CBIR Penyakit Kulit dengan Metode Co-Occurrence Matrix dan Color Moments

Ni Putu Chendy Widya Santi (Program Studi Teknologi Informasi Universitas Udayana Bukit Jimbaran, Bali, Indonesia)
I Ketut Gede Darma Putra (Program Studi Teknologi Informasi Universitas Udayana Bukit Jimbaran, Bali, Indonesia)
I Made Sunia Raharja (Program Studi Teknologi Informasi Universitas Udayana Bukit Jimbaran, Bali, Indonesia)

Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi)
Vol. 5, No. 2 Agustus 2017

Content Based Image Retrieval (CBIR) is a technique for searching images from database based on information from the image which developed because the technique based on text-based is less effective for represent an image. CBIR skin disease in this research use 12 sample of skin disease images such as Acne, Acropustulosis, Alopecia, Dermatitis, Hemangioma, Herpes, Ichtyosis, Molluscum, Nummular, Skin Tag, Urticaria, and Vitiligo. Method use for this research is for extraction texture feature and color feature from a skin disease image. Texture feature is using co-occurrence Matrix which compute energy, contrast, entropy, homogeneity, and correlation until vector texture result. Extraction color use color moments to compute color space using three moments which result color feature from color distributions such as mean, standard deviation, and skewness. Final result showed the comparison of similarity computation of two methods is the acuration of Color Moments method is more robust than Co-occurrence Matrix Method for skin disease images.