Amazon Technologies, Inc.

Manoj Aggarwal

Gerard Guy Medioni

Dilip Kumar

Igor Kviatkovsky

Nadav Israel Bhonker

Alon Shoshan

Korwin Jon Smith

Prithviraj Banerjee

Rajeev Ranjan

Jordan Tyler Williams

Lior Zamir

Jason Garfield

Rui Zhao

Dmitri Veikherman

Miriam Farber

Brad Musick

Zheng Tang

George Leifman

Natan Peterfreund

Baomin Wang

Sora Kim

Zhen Han

Lavisha Aggarwal

Roman Goldenberg

Nikolai Orlov

Abhinav Kashyap

Umer Shahid

Georgios Skolianos

Yevgeni Nogin

Tianyi Wang

Jiuhong Xiao

Divyansh Aggarwal

Adam Botach

Shunit Haviv Hakimi

Oron Anschel

Ori Linial

Quanfu Fan

Hongcheng Wang

Carlos D Castillo

Joshua Engelsma

Chad Desjardins

Shunit Haviv

Gal Novich

During operation a biometric identification system acquires an image of at least a portion of a user that is processed by a representation model to determine representation data. The representation data may be securely stored for later use. The image is not stored. The stored representation data is smaller than equivalent image data. The representation model may comprise a subset of a first recognition model that has been trained using image training data. The image training data may be processed by the trained representation model to determine training representation data. The representation data contains sufficient information to be used as training data for recognition models, instead of acquired images. Training of recognition models using representation data is more computationally efficient compared to training with image data. Recognition comparisons using query representation data are more computationally efficient compared to query image data.

Storable representation of biometric data

A biometric identification system uses inputs of a user that are acquired using different modalities. A model having an intersection branch is trained to determine an embedding using features present in two or more modalities (an intersection of modalities). A first input acquired using a first modality is processed by the model to determine a first embedding. A second input acquired using a second modality is also processed by the model to determine a second embedding. Comparison of the first embedding and the second embedding may be used to determine if the first input and the second input are associated with the same user.

System for multi-modality mismatch determination

An image of at least a portion of a user during enrollment to a biometric identification system is acquired and processed with a plurality of models to determine embeddings that are representative of features in that image in respective embedding spaces. Transformers are trained to accept as input an embedding from a respective model and produce as output a transformed embedding consistent with a common embedding space. These transformed embeddings are aggregated to produce transformed aggregated embedding data and stored for later comparison to identify the user. Subsequently, one or more embedding models may be used to process a query image to determine a query embedding. The query embedding may be transformed into the common embedding space for comparison.

System to reduce data retention using aggregated embedding data

A biometric identification system acquires an image of at least a portion of a user that is processed by an embedding model. Additional training of the embedding model is performed using selected training data. In one implementation, the selected training data is determined based on similarity to embedding data acquired during operation. For example, a query image is processed to determine query embedding data. If the query embedding is deemed to be a close match to embedding data of a previously enrolled user, additional synthetic training data that is also similar to the query embedding data is selected for use in subsequent training. In another implementation, enrolled user data may be analyzed to find close matches to synthetic training data, from which selected training data is determined. Use of the additional synthetic training data facilitates the subsequent training in distinguishing between similar instances of embedding data.

System to determine biometric identification training data

During enrollment to a biometric identification system an image of at least a portion of a user is acquired and processed to determine a compact representation (CR). The CR may be stored for later comparison to identify the user, to train embedding models, and so forth. The image is not stored. A machine learning system that comprises a variational autoencoder is trained to produce the CR with a loss function that includes a distortion loss, an embedding distance loss, and in some implementations a bitrate loss. The trained encoder is used to determine the CR from an input image, while the decoder is not stored. The CR contains sufficient information to be used as training data for embedding models, instead of acquired images. Training may be more computationally efficient using the CR. Recognition comparisons may be more efficiently performed using the CR, compared to query images.

System to determine compact representation of data

A biometric identification system may store biometric data for later assessment. Data storage parameters, such as cryptographic keys used to encrypt and decrypt the biometric data, may be determined based on the biometric data. In one implementation, the biometric data comprises embedding data in an embedding space. During enrollment and storage, the embedding data is assessed to determine nearest anchor data in the embedding space. Cryptographic parameters, such as an encryption key, are determined based on 'k' anchor data that are within a threshold distance of the embedding data in the embedding space. During query, query embedding data is similarly processed to determine cryptographic parameters, such as a decryption key. The decryption key may then be used to attempt decryption of the encrypted at-rest biometric data. If successful, the decrypted biometric data may then be compared to the query embedding to assert an identity.

