The relationship between gray value of pixels and macro-information in image has been analyzed with the method in statistical mechanics. After simulating and curve fitting with the experiment data by statistic and regression method, an adaptive threshold model between average gray value and image threshold has been proposed in terms of Boltzmann statistics. On the other hand, the image characteristics around the eye region and the states of eyeball also have been analyzed, and an algorithm to extract the eye feature and locate its position on the image has been proposed, furthermore, another algorithm has been proposed to find the iris characteristic line and then to coordinate the iris center. At last, considering the cases of head gesture, different head position, and the opening state of eyes, some experiments have been respectively done with the function based on the adaptive threshold model and the designed algorithms in eye-gaze input human-computer interaction (HCI) system. The experiment results show that the algorithms can widely be applied in different cases, and real-time iris tracking can be performed with the adaptive threshold model and algorithms.
The characteristics of the vision-based human-computer interaction system have been analyzed, and the practical application and its limited factors at present time have also been mentioned. The information process methods have been put forward. In order to make the communication flexible and spontaneous, the algorithms to adaptive control of user’s head movement has been designed, and the events-based methods and object-oriented computer language is used to develop the system software, by experiment testing, we found that under given condition, these methods and algorithms can meet the need of the HCI.
A kind of eye-gaze input sensing model based on the pupil’s relative offset to the reflection point on the cornea (Purkinje spot) from an assistant infrared light source in front of the user’s head, has been completely set up. A set of control strategy that can adapt to the user’s head movement, has also been put forwards. It can effectively overcome the difficulties existing in the similar systems that the user’s head should be stationary or just allowed a little movement while the system works. Therefore it is a spontaneous and harmonious human-computer interaction system. Moreover, this system has the obvious merits such as convenient to use, non-contact, non-wear, non-interference, non-restraint, and so on. An experiment eye-gaze input platform for human-computer interaction has been built, and the sensing and controlling model have been verified.