Flower Image Retrieval Using Color and Shape Features and Multiple Distance Functions

  • Mohammad Farhad Bulbul
  • Khadiza Sultana Happy Department of Mathematics, Jessore University of Science and Technology; Bangladesh
  • Zannatul Azme Department of Mathematics, Jessore University of Science and Technology; Bangladesh

Abstract

It is noticeable that when flower images are observed, flower’s color signifies people and often people ignore small and isolated sectors of the image. So for retrieving flower images color feature of the images is very important. Different flowers have also different shapes. So for differing flower images from another flower images shape feature is also a significant feature. In this paper, we proposed a method of retrieving flower images using their color and shape feature. We used HSV color histogram, color moments and color auto correlogram descriptors for describing color feature and HOG descriptor for describing shape feature. We calculate the similarities between the query image and the database images by employing a set of distance functions.  We evaluated our result for our own dataset of 15 categories flower images. 

References

(1) Eakins, John P., and Margaret E. Graham. "Content based image retrieval: A report to the JISC technology applications programme." (1999).

(2) Afifi, Ahmed J., and Wesam M. Ashour. "Image retrieval based on content using color feature." International Scholarly Research Notices 2012 (2012).

(3) Nilsback, Maria-Elena, and Andrew Zisserman. "Automated flower classification over a large number of classes." Computer Vision, Graphics & Image Processing, 2008. ICVGIP'08. Sixth Indian Conference on. IEEE, 2008.

(4) Varma, Manik, and Debajyoti Ray. "Learning the discriminative power-invariance trade-off." Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. IEEE, 2007.

(5) Li, Lin, and Yu Qiao. "Flower image retrieval with category attributes." Information Science and Technology (ICIST), 2014 4th IEEE International Conference on. IEEE, 2014.

(6) Kumara, YH Sharath, and D. S. Gurub. "Retrieval of flower based on sketches." Procedia Computer Science 46 (2015): 1577-84.

(7) Long, Fuhui, Hongjiang Zhang, and David Dagan Feng. "Fundamentals of content-based image retrieval." Multimedia Information Retrieval and Management. Springer, Berlin, Heidelberg, 2003. 1-26.

(8) https://stackoverflow.com/questions/4063965/how-can-i-convert-an-rgb-image-to-grayscale-but- keep-one-color.

(9) Stricker, Markus Andreas, and Markus Orengo. "Similarity of color images." Storage and Retrieval for Image and Video Databases III. Vol. 2420. International Society for Optics and Photonics, 1995.

(10) Hazra, Dipankar. "Retrieval of color image using color correlogram and wavelet filters." Proc. of International Conference on Advances in Computer Engineering. 2011.

(11) Singla, Amit, and Meenakshi Garg. "Cbir approach based on combined hsv, auto correlogram, color moments and gabor wavelet." International Journal of Engineering and Computer Science 3.10 (2014).

(12) Yang, Mingqiang, Kidiyo Kpalma, and Joseph Ronsin. "A survey of shape feature extraction techniques." (2008): 43-90.

(13) https://en.wikipedia.org/wiki/Histogram_of_oriented_gradients

(14) https://lyfat.wordpress.com/2012/05/22/euclidean-vs-chebyshev-vs-manhattan-distance/

(15) https://en.wikipedia.org/wiki/Cosine_similarity

(16) http://people.revoledu.com/kardi/tutorial/Similarity/Correlation.html

(17) https://docs.tibco.com/pub/spotfire/7.0.0/doc/html/hc/hc_city_block_distance.htm

(18) https://en.wikipedia.org/wiki/Minkowski_distance

Published
2019-01-01