Pain is an unpleasant emotional experience caused by tissue damage. Pain is subjective, where each individual has a different pain response, sometimes difficult to express and can only be felt by the individual without being felt by others. Therefore, the assessment of pain for each treatment by medical personnel can be different. This could lead to non-standard handling of patients in pain medical treatment. The automatic stand alone system for pain detection based on face recognition is developed. The system determines patient paint level detector based on facial expression recognition. The face detection is based on face image procession technique and Convolution Neural Network (CNN). The system is working properly, since it resulting the training and testing accuracy of 90% and 70%, respectively.