Amazon Technologies, Inc.

Other

Gerard Guy Medioni

Dilip Kumar

Manoj Aggarwal

Jayakrishnan Kumar Eledath

Nishitkumar Ashokkumar Desai

Igor Kviatkovsky

Ehud Benyamin Rivlin

Liefeng Bo

Roman Goldenberg

Kushagra Srivastava

Nadav Israel Bhonker

Prithviraj Banerjee

Nikhil Chacko

Alon Shoshan

Ofer Meidan

Paul Eugene Munger

Jean Laurent Guigues

George Leifman

Pahal Kamlesh Dalal

Rajeev Ranjan

Robert Crandall

Gopi Prashanth Gopal

Lior Zamir

Kartik Muktinutalapati

Hoi Cheung Pang

Miriam Farber

Gang Hua

Daniel Bibireata

Amit Adam

Jaechul Kim

Dmitri Veikherman

Rui Zhao

Ohil Krishnamurthy Manyam

Ramanathan Palaniappan

Michel Leonard Goldstein

Navid Shiee

Tian Lan

Leonid Pishchulin

Fan Sun

Chuhang Zou

Shaonan Zhang

Boris Cherevatsky

Brad Musick

Zheng Tang

Hui Liang

Korwin Jon Smith

Joseph Patrick Tighe

Connor Spencer Blue Worley

Behjat Siddiquie

Robert Matthias Steele

Yacov Hel-Or

Alessandro Bergamo

Vuong Van Le

Petko Tsonev

Natan Peterfreund

Baomin Wang

Claire Law

Kaustav Kundu

Samuel Nathan Hallman

Eli Osherovich

Sora Kim

Marian Nasr Amin George

Lu Xia

Rakesh Ramakrishnan

Kostia Robert

Geoffrey A Franz

Zhen Han

Paul Ignatius Dizon Echevarria

Matthew Fletcher Harrison

Lavisha Aggarwal

Xiaoyu Miao

Li Guan

Nikolai Orlov

Jordan Tyler Williams

Abhinav Kashyap

Oron Anschel

Philip Pinette

Monti R Wilson

Chris Broaddus

Keunhong Park

Umer Shahid

Georgios Skolianos

Tianyi Wang

Yevgeni Nogin

Gal Novich

Shunit Haviv

Ning Xu

Benjamin James Biggs

Scott Chenghui Sun

Charu Kothari

Achal Dushyant Dave

Caitlin Isaac Cagampan

Maxim Berman

Chad Desjardins

Joshua Engelsma

Carlos D Castillo

Haichao Zhang

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

This disclosure describes techniques for updating planogram data associated with a facility. The planogram may indicate inventory locations within the facility for various types of items supported by product fixtures. In particular an image of a product fixture is analyzed to identify image segments corresponding to product groups, where each product group consists of instances of the same product and each image segment corresponds to a group of image points. Image data is further analyzed to determine coordinates of the points of each image segment. A product space corresponding to the product group is then defined based on the coordinates of the points of the product group. In some cases, for example, a product space may be defined in terms of the coordinates of the corners of a rectangular bounding box or volume.

Image-based detection of planogram product spaces

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

Techniques for a service provider network to manage a meeting between individuals located in a conference room with one or more other individuals remote from the conference room are discussed herein. An Enterprise system can implement one or more machine learned models to generate tiles that represent different individuals associated with a meeting. A same or different machine learned model can automatically arrange a series of tiles for display that, when presented collectively, promotes inclusiveness and attention for both in-room and remote participants of the meeting. The meeting management techniques can include determining which content to include on a display device based on evaluating changes in behavior of the meeting participants over time.

Determination of meeting content for display by an enterprise system

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

Cameras having storage fixtures within their fields of view are programmed to capture images and process the images to determine whether such images depict an interaction by an actor with one of the storage fixtures. If a camera determines that an actor is present within imaging data captured thereby, the camera generates feature tensors from images captured over a predetermined period of time and pools the feature tensors into features corresponding to locations of the respective storage units of the actor within such images. Cameras provide pooled features to a multi-camera system that processes the pooled features to determine whether an interaction occurred at a storage unit, and to update a record of items associated with the actor accordingly.

Detecting events by streaming pooled location features from cameras

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

Multiple video files that are captured by calibrated imaging devices may be annotated based on a single annotation of an image frame of one of the video files. An operator may enter an annotation to an image frame via a user interface, and the annotation may be replicated from the image frame to other image frames that were captured at the same time and are included in other video files. Annotations may be updated by the operator and/or tracked in subsequent image frames. Predicted locations of the annotations in subsequent image frames within each of the video files may be determined, e.g., by a tracker, and a confidence level associated with any of the annotations may be calculated. Where the confidence level falls below a predetermined threshold, the operator may be prompted to delete or update the annotation, or the annotation may be deleted.

Multi-video annotation

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 method includes generating a virtual model of a human body based at least in part on a selected image of the human body and generating a segment of an article of clothing based at least in part on a selected image of the article of clothing. The method also includes generating a layer mask indicating whether a plurality of output pixels of an output image should be produced according to the image of the human body, the image of the shirt, or the image of the pair of pants and producing the plurality of output pixels of the output image according to the layer mask. The output image shows the article of clothing on the human body in the selected image of the human body.

Method and system for outfit simulation using layer mask

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

Growing community of inventors

Seattle, WA, United States of America

Gerard Guy Medioni