Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer identifies two eyes and a nose of a face in an image. The computer generates a triangle defined by points corresponding to the centers of the eyes and a nose-tip of the face. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first triangle based on the demographic characteristic and a range of a length for at least one side of the first triangle. The computer identifies another image. The second image includes another face with a triangle formed by the eyes and nose of that face that is included in the determined search range for the first triangle. The computer determines at least one potential identity that is associated with the first detected face based on an identity of the second face.

Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer identifies two eyes and a nose of a face in an image. The computer generates a triangle defined by points corresponding to the centers of the eyes and a nose-tip of the face. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first triangle based on the demographic characteristic and a range of a length for at least one side of the first triangle. The computer identifies another image. The second image includes another face with a triangle formed by the eyes and nose of that face that is included in the determined search range for the first triangle. The computer determines at least one potential identity that is associated with the first detected face based on an identity of the second face.

Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer determines a first eye-to-eye distance of a first detected face of a first image, and wherein the eye-to-eye distance is a biometric measurement. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first eye-to-eye distance based, at least in part, on the selection of the demographic characteristic, and the first eye-to-eye distance. The computer identifies a second image from a plurality of images, wherein the second image includes a second eye-to-eye distance that is included in the determined search range for the first eye-to-eye distance. The computer applies a facial recognition algorithm to the second image to determine at least one potential identity that is associated with the first detected face.

Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer determines a first eye-to-eye distance of a first detected face of a first image, and wherein the eye-to-eye distance is a biometric measurement. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first eye-to-eye distance based, at least in part, on the selection of the demographic characteristic, and the first eye-to-eye distance. The computer identifies a second image from a plurality of images, wherein the second image includes a second eye-to-eye distance that is included in the determined search range for the first eye-to-eye distance. The computer applies a facial recognition algorithm to the second image to determine at least one potential identity that is associated with the first detected face.

Abstract: An object detection method can begin with receipt of an ensemble classifier previously trained upon a binary dataset of images for an object. The ensemble classifier can be defined by a list, W, of N weak classifiers, wn for n=1, . . . , N. The ensemble classifier can be trained as a detector for the object using a training dataset of images; each image can have a set of candidates having one or more known ground truth candidates. As a result of training, the weak classifiers can be reordered, based upon performance, into a new list, W?, and a rejection threshold on candidate rank can be assigned for each detection stage. A cascading algorithm can be performed using the trained detector to detect the object in an image having known object candidates. The rejection threshold for a stage of the cascading algorithm can be applied to a rank of the object candidates.

Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer determines a first eye-to-eye distance of a first detected face of a first image, and wherein the eye-to-eye distance is a biometric measurement. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first eye-to-eye distance based, at least in part, on the selection of the demographic characteristic, and the first eye-to-eye distance. The computer identifies a second image from a plurality of images, wherein the second image includes a second eye-to-eye distance that is included in the determined search range for the first eye-to-eye distance. The computer applies a facial recognition algorithm to the second image to determine at least one potential identity that is associated with the first detected face.

Abstract: Embodiments of the present invention disclose a method for facial recognition processing using biometric pre-filters. The computer determines a first eye-to-eye distance of a first detected face of a first image, and wherein the eye-to-eye distance is a biometric measurement. The computer receives a selection of a demographic characteristic. The computer determines a search range for the first eye-to-eye distance based, at least in part, on the selection of the demographic characteristic, and the first eye-to-eye distance. The computer identifies a second image from a plurality of images, wherein the second image includes a second eye-to-eye distance that is included in the determined search range for the first eye-to-eye distance. The computer applies a facial recognition algorithm to the second image to determine at least one potential identity that is associated with the first detected face.