<![CDATA[Image or image recognition has quite complex stages so that the computer is able to recognize what objects to identify, there are several stages used in the image processing process, image extraction data input and image classification, this study will examine the extent to which the algorithm for extraction have an influence on the final classification results. This study uses the image of chili as a test material and the results of the test are the introduction of chili with 4 levels, ripe, half cooked, raw and rotten. This study also uses tools to perform the image recognition process. The image recognition method used in this study is Hue Saturation Value (HSV) Gray Level Co-occurrence Matrix (GLCM) and Learning Vector Quantization (LVQ3) for classification, in the process it will be tested. With 2 image recognition scenarios, the first method uses GLCM and LVQ3, the second scenario uses HSV GLCM and LVQ3. The results of this study are to see how much influence HSV has on the digital image recognition process of chili, the extraction results using GLCM extraction LVQ3 classification is 59.58%, and the results of LVQ3 classification using HSV and GLCM extraction yields 93.58%. In conclusion, the HSV extraction method provides an additional 34% accuracy compared to using only GLCM as the extraction method]]>
Copyrights © 2021
