<![CDATA[The level of development of human growth depends on food consumed daily. The good condition of the human body comes from healthy and hygienic food. Recognizing a food becomes a problem for visitors or tourists who are visiting a food place that has no known nutrient levels and ingredients. To overcome this problem, research needs to be done to classify a food image. Morphological Shape Descriptors (MSD), Color Moments (CM), and Gray Level Co-ocurence Matrix (GLCM) features with Haralick have been shown to produce good features for classification. The Neighbor Weight K-Nearest Neighbor method is also an alternative to the image classification process.Based on the test results from k-fold cross validation with k = 10 and the evaluation method in the form of accuracy, obtained maximum accuracy of 0.86 with parameter values ​​E = 11 and k = 3 in the case of training data amounting to 530 images of single food which has been pre-processing. This shows that the classification of food images based on the extraction of textural features such as form (MSD), color (CM), and texture (GLCM) results in relatively better accuracy. In addition, the combination of the use of these three features affects the results of accuracy. This is indicated by testing which shows that the results of relative accuracy are better achieved in features of a combination of textures, shapes, and colors.]]>
Copyrights © 2019
