Multimedia Tools and Applications

, Volume 77, Issue 7, pp 9171–9188 | Cite as

Exploring feature dimensionality reduction methods for enhancing automatic sport image annotation

  • Yomna Hatem
  • Sherine Rady


Nowadays, multimedia information requires the demand to investigate and apply efficient techniques for better annotation and retrieval purposes. In the content-based indexing, low-level features are generally extracted from images to serve as image descriptors. Other than the descriptor poses a computational overhead, the learning model may also tend to overfit, resulting in performance degeneration. This work solves such problems in the sport image domain by proposing feature dimensionality reduction techniques for the retrieval and annotation of image datasets. Different techniques are investigated, such as Information Gain, Gain Ratio, Chi-Square, and Latent Semantic Analysis (LSA), and applied for sport images classification using Support Vector Machine (SVM) classifier. A comparison between the performances of applying SVM alone and when incorporating the different reduction methods is presented. Experimental results show that the SVM classification accuracy is 76.4%; while integrating LSA technique manages to raise the accuracy to 96%, with the other techniques recording 74% accuracy at 50% feature space reduction.


Sport images annotation SVM Feature extraction and selection Information gain Chi-Square LSA 


  1. 1.
    Aslam N, Irfanullah, Loo J, Looms M and Roohullah (2010) A Semantic Query Interpreter Framework by using Knowledge Bases for Image Search and Retrieval. In: IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Luxor, pp 414–419.
  2. 2.
    Assfalg J, Bertini M, Colombo C, Bimbo AD (2002) Semantic annotation of sports video. IEEE Trans Multimedia 9(2):52–60. CrossRefzbMATHGoogle Scholar
  3. 3.
    Banerjee M and Islam S M (2015) Tackling Curse of Dimensionality for Efficient Content Based Image Retrieval. In: International Conference on Pattern Recognition and Machine Intelligence, Warsaw, Poland, pp 149–158.–3–319-19941-2-15
  4. 4.
    Barrena M, Caro A, Duran ML, Rodriguez PG, Arias-Nicolas JP, Alonso T (2015) Qatris iManager: a general purpose CBIR system. Mach Vis Appl 26(4):423–442. CrossRefGoogle Scholar
  5. 5.
    Buathong W, Meesad P (2013) Enhancing the Efficiency of Dimensionality Reduction Using a Combined Linear SVM Weight with ReliefF Feature Selection Method. In: 9th International Conference on Computing and Information Technology (IC2IT2013), vol 209. Springer, Berlin Heidelberg, pp 125–134.–3–642-37371-8_16 CrossRefGoogle Scholar
  6. 6.
    Burkhardt H and Reisert M (2006) Feature Selection for Retrieval Purposes. In: International Conference Image Analysis and Recognition, Portugal, Springer Berlin Heidelberg, pp 661–672.
  7. 7.
    Cai D, He X, Han J (2005) Document clustering using locality preserving indexing. IEEE Trans Knowl Data Eng 17(12):1624–1637. CrossRefGoogle Scholar
  8. 8.
    Cai X, Wang H, Huang H, Ding C (2012) Simultaneous image classification and annotation via biased random walk on tri-relational graph. In: European conference on computer vision. Springer, Berlin Heidelberg, pp 823–836. Google Scholar
  9. 9.
    Castelli V and Bergman L D (2002) Digital Imagery: Fundamentals. Image Databases: Search and retrieval of digital imagery, Wiley, pp 1–10.
  10. 10.
    Chen G-B, Chien B-C (2013) Feature Reduction and Selection for Automatic Image Annotation. In: Advances in Intelligent Systems and Applications, vol 1. Springer, Berlin Heidelberg, pp 317–326.–3–642-35452-6_33 Google Scholar
  11. 11.
    Chong W, Blei D and Li F (2009) Simultaneous Image Classification and Annotation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR09), Miami, FL, pp 1903–1910.
  12. 12.
    Han J, Kamber M, Pei J (2012) Data mining: concepts and techniques, 3rd edn. Elsevier Inc, USAzbMATHGoogle Scholar
  13. 13.
    Hatem Y, Rady S, Ismail R, Bahnasy K (2016) Automatic Content Description and Annotation of Sport Images using Classification Techniques. In: Proceedings of the 10th International Conference on Informatics and Systems. ACM, Egypt, pp 88–94. CrossRefGoogle Scholar
  14. 14.
    Jaworska T (2015) Spatial Representation of Object Location for Image Matching in CBIR. In: New Research in Multimedia and Internet Systems, Springer International Publishing, pp 25–34.–3–319-10383-9
  15. 15.
    Johnson S and Everingham M (2010) Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of the British Machine Vision Conference, vol 2, pp. 12.1–12.11.
