Scientists from the Chinese research Institute has created software capable of determining the biological age.
For this program you need to upload the photo of the person. Functions of the software by a unique algorithm is guaranteed to be without error, and without determining the exact age with the use of common reference points. The first results of its research, Chinese scientists have already shared on the pages of the publishing house "Cell".
Under the statement of the scientists themselves, in the process of human aging change only external quality, and bare body shape. For all these processes is due to the fact that the bones with the onset of the aging process become less rigid, cartilage narrowing and calcium is released.
and http://gallery.azureml.net/MachineLearningAPI/b0b2598aa46c4f44a08af8891e415cc7
Well ! Don’t guess the age od a person from the FACE. Face can be deceptive. Facial age and biological / chronological age do not go togather in most cases. Facial age / biological age are dependent on genetics and environment. Some people may look younger than their chronological age and vice versa. This is due to their genetic endowment. Extreme case is of Progeria in which gene(s) alone make a person of 6 years look like a person of 60. This is early aging in which biological clock is running faster than chronological clock
People who cares about their looks and take care of their face through crèmes, etc., may look younger. They feel happy but they cannot cheat the chronological age. Their body is aging slowly or fastly according to their genetic makeup. This is our genetic fate.
Unsure re: software for identifying age by one's face. Though another way to measure age is to purely listen to one's voice. This tends to be an excellent indicator of age. Best wishes with your research.
V. Carletti, A. Greco, G. Percannella, and M. Vento,"Age from faces in the deep learning revolution,"IEEE Transactions on Pattern Analysis and Machine Intelligence, p. In press, 2019, [Online] Available: https://ieeexplore.ieee.org/document/8686239