<![CDATA[Ketupat is a unique culture and tradition in Bali. Ketupat is often used as a banten offering. This unique procession of the ketupat war is held once a year to coincide with the Purnama Kapat. The ketupat war is a traditional event with participants throwing ketupat at each other. It aims to be grateful for all the gifts that the Creator has given to humans in this world. This tradition has existed since the 1970s with the beginning of its appearance involving two shirtless men. The ketupat war ceremony is part of the yadnya as the basis for the return of the Tri Rna. In today's era of the development of science and technology, people are only focused on meeting material needs, understanding the meaning of rituals and religious events is decreasing, and it is considered an incriminating or even meaningless activity. In this study, a dataset of 90 was used with 18 types of ketupat used, namely: bagia, batu dam-pulan, bracelet, kale, mattress, kedis, kepel, kroso, lepet, pengambean, sai, cow, sari, sirikan, suna, tulud, tumpeng. This study aims to determine the per-formance of Logistic Regression Classifier by using color, HSV, GLCM and shape features. The dataset used is a typical Balinese ketupat type of 90 data. In this test, 4 test scenarios are used: 1) The first test scenario, the dataset input performs the preprocessing process, HSV imagery, and the color feature extraction process where the output results are in the form of hue, saturation and value values in the form of excel files. 2) The second test scenario, the input dataset performs a preprocessing process, grayscale, and performs the GLCM feature extraction process where the output results are in the form of feature values of angle 00, angle 450, angle 900 and angle 1350 in the form of an excel file. 3) The third test scenario, the dataset input performs the preprocessing process, binner, performs the form feature extraction process where the output results are in the form of metric, eccentricity in the form of excel files. 4) The fourth test scenario, from the 3 (three) feature extractions carried out, the new dataset, the next stage is to implement the Logistic Re-gression classifier method to obtain accuracy values. Based on the results of the classification, testing and analysis, the level of accuracy from each of them was obtained with a training accuracy value of 69.84% and a testing accuracy of 22.2%, which means that the classification method was declared ineffective in analyzing the features used in the ketupat classification, so it is necessary to compare it with other methods so that it gets an accuracy result above 90%.]]>
