The week's pick
Random Articles
Reseach Article
An Improvised Approach to Content based Image Retrieval
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 106 - Number 17 |
| Year of Publication: 2014 |
| Authors: K.Lakshmi Sudha, Megha Redkar, Anitha Ranganathan, Karishma Upadhyay |
10.5120/18711-9688
|
K.Lakshmi Sudha, Megha Redkar, Anitha Ranganathan, Karishma Upadhyay . An Improvised Approach to Content based Image Retrieval. International Journal of Computer Applications. 106, 17 ( November 2014), 41-44. DOI=10.5120/18711-9688
Abstract
Image matching is a fundamental aspect of many problems in computer vision, solving for 3D structure from multiple images, stereo correspondence, and motion tracking. An image may have features that have properties making them suitable for matching images. There have been various algorithms and optimizations for Content Based Image Retrieval. A few algorithms include Simple Harris, SIFT. Feature detectors and high matching consuming creates a low automation problem. To overcome these issues there have also been papers proposing optimized algorithms on Harris and SIFT [1]. This algorithm also has several flaws. The optimized algorithm uses Harris for feature extraction and description but Harris has a constraint that Harris detectors detect points only on black and white events. SIFT is flawed in itself since it is inefficient for poor resolution images and is also a time consuming algorithm [5]. The nearest neighbor search used as a matching algorithm is also time consuming and results in random overhead of outcomes. To overcome these shortcomings this paper proposes an algorithm that combines the advantages of Harris, SIFT and the matching algorithms. Color saliency is used along with Harris improvising its efficiency [6]. SIFT matching technique along with the nearest neighbor algorithm is supplemented with an epipolar concept to tender accurate results with lesser discrepant values.
References
- Jie Zhao1, Li-Juan Xue1, Guo-Zun Men. Optimization Matching Algorithm Based on improvement Harris and SIFT. College of Electronics and Information Engineering of Hebei University, Baoding 071002 at China College of Economics, Hebei University, Baoding, 071002, China 11-14th July 2010.
- K. Mikolajczyk and C. Schmid. Scale and affine invariant interest point detectors. Int. J. Computer Vision, 60(1):63–86, 2004.
- P. Bendale, B. Triggs, and N. Kingsbury. Multiscale keypoint analysis based on complexwavelets. In British Machine Vision Conference, August 2010.
- Mamta Kamath, Disha Punjabi, Tejal Sabnis, Divya Upadhyay, Seema Shrawne. Improving Content Based Image Retrieval usingScale Invariant Feature Transform. International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 –8958, Volume-1, Issue-5, June 2012.
- K.Velmurugan, Lt. Dr. S.Santhosh Baboo. Image Retrieval using Harris Corners and Histogram of Oriented Gradients. International Journal of Computer Applications (0975 – 8887) Volume 24– No.7, June 2011.
- Hiremath P.S. and Jagadeesh PujariContent Based Image Retrieval using Colour Boosted SalientPoints and Shape features of an image.International Journal of Image Processing, Volume (2): Issue (1) 10.
- K. Arbter, W. E. Snyder, H. Burkhardt, and G. Hirzinger, "Application of affine-invariant Fourier descriptors to recognition of 3D objects," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 640-647, 1990.
- E. M. Arkin, L.P. Chew, D.P. Huttenlocher, K. Kedem, and J.S.B. Mitchell, "An efficiently computable metric for comparing polygonal shapes," IEEE Trans. Pattern Analysis and MachineIntelligence, vol. 13, no. 3, pp. 209- 226, 1991.
- Dr. Fuhui Long, Dr. Hongjiang Zhang and Prof. David Dagan Feng. Fundamentals of content-based image retrievals. 2004.
- Faraj Alhwarin, Chao Wang, Danijela Risti -Durrant, Axel Gräser. Improved SIFT-Features Matching for Object Recognition. BCS International Academic Conference 2008 – Visions of Computer Science.
- J. van de Weijer, Th. Gevers, J-M Geusebroek, "Boosting Colour Saliency in Image Feature Detection", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27 (4), April 2005. ,” in CVPR, 2000, pp. 612–618.
- David G. Lowe. : Object recognition from local scale- invariant features, International Conference on Computer Vision, Corfu, Greece (September 1999), pp. 1150-1157.
- David G. Lowe. : Local feature view clustering for 3D object recognition, IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii (December 2001), pp. 682-688.
Index Terms
Keywords