Identification of Malaria Parasite Patterns With Gray Level Co-Occurance Matrix Algorithm (GLCM)

Annas Prasetio (University Of Potensi Utama Medan)
Rika Rosnelly (University Of Potensi Utama Medan)
Wanayumini (University Of Potensi Utama Medan)

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Vol 6 No 3 (2022): Juni 2022

The results of the test using 5 data of malaria parasite test imagery found that image 1 has an average accuracy value of the energy of 0.55627, homogeneity average of 0.8371, PSNR of 6.1336db, and MSE of 0.24358. Image 2 has an average energy accuracy value of 0.22274, an average Homonegity of 0.98532, a PSNR of 6.1336db, and an MSE of 0.24358. Image 3 has an energy average accuracy value of 0.28735, a Homonegity average accuracy value of 0.9793, a PSNR of 6.133db, and an MSE of 0.24358. Image 4 has an energy average accuracy value of 0.32907 and an average homogeneity accuracy value of 0.97073, PSNR 6.133db, and MSE 0.24358. Image 5 has an average accuracy value of 0.74102, Homonegity average of 0.99844, PSNR of 6.133db, and MSE of 0.4358. Image 6 has an accuracy value of 0.34758 energy, an average accuracy value of homogeneity of 0.99129, a PNSR of 6.133db, and an MSE of 0.24358. Obtained the rule if the average value of energy > = 0.50 then the pattern of malaria parasites is very clear, namely Image 1 and image 5 with a pattern of malaria parasites is very clear.