Klasifikasi Mamalia Berdasarkan Bentuk Wajah Dengan k-NN Menggunakan Fitur CAS dan HOG

  • Muhammad Ezar Al Rivan STMIK Global Informatika MDP
  • Yohannes Yohannes STMIK Global Informatika MDP
Keywords: Context Aware Saliency, Histogram of Oriented Gradient, K-Nearest Neighbors, Mammals, Classification

Abstract

Object classification has been done to various images. Animal classification has been done using segmentation and non-segmentation approach as initial stage. Context Aware Saliency (CAS) is a method that able to make the object area more dominant than the background in saliency mode so that it can be an alternative object segmentation process. The shape feature will taken based on saliency results using the Histogram of Oriented Gradient (HOG). The K-Nearest Neighbors (K-NN) used to classify mammal species based on HOG features from saliency images. The dataset used in this study is LHI-Animal-Faces. The results obtained show that animal species that can be recognized well are cats and tigers, while sheep, dogs, and pigs have not been able to be recognized properly.

References

[1] M. N. Alli and S. Viriri, “Animal identification based on footprint recognition,” IEEE Int. Conf. Adapt. Sci. Technol. ICAST, 2013.

[2] Z. Cao, J. C. Principe, B. Ouyang, F. Dalgleish, and A. Vuorenkoski, “Marine Animal Classification Using Combined CNN and Hand-designed Image Features,” Ocean. 2015 - MTS/IEEE Washingt., pp. 2–7, 2015.

[3] N. Manohar, Y. H. S. Kumar, and G. H. Kumar, “Supervised and unsupervised learning in animal classification,” 2016 Int. Conf. Adv. Comput. Commun. Informatics, ICACCI 2016, pp. 156–161, 2016.

[4] Y. H. S. Kumar, N. Manohar, and H. K. Chethan, “Animal classification system: A block based approach,” Procedia Comput. Sci., vol. 45, no. C, pp. 336–343, 2015.

[5] S. Taheri and Ö. Toygar, “Animal classification using facial images with score-level fusion,” IET Comput. Vis., vol. 12, no. 5, pp. 679–685, 2018.

[6] S. Goferman, L. Zelnik-Manor, and A. Tal, “Context-Aware Saliency Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 10, pp. 1915–1926, Oct. 2012.

[7] Z. Si and S. Zhu, “Learning Hybrid Image Templates (HIT) by Information Projection,” IEEE Trans. Pattern Anal. Mach. Intell., pp. 1354–1367, 2012.

[8] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 2005, vol. I, pp. 886–893.

[9] J. P. Jose, P. Poornima, and K. M. Kumar, “A novel method for color face recognition using KNN classifier,” 2012 Int. Conf. Comput. Commun. Appl. ICCCA 2012, 2012.
Published
2019-03-09
Section
Articles