<![CDATA[The habit of consuming food irregularly is one factor increasing health risks. One solution to make it easier for the public to know, record and monitor the types of food consumed is to create an intelligent system. To support this solution, research is conducted to identify the type of food that will be consumed. The initial stage in making an introduction is to classify these foods. The classification process is done from the value of the feature extraction used. The introduction process begins with the image preproccessing process which is then performed a feature extraction. Feature extraction used is Color Histogram and Gray Level Co-occurrence Matrix. In feature extraction using the Color Histogram using 3 colors namely red, green, blue with each color having the mean, standard deviation, and skewness features. In addition, feature extraction with the Gray Level Co-occurrence Matrix has 6 types of features such as contrast, dissimilarity, homogeneity, angular second moment, energy, and entropy with the angle of taking pixel values ​​0o, 45 o, 90 o, and 135 o. The method applied to classify the value of the feature extraction results can use is the K-Nearest Neighbor method. The results of the average accuracy produced by these methods amounted to 93.33%. This proves that the methods used in this study are able to classify the types of food images.]]>
Copyrights © 2019
