PERBANDINGAN KOMBINASI METODE EKTRAKSI FITUR BENTUK DAN WARNA PADA CONTENT BASED IMAGE RETRIEVAL BUSANA MUSLIMAH

Cut Mutia

Abstract


Content Based Image Retrieval (CBIR) is an image search technique by using image content as a query. The imagery or often referred to as features consists of features of shapes, colors and textures. In this study, we combined two features namely shape features and color features. This article, describes a combination of extraction methods of shape and color features and looks at the performance level of the combination of such features in CBIR Busana Muslimah. The experiment was applied to 180 image datasets consisting of groups of blouses, shirts and outerwear. Each fashion group has 30 red imagery and 30 blue imagery. There are 2 combinations of features that we do, namely, (1) a combination of PHOG and DCD methods, (2) a combination of HOG and DCD methods. The performance results of the combination method are measured by recall, precision, and f-measure. The measurement resulted in a better combination of PHOG and DCD with a 11 – 26% percentage increase for the blouse-pants and gamis fashion group, as well as 2% for the outerwear group

 

Kata kunci: CBIR, Feature, PHOG, HOG, DCD


References


Y. Dhyanti, K. Munadi, and F. Arnia, “Penerapan Deskriptor Warna Dominan untuk Temu Kembali Citra Busana pada Peranti Bergerak,” J. Rekayasa Elektr., vol. 12, no. 3, p. 104, 2016, doi: 10.17529/jre.v12i3.5701.

A. F. Dewi, F. Arnia, and R. Muharar, “Effectiveness of MPEG-7 color features in clothing retrieval,” Bull. Electr. Eng. Informatics, vol. 6, no. 2, pp. 166–173, 2017, doi: 10.11591/eei.v6i2.619.

A. Bosch, A. Zisserman, and X. Munoz, “Representing shape with a spatial pyramid kernel,” Proc. 6th ACM Int. Conf. Image Video Retrieval, CIVR 2007, pp. 401–408, 2007, doi: 10.1145/1282280.1282340.

N. C. Yang, W. H. Chang, C. M. Kuo, and T. H. Li, “A fast MPEG-7 dominant color extraction with new similarity measure for image retrieval,” J. Vis. Commun. Image Represent., vol. 19, no. 2, pp. 92–105, 2008, doi: 10.1016/j.jvcir.2007.05.003.

Z. R. Tan, S. Tian, and C. L. Tan, “Using pyramid of histogram of oriented gradients on natural scene text recognition,” 2014 IEEE Int. Conf. Image Process. ICIP 2014, pp. 2629–2633, 2014, doi: 10.1109/ICIP.2014.7025532.

N. V. Shirahatti and K. Barnard, “Evaluating image retrieval,” Proc. - 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognition, CVPR 2005, vol. I, pp. 955–961, 2005, doi: 10.1109/CVPR.2005.147.


Refbacks

  • There are currently no refbacks.