Amazon Technologies, Inc.

Oron Anschel

Shai Mazor

Rahul Bhotika

Stefano Soatto

Amit Adam

Hadar Averbuch Elor

Or Perel

Andrea Olgiati

Shahar Tsiper

Wendy Tse

Gal Sabina Star

Gerard Guy Medioni

Dilip Kumar

Manoj Aggarwal

Raghavan Manmatha

Igor Kviatkovsky

Jonathan Wu

Nadav Israel Bhonker

Alon Shoshan

Ron Litman

Roee Litman

Omri Ben-Eliezer

Divyansh Aggarwal

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

Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual feature sequence from the extracted features; performing selective contextual refinement at least one selective contextual refinement block of a stack of selective contextual refinement blocks to generate a text prediction by: generating a contextual feature map and combining the contextual feature map with the visual feature sequence into a visual feature space, and applying a selective decoder that utilizes a two-step attention on the visual feature space to generate a text prediction, wherein the two-step attention includes performing a 1-D self-attention computation to generate attentional features and decoding the attentional features to generate the text prediction; and outputting the generated text prediction.

Residual context refinement network architecture for optical character recognition

Techniques for auto-generation of annotated real-world training data are described. An electronic document is analyzed to determine text represented in the document and corresponding locations of the text. A representation of the electronic document is modified to include markers and printed. The printed document is photographed in real-world environments, and the markers within the digital photographs are analyzed to allow for the depiction of the document within the photographs to be rectified. The text and location data are used to annotate the rectified images.

Auto-annotation techniques for text localization

Techniques for grammar-based automated generation of annotated synthetic form training data for machine learning are described. A training data generation engine utilizes a defined grammar to construct a layout for a form, select key-value units to place within the layout, and select attribute variants for the key-value units. The form is rendered and stored at a storage location, where it can be provided along with other similarly-generated forms to be used as training data for a machine learning model.

Grammar-based automated generation of annotated synthetic form training data for machine learning

Techniques for automated form understanding via layout-agnostic identification of keys and corresponding values are described. An embedding generator creates embeddings of pixels from an image including a representation of a form. The generated embeddings are similar for pixels within a same key-value unit, and far apart for pixels not in a same key-value unit. A weighted bipartite graph is constructed including a first set of nodes corresponding to keys of the form and a second set of nodes corresponding to values of the form. Weights for the edges are determined based on an analysis of distances between ones of the embeddings. The graph is partitioned according to a scheme to identify pairings between the first set of nodes and the second set of nodes that produces a minimum overall edge weight. The pairings indicate keys and values that are associated within the form.

Automated form understanding via layout agnostic identification of keys and corresponding values

Techniques for layout-agnostic clustering-based classification of document keys and values are described. A key-value differentiation unit generates feature vectors corresponding to text elements of a form represented within an electronic image using a machine learning (ML) model. The ML model was trained utilizing a loss function that separates keys from values. The feature vectors are clustered into at least two clusters, and a cluster is determined to include either keys of the form or values of the form via identifying neighbors between feature vectors of the cluster(s) with labeled feature vectors.

Layout-agnostic clustering-based classification of document keys and values

Growing community of inventors

Haifa, Israel

Oron Anschel