Amazon Technologies, Inc.

Fair Isaac Corporation

Ilya Levner

Scott Michael Zoldi

Zhaoqing Ma

Canku Alp Calargun

Maria Edna Derderian

Prajwal Yadapadithaya

Venkata Krishnan Ramamoorthy

Konstantinos Boulis

Gurbinder Gill

Dharmil Satishbhai Chandarana

Riley James Williams

Aditya Ghuge

Prama Anand

Tabrez Mohammed

Techniques are generally described for cropped image evaluation. In various examples, first image data representing a first image and second image data representing a cropped version of the first image may be received. An image captioning model may be used to generate first text data describing the first image data and second text data describing the second image data. A first encoder may be used to generate first data representing the first text data and second data representing the second text data. In various examples, a third data representing a degree of similarity between the first data and the second data may be generated. In some cases, first computer-executable instructions configured to cause the second image data to be displayed on a display may be generated based at least in part on the third data.

Automatic image cropping

Techniques for improved image classification are provided. Face embeddings are generated for each face depicted in a collection of images, and the face embeddings are clustered based on the individual whose face is depicted. Based on these clusters, each embedding is assigned a label reflecting the cluster assignments. Some or all of the face embeddings are then used to train a classifier model to generate cluster labels for new input images. This classifier model can then be used to process new images in an efficient manner, and classify them into appropriate clusters.

Incremental clustering for face recognition systems

Categorizing images may include training a first neural network to cluster a plurality of images to obtain a first image embedding space, wherein a vector representation is determined for each of the plurality of images based on the training, determining a vector norm value corresponding to each of the plurality of images based on the vector representation for each of the plurality of images, and identifying a first subset of the images for which a corresponding vector norm value satisfies a predetermined vector norm quality threshold. Then, a second neural network may be trained using the first subset of images to obtain a second image embedding space, and the second image embedding space may be used to categorize additional images.

Vector norm algorithmic subsystems for improving clustering solutions

A system and method for detecting a test event involving a financial transaction device at a merchant having a merchant profile is disclosed. The method includes receiving data associated with a transaction involving a financial transaction device; calculating a score using at least the transaction data; comparing the score to a threshold value; and attaching a merchant probe flag to the merchant profile if the score exceeds the threshold value. The merchant probe flag indicates a likelihood that a test event has occurred at the merchant based on the score. If a test event has occurred, then financial transaction devices involved in the test event can have their profiles updated to reflect that they have been probed. If a financial transaction device that has been probed is used in a subsequent transaction, then a specialized fraud scoring model can be used to provide an improved fraud risk score.

Card fraud detection utilizing real-time identification of merchant test sites

Growing community of inventors

Woodinville, WA, United States of America

Ilya Levner