CBIR with Partial Input of Unshaped Images Using Compressed-Pixel Matching Algorithm

Authors

  • Ahilandeswari Thangarajan
  • Vivekanandan Kalimuthu

DOI:

https://doi.org/10.14419/ijet.v7i3.27.17762

Published:

2018-08-15

Keywords:

Partial input image, content based image retrieval (CBIR), shapes, ROI, compression.

Abstract

Many works have been done to find out whether given image is in the database using Content Based Image Retrieval (CBIR) techniques. However if the query image is unshaped or noise filled then retrieval of that image in the database is difficult .We propose an approach by which for any shape of input image the databases is searched and the most relevant image is retrieved. Results provides better accuracy than existing one and time elapsed also reduced because of making comparison after compression of both partial image and images from the database. The attainment of the proposed system is assessed using LFW and WANG image sets consisting of 2000 and 9990 images, respectively, and it measured with familiar methods with regard to precision and recall which demonstrates the advantages of the proposed approach.

 

References

[1] Tajeripour F, Saberi M & Ershad SF, “Developing a novel approach for content based image retrieval using modified local binary patterns and morphological transformâ€, Int. Arab J. Inf. Technol., Vol.12, No.6,(2015), pp.574-581.

[2] Takahashi T & Kurita T, “Mixture of subspaces image representation and compact coding for large-scale image retrievalâ€, IEEE transactions on pattern analysis and machine intelligence, Vol.37, No.7,(2015), pp.1469-1479.

[3] Han J & McKenna SJ, “Query-dependent metric learning for adaptive, content-based image browsing and retrievalâ€, IET Image Process , Vol.8, (2014), pp.610–618.

[4] Yue J, Li Z, Liu L & Fu Z, “Content-based image retrieval using color and texture fused featuresâ€, Mathematical and Computer Modelling, Vol.54, No.3-4,(2011), pp.1121-1127.

[5] Elleuch Z & Marzouki K, “Multi-index structure based on SIFT and color features for large scale image retrievalâ€, Multimed Tools Appl, (2016).

[6] Khokher A & Talwar R, “A fast and effective image retrieval scheme using color, texture, and shape-based histogramsâ€, Multimed Tools Appl, (2016).

[7] Deepika, J., Senthil, T., Rajan, C., & Surendar, A. (2018). Machine learning algorithms : a background artifact. International Journal of Engineering & Technology, 7, 143–149

[8] Xu B, Bu J, Chen C, Wang C, Cai D & He X, “EMR: A scalable graph-based ranking model for content-based image retrievalâ€, IEEE Transactions on knowledge and data engineering, Vol.27, No.1,(2015), pp.102-114.

[9] G Mussabekova, S Chakanova, A Boranbayeva, A Utebayeva, K Kazybaeva, K Alshynbaev (2018). Structural conceptual model of forming readiness for innovative activity of future teachers in general education school. Opción, Año 33. 217-240

[10] G Cely Galindo (2017) Del Prometeo griego al de la era-biós de la tecnociencia. Reflexiones bioéticas Opción, Año 33, No. 82 (2017):114-133

View Full Article: