Embodiments of the present disclosure include systems and methods for identifying people in an image that contains more than one face images. In embodiments, a query feature vector that represents features is extracted from each face image. In embodiments, each query feature vector is compared to image feature vectors in a database and a set of candidate vectors is selected among the image feature vectors. Then, a set of user accounts that is associated with the set of candidate vectors is selected. The strengths of connection in a network between user accounts in a set of candidate user accounts corresponding to a face image and user accounts in a different set of candidate user accounts corresponding to a different face image may be determined. In embodiments, user accounts that has the highest strength of connection are selected and used to identify the persons corresponding to the face images.