Abstract

Recent rapid growth in the demand for technology and image investigation in many applications, such as image retrieval systems and Visual Object Categorization (VOC), effective management of these applications has become crucial. Computer vision and its various applications are a primary focus of research. Content-based image retrieval is considered an extremely challenging issue and has remained an open research area. Obviously, the main challenge associated with this kind of research is the gap between the low-level features and the richness of the semantic concept of the human mind. This problem is called the semantic gap. Several methods have been proposed to increase the performance of the system and reduce the semantic gap. These proposed techniques make use of either global or local features or a combination of both global and local features on one side and the visual content and keyword-based retrieval on the other side. However, the aim of this study is to provide a constructive critique of the algorithms used in extracting the low-level features, either globally or locally or as a combination of both. In addition, it identifies the factors that can affect the low-level features that lead to the semantic gap. As well as, proposed a new framework to improve the Gabor filter and the edge histogram limitations. Finally, recommendations are made for the choice of the descriptors used to describe the low-level features, both locally and globally, depending on the area of limitations or drawbacks of the previous state-of-the-art research.

Keywords:

Combination feature, content-based image retrieval, global and local descriptors, SIFT descriptor, similarity measure,

References

1. Abdullah, A., R.C. Veltkamp and M.A. Wiering, 2010. Fixed partitioning and salient points with MPEG-7 cluster correlograms for image categorization. Pattern Recogn., 43: 650-662.
   CrossRef    
2. Abdullah, A. and Wiering, M.A. 2007. CIREC: Cluster Correlogram Image Retrieval and Categorization using MPEG-7 Descriptors. IEEE Symposium on Computational Intelligence in Image and Signal Processing.
   CrossRef    
3. Abdullah, S.N.H.S., M. Khalid, R. Yusof and K. Omar, 2007a. Comparison of feature extractors in license plate recognition. Proceedings of 1st Asia International Conference on Modelling and Simulation (AMS2007). Phuket, Thailand, pp: 502-506.
   CrossRef    
4. Abdullah, S.N.H.S., M. Khalid, R. Yusof and K. Omar, 2007b. License plate recognition based on geometrical features topology analysis and support vector machine. Proceeding of the Malaysia-Japan International Symposium on Advanced Technology (MJISAT’2007). Kuala Lumpur, Malaysia.
   
5. Abdullah, S.N.H.S., K. Omar, S. Sahran and M. Khalid, 2009. License plate recognition based on support vector machine. Proceeding of the International Conference on Electrical Engineering and Informatics (ICEEI'09), 1: 78-82.
   CrossRef    
6. Alemu, Y., J.B. Koh, M. Ikram and D.K. Kim, 2009. Image retrieval in multimedia databases: A survey. Proceeding of the 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing.
   CrossRef    
7. Arif, T., Z. Shaaban, L. Krekor and S. Baba, 2009. Object classification via geometrical, zernike and legendre moments. J. Theor. Appl. Inf. Technol., 7: 31-37.
   
8. Ayad, H., S.N.H.S. Abdullah and A. Abdullah, 2012. Visual object categorization based on orientation descriptor. Proceeding of the 6th Asia International Conference on Mathematical Modeling and Computer Simulation (ASM’2012). Bali, Indonesia.
   CrossRef    
9. Bataineh, B., S.N.H. Abdullah and K. Omar, 2011. A statistical global feature extraction method for optical font recognition. In: Nguyen, N.T., C.G. Kim and A. Janiak (Eds.), ACIIDS, 2011. LNAI 6591, Springer-Verlag, Berlin, Heidelberg, pp: 257-267.
   CrossRef    
10. Bay, H., T. Tuytelaars and L.V. Gool, 2008. SURF: Speeded up robust features. Comput. Vis. Image Und., 110(3).
    CrossRef    
11. Bin Adam, H., M. Fauzi bin Hassan, M. Jaisbin Gimin and A. Bin Abdullah, 2011. Material surface analysis for robot labeling. Proceeding of the International Conference on Pattern Analysis and Intelligent Robotics (ICPAIR), 1: 136-138.
    CrossRef    
12. Canny, J., 1986. A computational approach to edge detection. IEEE T. Pattern Anal., 8: 679-698.
    CrossRef    
13. Chih-Fong, T. and L. Wei-Chao, 2009. A Comparative study of global and local feature representations in image database categorization. Proceeding of the 5th International Joint Conference on INC, IMS and IDC (NCM'09), pp: 1563-1566.
    
