公开(公告)号：US11854301B1

公开(公告)日：2023-12-26

申请号：US18296807

申请日：2023-04-06

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Manoj Aggarwal ,  Brad Musick ,  Gerard Guy Medioni ,  Rui Zhao ,  Zhen Han

IPC: G06V40/12 ,  G06V40/50 ,  G06V40/13

CPC classification number: G06V40/1394 ,  G06V40/1312 ,  G06V40/1318 ,  G06V40/1388 ,  G06V40/50

Abstract: A person may attempt to gain access to a facility via transaction data, such as images of a hand of the person or other identifying information as acquired by an input device. Possible fraud may be detected by comparing the transaction data with previously stored exclusion data. The exclusion data may include known bad data or synthetic trained data for detecting possible fraud. If the biometric input matches or is similar to the exclusion data, possible fraud is detected and the person is prompted for additional data. The reply data acquired from the person is compared with the exclusion data to determine if possible fraud is still detected. If so, additional prompts are presented to the person until the reply data provides enough confidence of no fraud or until the transaction is terminated.

公开(公告)号：US11804060B1

公开(公告)日：2023-10-31

申请号：US17443365

申请日：2021-07-26

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Rui Zhao ,  Manoj Aggarwal ,  Gerard Guy Medioni ,  Dilip Kumar

IPC: G06V40/10 ,  G06F18/21 ,  G06F18/2415 ,  G06V40/14

CPC classification number: G06V40/107 ,  G06F18/2193 ,  G06F18/2415 ,  G06V40/10 ,  G06V40/117 ,  G06V40/14

Abstract: A pair of input images acquired using a first modality and a second modality is processed using a multi-classifier trained to determine classification data indicative of whether the pair is normal or abnormal. A pair may be deemed abnormal if one or both input images are obscured or inconsistent with one another. Training data comprising normal and abnormal images are used to train the multi-classifier. During training, the multi-classifier uses an objective function that includes cross entropy loss, distance loss, and discrepancy loss to process the training data. During use, the trained multi-classifier processes a pair of input images. If the resulting classification data indicates the pair of input images are normal, the pair of input images may be processed to assert an identity.

公开(公告)号：US12277794B1

公开(公告)日：2025-04-15

申请号：US17303623

申请日：2021-06-03

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Baomin Wang ,  Umer Shahid ,  Tianyi Wang ,  Georgios Skolianos ,  Rui Zhao ,  Manoj Aggarwal ,  Gerard Guy Medioni

IPC: G06V10/141 ,  G06V10/143 ,  G06V10/56 ,  G06V40/10

Abstract: An input device determines presence of an actual user, instead of an artifact, by using multi-wavelength reflectance spectroscopy. Light sources are operated to illuminate an object with different colors of light at different times. A detector determines, at those different times, intensity data indicative of intensity light of these different colors as reflected from the object. The intensity data is processed to determine whether the object is part of a user or is an artifact. For example, if the object is deemed to be a user, biometric input may be acquired. The biometric input may then be processed to identify the user. The input device may be used at various locations, such as at an entry portal, point of sale, and so forth.

公开(公告)号：US11625947B1

公开(公告)日：2023-04-11

申请号：US16807976

申请日：2020-03-03

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Manoj Aggarwal ,  Brad Musick ,  Gerard Guy Medioni ,  Rui Zhao ,  Zhen Han

IPC: G06K9/00 ,  G06V40/12 ,  G06V40/50 ,  G06V40/13

Abstract: Biometric input, such as images of a hand obtained by a biometric input device, may be used to identify a person. An attacker may attempt to gain access by presenting false biometric data with an artificial biometric model, such as a fake hand. During a suspected attack, the attacker is prompted for additional data. For example, email address, telephone number, payment information, and so forth. This provides additional information about the attack while prolonging the time spent by the attacker on the attack. Information explicitly indicating failure is delayed or not presented at all. Data associated with an attack is placed into an exclusion list and further analyzed to recognize and mitigate future attacks. A subsequent attempt that corresponds to exclusion data proceeds with presenting prompts, gathering further information and consuming more of the attacker's time and resources.