  16. 16.
    Kesorn K, Poslad S (2009) Enhanced sports image annotation and retrieval based upon semantic analysis of multimodal cues. In: Pacific-rim symposium on image and video technology. Springer, Berlin Heidelberg, pp 817–828. Google Scholar
  17. 17.
    Kharkate SK, Janwe NJ (2013) A novel approach for automatic image annotation using color saliency. Int J Innov Res Comput Commun Eng 1(5):1142–1148Google Scholar
  18. 18.
    Khemchandani R, Saigal P (2015) Color image classification and retrieval through ternary decision structure based multi-category TWSVM. Neurocomputing Elsevier 165:444–455. CrossRefGoogle Scholar
  19. 19.
    Kim P, Choi D (2012) Automatic image annotation using semantic text analysis. In: International conference on availability, reliability, and security. Springer, Berlin Heidelberg, pp 479–487. Google Scholar
  20. 20.
    Leung CH, Li Y (2011) Comparison of different ontology-based query expansion algorithms for effective image retrieval. In: Signal processing, image processing and pattern recognition. Springer, Berlin Heidelberg, pp 291–299. CrossRefGoogle Scholar
  21. 21.
    Liu H and Setiono R (1995) Chi2: Feature selection and discretization of numeric attributes. In: Proceedings of the 7th International Conference on Tools with artificial intelligence, IEEE, pp 338–391.
  22. 22.
    Lulio L C, Tronco M L and Porto A J V (2012) Cognitive and Statistical Pattern Recognition Applied in Color and Texture Segmentation for Natural Scenes. In: Advances in Image Segmentation, INTECH Open Access Publisher, pp.103–120.
  23. 23.
    Panakarn P, Phimoltares S, Lursinsap C (2015) Identifying sport types and postures with complex background by fusion of local descriptors. Int J Pattern Recognit Artif Intell 29(02):1550008. MathSciNetCrossRefGoogle Scholar
  24. 24.
    Prasad Y, Biswas K, Jain CK (2010) SVM Classifier Based Feature Selection Using GA, ACO and PSO for siRNA Design. In: International Conference in Swarm Intelligence, vol 6146. Springer, Berlin Heidelberg, pp 307–314. Google Scholar
  25. 25.
    Priyogi B, Selviandro N, Hasibuan ZA, Ahmad M (2014) Image Clustering Using Multi-Visual Features. In: Proceedings of Information and Communication Technology-EurAsia Conference. Springer, Berlin Heidelberg, pp 179–189.–3–642-55032-4_18 Google Scholar
  26. 26.
    Sangeetha M, Anandakumar K, Bharathi A (2016) Automatic image annotation and retrieval: a survey. Int Res J Eng Technol (IRJET) 3(4):1143–1147Google Scholar
  27. 27.
    Seng T Y, Loong C T and Lukose D (2010) Semantic Image Annotation and Retrieval for Sport Images. In: Proceedings of the 2nd Semantic Technology and Knowledge Engineering Conference (STAKE2010), Kuching, Sarawak, Malaysia, pp 74–85Google Scholar
  28. 28.
    Seo K (2007) A GA-Based Feature Subset Selection and Parameter Optimization of Support Vector Machine for Content Based Image Retrieval. In: International Conference on Advanced Data Mining and Applications, vol 4632. Springer, Berlin Heidelberg, pp 594–604.–3–540-73871-8_57 CrossRefGoogle Scholar
  29. 29.
    Siddiqui A, Mishra N, Verma JS (2015) A survey on automatic image annotation and retrieval. Int J Comput Appl 118(20):27–32. Google Scholar
  30. 30.
    Tang J, Salem A, Liu H (2014) Feature selection for classification: a review. In: Aggarwal C (ed) Data classification: algorithms and application. CRC Press, New York, pp 37–58Google Scholar
  31. 31.
    Wang L and Khan L (2004) Automatic image annotation and retrieval using weighted feature selection. In: Proceedings of IEEE 6th International Symposium on Multimedia Software Engineering, pp 435–442.
  32. 32.
    Zhang S, Huang J, Huang Y and Yu Y (2010) Automatic Image Annotation Using Group Sparsity. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, pp 3312–3319.
  33. 33.
    Zhang D, Islam MM, Lu G (2013) Structural image retrieval using automatic image annotation and region based inverted file. J Vis Commun Image Represent 24(7):1087–1098. CrossRefGoogle Scholar
  34. 34.
    Zhang S, Tian Q, Hua G, Huang Q, Gao W (2014) ObjectPatchNet: towards scalable and semantic image annotation and retrieval. Comput Vis Image Underst 108:16–29. CrossRefGoogle Scholar
  35. 35.
    Zheng H, Horace HS (2014) Image classification and annotation based on robust regularized coding. SIViP 10(1):55–64. CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Faculty of Computer and Information Sciences, Information Systems DepartmentAin Shams UniversityCairoEgypt

Personalised recommendations