IJSTR

International Journal of Scientific & Technology Research

IJSTR@Facebook IJSTR@Twitter IJSTR@Linkedin
Home About Us Scope Editorial Board Blog/Latest News Contact Us
CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT
QR CODE
IJSTR-QR Code

IJSTR >> Volume 4 - Issue 12, December 2015 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Low Quality Image Retrieval System For Generic Databases

[Full Text]

 

AUTHOR(S)

W.A.D.N. Wijesekera, W.M.J.I. Wijayanayake

 

KEYWORDS

Index Terms: Content Based Image Retrieval, Low Quality Images, K means Clustering Technique, Query Based Image Content, Image Binarization

 

ABSTRACT

Abstract: Content Based Image Retrieval (CBIR) systems have become the trend in image retrieval technologies, as the index or notation based image retrieval algorithms give less efficient results in high usage of images. These CBIR systems are mostly developed considering the availability of high or normal quality images. High availability of low quality images in databases, due to usage of different quality equipment to capture images, and different environmental conditions the photos are being captured, has opened up a new path in image retrieval research area. The algorithms which are developed for low quality image based image retrieval are only a few, and have been performed only for specific domains. Low quality image based image retrieval algorithm on a generic database with a considerable accuracy level for different industries is an area which remains unsolved. Through this study, an algorithm has been developed to achieve above mentioned gaps. By using images with inappropriate brightness and compressed images as low quality images, the proposed algorithm is tested on a generic database, which includes many categories of data, instead of using a specific domain. The new algorithm developed, gives better precision and recall values when they are clustered into the most appropriate number of clusters which changes according to the level of quality of the image. As the quality of the image decreases, the accuracy of the algorithm also tends to be reduced; a space for further improvement.

 

REFERENCES

[1] Fauzi, M. F. A., Content-based image retrieval of museum images. PhD diss., University of Southampton, 2004.W.-K. Chen, Linear Networks and Systems. Belmont, Calif.: Wadsworth, pp. 123-135, 1993. (Book style)

[2] Purba, S., ed. High-performance Web databases: design, development, and deployment. CRC Press, 2010.K. Elissa, “An Overview of Decision Theory,"unpublished. (Unplublished manuscript)

[3] Chakravarti, R., and Xiannong, M., A Study of Color Histogram Based Image Retrieval. In ITNG, pp. 1323-1328. 2009.C. J. Kaufman, Rocky Mountain Research Laboratories, Boulder, Colo., personal communication, 1992. (Personal communication)

[4] Treil, N., Mallat, S., and Bajcsy, R., Image Wavelet Decomposition and Applications. Technical Reports (CIS) : 781. 1989.S.P. Bingulac, “On the Compatibility of Adaptive Controllers,” Proc. Fourth Ann. Allerton Conf. Circuits and Systems Theory, pp. 8-16, 1994. (Conference proceedings)

[5] Jacobs, C. E., Finkelstein, A. and Salesin, D. H., Fast multiresolution image querying. In Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, pp. 277-286. ACM, New York, NY, USA, 1995.J. Williams, “Narrow-Band Analyzer,” PhD dissertation, Dept. of Electrical Eng., Harvard Univ., Cambridge, Mass., 1993. (Thesis or dissertation)

[6] Kannan, A., Mohan, V. and Anbazhagan, N., Image clustering and retrieval using image mining techniques. In 2010 IEEE International Conference on Computational Intelligence and Computing Research, Tamilnadu, India, December 2010.L. Hubert and P. Arabie, “Comparing Partitions,” J. Classification, vol. 2, no. 4, pp. 193-218, Apr. 1985. (Journal or magazine citation)

[7] Liu, Y., Zhang, D., Lu, G. and Ma, W.Y. A survey of content-based image retrieval with high-level semantics. Pattern Recognition 40, no. 1: 262-282. 2007.

[8] Vadivel, A., Majumdar, A.K. and Sural, S., Characteristics of weighted feature vector in content-based image retrieval applications. In Intelligent Sensing and Information Processing, 2004. Proceedings of International Conference on, pp. 127-132. IEEE, 2004.

[9] Silakari, S., Motwani, M. and Maheshwari, M. Color image clustering using block truncation algorithm. arXiv preprint arXiv:0910.1849. 2009.

[10] Moghaddam, R.F.., and Cheriet, M. AdOtsu: An adaptive and parameterless generalization of Otsu's method for document image binarization. Pattern Recognition 45, no. 6: 2419-2431. 2012.

[11] Wang, B., Li, X-F., Liu, F. and Hu, F-Q. Color text image binarization based on binary texture analysis. Pattern Recognition Letters 26, no. 11: 1650-1657. 2005.

[12] J.SauvolaandM.Pietikainen.Adaptivedocumentimagebinarization.,Pattern Recognition, 33(2):225{236,February2000.

[13] STAN HORACZEK. 2013. How Many Photos Are Uploaded to The Internet Every Minute?. [ONLINE] Available at: http://www.popphoto.com/news/2013/05/how-many-photos-are-uploaded-to-internet-every-minute. [Accessed 18 April 14].