14. Choi, W.P., S.H. Tse, K.W. Wang and K.M. Lam, 2008. Simplified gabor wavelets for human face recognition. Pattern Recogn., 41(3): 1186-1199.
    CrossRef    
15. Daugman, J.G., 1988. Complete discrete 2-D gabor transforms by neural networks for image analysis and compression. IEEE T. Acoust. Speech, 36(7): 1169-1179.
    CrossRef    
16. Deb, S., 2008. Overview of image segmentation techniques and searching for future directions of research in content-based image retrieval. Proceeding of the 1st IEEE International Conference on Ubi-Media Computing, pp: 184-189.
    CrossRef    
17. Deng, Y., B.S. Manjunath and H. Shin, 1999. Color image segmentation. Proceeding of the CVPR, pp: 2446-2451.
    
18. Harris, C. and S. Mike, 1988. A combined corner and edge detector. Proceeding of the Alvey Vision Conference, pp: 147-151.
    CrossRef    
19. Hiremath, P.S. and J. Pujari, 2007. Content based image retrieval using color, texture and shape features. Proceeding of the International Conference on Advanced Computing and Communications (ADCOM’2007), pp: 780-784.
    CrossRef    
20. Hu, M.K., 1962. Visual pattern recognition by moment invariants. IRE T. Inform. Theor., 8: 179-187.
    CrossRef    
21. Jaswal, G. and A. Kaul, 2009. Content based image retrieval: A literature review. Proceeding of the National Conference on Computing, Communication and Control (CCC-09), pp: 198-201.
    
22. Ke, Y. and R. Sukthankar, 2004. PCA-SIFT: A more distinctive representation for local image descriptors. Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR, 2004), 2: 506-513.
    
23. Kurniawati, N.N., S.N.H.S. Abdullah and S. Abdullah, 2009. Investigation on image processing techniques for diagnosing paddy diseases. Proceeding of the International Conference of Soft Computing and Pattern Recognition (SOCPAR'09), pp: 272-277.
    CrossRef    
24. Leow, W.K. and S.Y. Lai, 2000. Scale and Orientation-invariant Texture Matching for Image Retrieval. In: Pietikainen, M.K. (Ed.), Texture Analysis in Machine Vision. World Scientific, Singapore.
    CrossRef    
25. Liu, Y., D. Zhanga, G. Lua and W.Y. Mab, 2007. A survey of content-based image retrieval with high-level semantics. Pattern Recogn., 40: 262-282.
    CrossRef    
26. Long, F., H. Zhang and D.D. Feng, 2003. Multimedia Information Retrieval and Management: Technological Fundamentals and Applications. Springer, New York.
    
27. Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60: 91-110.
    CrossRef    
28. Lui, P., K. Jia and Z. Wang, 2007. An effective image retrieval method based on color and texture combined features. Proceeding of the 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP’2007), pp: 169-172.
    
29. Lukac, R. and K.N. Plataniotis, 2007. Color Image Processing: Methods and Applications. Taylor and Francis Group, LLC., Boca Raton.
    
30. Manjunath, B.S., J.R. Ohm, V.V. Vasudevan and A. Yamada, 2001. Color and texture descriptors. IEEE T. Circ. Syst. Vid., 11: 703-715.
    CrossRef    
31. Mikolajczyk, K. and C. Schmid, 2005. A performance evaluation of local descriptors. IEEE T. Pattern Anal., 27: 1615-1630.
    CrossRef    PMid:16237996    
32. Mingqiang, Y., K. Kidiyo and R. Joseph, 2008. A Survey of Shape Feature Extraction Techniques. In: Peng-Yeng Yin (Ed.), Pattern Recognition Techniques, Technology and Applications. I-Tech, Vienna, Austria.
    CrossRef    
33. Moghadam, P., J.A. Starzyk and W.S. Wijesoma, 2012. Fast vanishing-point detection in unstructured environments. IEEE T. Image Process., 21(1): 425-430.
    CrossRef    PMid:21775263    
34. Mohan, V., P. Shanmugapriya and Y. Venkataramani, 2008. Object recognition using image descriptors. Proceeding of the International Conference on Communication and Networking Computing (ICCCn 2008), pp: 1-4.
    CrossRef    
35. Nadernejad, E., S. Sharifzadeh and H. Hassanpour, 2008. Edge detection techniques: Evaluations and comparisons. Appl. Math. Sci., 2: 1507-1520.
    
