Strabismus Classification Using Face Features

Strabismus is one of the most common vision diseases that would cause amblyopia and even permanent vision loss. Timely diagnosis is crucial for well treating strabismus. In contrast to manual diagnosis, automatic recognition can significantly reduce labor cost and increase diagnosis efficiency. This paper present a completely automatic strabismus detection system using face features. It is based on automatically analyze the degree of left and right symmetry of the patient face measurements. To achieve that was created a special model, using Active appearance model (AAM) algorithm that detected face landmarks that were used for calculation strabismus features slope differences.