One of the important parts that ensures the availability of electrical energy supplies which takes place from the central power plant and then through the transmission line to distribution to the load is the insulator. However, over time, insulators can experience anomalies such as corrosion. Insulator corrosion can be caused by many environmental factors, including pollution, humidity, high temperatures and exposure to chemicals. Previously, maintenance personnel usually identified the level of corrosion on insulators visually by using their knowledge and experience through routine inspection activities to check the condition of the insulators. This technique, however, takes a long time and is often subjective. Therefore, in this research, the way to detect the degree of corrosion on insulators is by using image processing and using active contour segmentation to determine the degree of corrosion on insulators and using decision trees as a method to create a classification model for the degree of corrosion. This can help reduce reliance on subjective human judgment, increase the effectiveness of the recognition process, and optimize overall isolator maintenance efforts. The application created in this research has a user interface that makes it easier to process images of corrosion insulators. The front page, practice page, and test page comprise this interface. Meanwhile, the results of classification using a decision tree for the low category are in the ratio x1 < 0.082104, the medium category is in the ratio 0.082104 =< x1 < 0.15061, and the high category is in the ratio x1 >= 0.15061 with an accuracy result obtained of 93.33% for test image data and recall and precision values obtained 100% results.