Heart disease is the main cause of the death. Some modern examination methods in hospitals need a lot of money for this disease. So there is Iridology, one of the popular alternative ways to have a preliminary detection for the condition of organs. Many studies before that combine this method with the computation system. This research proposes a new model for detecting the heart abnormalities through iris based on mobile with several phases of the process, such as capturing based on target, pre-processing, auto crop based on a histogram analysis, heart area extraction feature and classification using thresholding algorithm. This detection is conducted on images taken by the camera of a mobile device and the testing process is carried out on a mobile device. The technique used to capture the iris has affect to the cropping method and the classification process. This experiment is assisted by the iridology expert in Surabaya Mugi Barokah Clinic. The system performance produces 86.66% precision. Some mistakes happen due to the unsuccessful cropping results. The unsuccessful result will impact the segmentation process and the result of segmentation in the heart area.