Acne is a skin disease that most often grow in the face and very disruptive to affect the appearance of a person's face. Viola Jones is one method to help detect acne so someone get information about the state of the face and immediately overcome. Viola Jones Method has three main processes integral image is used to determine whether there is a feature haar particular in an image, the method adaboost machine learning is used to select features haar specific that will be used to adjust the threshold value, and a cascade classifier as the classification of the final determining regions the face in the picture. Testing of 30 samples, the results obtained showed that the method is less accurate Viola Jones is used as a method of detection of acne with results average 25 % the percentage of common acne, blackheads 0 % and 45% of cystic acne. The number of samples used to create xml greatly affect the results of detection.