickr image collections”, IEEE Trans. Circuits Syst. Video Technol., 19 (2): 273-288, 2008.
4. [4]. P. Bhagat, N. Mahakalkar, R. Chaudhari, and A. Gotmare, “A survey paper on profile- based image recommender system for smartphone”, In International Journal of Engineering Research and Technology, vol(3), ESRSA Publications, 2014.
5. [5]. L. Cao, J. Luo, A. Gallagher, X. Jin, J. Han, and T.S. Huan, “A worldwide tourism recommendation system based on geotaggedweb photos”, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2274-2277, 2010.
6. [6]. D. G. Lowe, “Distinctive image features from scale-invariant keypoints”, Int. J.Comput. Vision, 60: 91-110, 2004.
7. [7]. S. Van de, E.A. Koen, T. Gevers, and G. M.C. Snoek, “Evaluating color descriptors for object and scene recognition”, IEEE T. Pattern Anal., 32 (9):1582-1596, 2010.
8. [8]. H. Bay, T. Tuytelaars, and L.V. Gool, “SURF: Speeded up robust features”, In ECCV, (1): 404-417, 2006.

9. [9]. J. Matas, O. Chum, M. Urban, and T. Pajdla, “Robust wide baseline stereo from maximally stable extremal regions”, Proc. of British Machine Vision Conference, 384-396, 2002.
10. [10]. M. Heikkila, M. Pietikainen, and C. Schmid, “Description of interest regions with local binary patterns”, Pattern Recogn. , 42: 425-436, 2009.
11. [11]. https://webscope.sandbox.yahoo.com/catalog.php?datatype=i.