System for determining storage parameters for biometric data

A user performs an enrollment process to utilize a biometric identification system. This includes acquisition of biometric input data. Accuracy of subsequent identification is improved by utilizing high quality input data during enrollment. Input data is processed using a plurality of embedding models to determine a plurality of embedding vectors. These embedding vectors are translated into a common embedding space. Input quality may be determined based on analysis of these embedding vectors. For example, if a mean distance of the translated embedding vectors is less than a threshold value, the input data may be deemed to be of sufficient quality for use to complete an enrollment process. This analysis may also be used for post-enrollment operation, such as during an identification process to determine query input data that is of insufficient quality.

System to assess biometric input data

This disclosure describes a user-recognition system that may perform one or more verification methods upon identifying a previous image that matches a current image of a palm of a user. For instance, the user-recognition system may perform the verification method(s) as part of the recognition method (e.g., after recognizing a matching image), in response to an audit process, in response to a request to re-analyze the image data (e.g., because a user indicates that he or she was not associated with a particular purchase or shopping session), and/or the like.

Utilizing sensor data for automated user identification

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.

System to determine user presence

Maintaining the security of biometric data is an utmost priority. Biometric data is secured using one or more techniques. With one technique, biometric input such as images of a user's palm is used to generate first primary data (PD). The original biometric input is deleted from temporary secure storage while the first PD is securely stored. The first PD may then be processed later to determine a second PD. The first PD may then be deleted, and the second PD subsequently used. With another technique, biometric input or a PD may be processed by a first model to determine first secondary data (SD) that is representative of features of a particular user within a first embedding space. Later the PD may be processed by a second model to determine a second SD in a second embedding space. The first SD is deleted, and the second SD subsequently used.

System to manage biometric data

User enrollment to a biometric identification system begins on selected general input devices (GID) such as smartphones. The user may enter identification data (e.g. name) and use a red-green-blue (RGB) camera of the GID to acquire a first image (e.g. hand). The first image is processed using both a first model to determine a first representation and a second model to determine a second representation. Upon presentation of a hand at a biometric input device, a second image is acquired using a first modality and a third image is acquired using a second modality. The second image is processed using the first model to determine a third representation. The third image is processed using the second model to determine a fourth representation. Given a match between both the first and third representations, as well as the second and fourth representations, enrollment is completed by storing the third and fourth representations.

Multi-device enrollment for biometric identification system

This disclosure describes techniques for identifying users that are enrolled for use of a user-recognition system and updating enrollment data of these users over time. To enroll in the user-recognition system, the user may initially scan his or her palm. The resulting image data may later be used when the user requests to be identified by the system by again scanning his or her palm. However, because the characteristics of user palms may change over the time, the user-recognition system may continue to build more and more data for use in recognizing the user, in addition to removing older data that may no longer accurately represent current characteristics of respective user palms.

Images of a hand are obtained by a camera. A pose of the hand relative to the camera may vary due to rotation, translation, articulation of joints in the hand, and so forth. Avatars comprising texture maps from images of actual hands and three-dimensional models that describe the shape of those hands are manipulated into different poses and articulations to produce synthetic images. Given that the mapping of points on an avatar to the synthetic image is known, highly accurate annotation data is produced that relates particular points on the avatar to the synthetic image. An artificial neural network (ANN) is trained using the synthetic images and corresponding annotation data. The trained ANN processes a first image of a hand to produce a second image of the hand that appears to be in a standardized or canonical pose. The second image may then be processed to identify the user.

System for mapping images to a canonical space

Enhanced training data representative of possible inputs is used to train a machine learning system. For example, a machine learning system to determine identity based on an image of a human palm may be trained using enhanced training data comprising images. The enhanced training data may comprise source images that have been modified to appear to depict synthetic artifacts that attempt to simulate human palms, augmented images of dirty hands, and so forth. A synthetic artifact image may be produced by selectively removing some data from a source image. An augmented image may be produced by selectively blending the source image with features extracted from sample images. These images may then be used as training data to train the machine learning system.

System for generating enhanced training data

A biometric identification system acquires a multimodal image. The system is trained to determine three embeddings: a first embedding associated with features present in a first modality, an intersection embedding associated with features present in both the first and a second modality, and an XOR embedding associated with features that are not shared between the first modality and the second modality. Once trained, the system may process a multimodal query image to determine query embedding data. Additional information, such as minutiae depicted in the multimodal query image may also be determined. The query embedding data, and in some implementations the additional information, may be compared with enrolled embedding data associated with a previously enrolled user. If the comparison exceeds a threshold value, an identity may be asserted.

Growing community of inventors

Seattle, WA, United States of America

Manoj Aggarwal