36. Pabboju, S. and A.V.G. Reddy, 2009. Novel approach for content-based image indexing and retrieval system using global and region features. Int. J. Comput. Sci. Netw. Secur., 9(2): 119-130.
    
37. Pujari, J., S.N. Pushpalatha and P.D. Desai, 2010. Content-based image retrieval using color and shape descriptors. Proceeding of the International Conference on Signal and Image Processing (ICSIP), pp: 239-242.
    CrossRef    
38. Sarfraz, M., 2006. Object recognition using fourier descriptors: Some experiments and observations. Proceedings of the International Conference on Computer Graphics, Imaging and Visualisation (CGIV, 2006), pp: 281-286.
    
39. Serra, J., 2003. Image segmentation. Proceeding of the IEEE International Conference on Image Processing (ICIP).
    CrossRef    
40. Shen, L.L. and Z. Ji, 2009. Gabor wavelet selection and SVM classification for object recognition. Acta Automatica Sinica, 35(4): 350-355.
    CrossRef    
41. Shi-Kuo, C., S. Qing-Yun and Y. Cheng-Wen, 1987. Iconic indexing by 2-D strings. IEEE T. Pattern Anal., 9: 413-428.
    
42. Tamura, H., S. Mori and T. Yamawaki, 1987. Textural features corresponding to visual perception. IEEE T. Syst. Man Cyb., 8: 460-473.
    CrossRef    
43. Van de Sande, K.E.A., T. Gevers and C.G.M. Snoek, 2010. Evaluating color descriptors for object and scene recognition. IEEE T. Pattern Anal., 32: 1582-1596.
    CrossRef    PMid:20634554    
44. Wang, J.Z., J. Li and G. Wiederhold, 2001. SIMPLIcity: Semantics-sensitive integrated matching for picture libraries. IEEE T. Pattern Anal., 23(9): 947-963.
    CrossRef    
45. Wu, Y. and Y. Wu, 2009. Shape-based image retrieval using combining global and local shape features. Proceeding of the 2nd International Congress on Image and Signal Processing (CISP'09), pp: 1-5.
    CrossRef    
46. Xiaoyin, D., 2010. Image retrieval using color moment invariant. Proceeding of the 7th International Conference on Information Technology: New Generations (ITNG), pp: 200-203.
    
47. Xu, C. and J.L. Prince, 1998. Snakes, shapes and gradient vector flow. IEEE T. Image Process., 7: 359-369.
    CrossRef    PMid:18276256    
48. Yang, H. and Q. Wang, 2008. A novel local feature descriptor for image matching. Proceeding of the IEEE International Conference on Multimedia and Expo, pp: 239-242.
    
49. Yap, P.T., R. Paramesran and O. Seng-Huat, 2003. Image analysis by krawtchouk moments. IEEE T. Image Process., 12: 1367-1377.
    CrossRef    PMid:18244694    
50. Zhang, Y. and J. Yang, 2008. An object based image retrieval. Proceeding of the 2nd International Symposium on Intelligent Information Technology Application (IITA'08), pp: 385-388.
    CrossRef    
51. Zhu, J., M.I. Vai and P.U. Mak, 2004. A new Enhanced Nearest Feature Space (ENFS) classifier for gabor wavelets features-based face recognition. In: Zhang, D. and A.K. Jain (Eds.), ICBA, 2004. LNCS 3072, Springer-Verlag, Berlin, Heidelberg, pp: 124-131.
    CrossRef    
52. Zhu, Y., X. Liu and W. Mio, 2007. Content-based image categorization and retrieval using neural networks. Proceeding of the IEEE International Conference on Multimedia and Expo, pp: 528-531.
    CrossRef    
53. Zolkifli, Z.F.M., M. Farif Jemili, F. Hashim and S.N.H.S. Abdullah, 2011. Optimal features and classes for estimating mobile robot orientation based on support vector machine. Proceeding of the 14th FIRA RoboWorld Congress. Kaohsiung, Taiwan.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.