Support Vector Machine Untuk Klasifikasi Citra Jenis Daging Berdasarkan Tekstur Menggunakan Ekstraksi Ciri Gray Level Co-Occurrence Matrices (GLCM)
Abstrak: Texture is one of the
most important features for image analysis, which provides informations such as
the composition of texture on the surface structure, changes of the intensity,
or brightness. Gray level co-occurence matrix (GLCM) is a method that can be
used for statistical texture analysis. GLCM has proven to be the most powerful
texture descriptors used in image analysis. This study uses the four-way GLCM
0o, 45o, 90o, and 135o. Support vector machine (SVM) is a machine learning that
can be used for image classification. SVM has a high generalization capability
without any requirement of additional knowledge, even with the high dimension
of the input space. The data used in this study are the image of goat meat,
buffalo meat, horse meat, and beef with shooting distance 20 cm, 30 cm and 40
cm. The result of this study shows that the best recognition rate of 87.5% was
taken at a distance of 20 cm with neighboring pixels distance d = 2 in the
direction GLCM 135o.
Penulis: Neneng, Kusworo Adi,
Rizal Isnanto
Kode Jurnal: jptinformatikadd160410
