公开(公告)号：US20210034980A1

公开(公告)日：2021-02-04

申请号：US17073147

申请日：2020-10-16

Applicant: Amazon Technologies, Inc.

Inventor： Wei Xia ,  Weixin Wu ,  Meng Wang ,  Ranju Das

IPC: G06N3/08 ,  G06N3/04

Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.

公开(公告)号：US10706322B1

公开(公告)日：2020-07-07

申请号：US15821629

申请日：2017-11-22

Applicant: Amazon Technologies, Inc.

Inventor： Shuo Yang ,  Hao Wu ,  Jonathan Wu ,  Meng Wang

IPC: G06K9/34 ,  G06K9/62 ,  G06T7/70 ,  G06K9/72

Abstract: Embodiments of the present disclosure provide systems and processes for automatically determining a layout of text within an image that makes sense from a semantic perspective. In certain embodiments, the systems disclosed herein receive bounding box information relating to one or more bounding boxes that surround text within the image. The systems compare the received bounding box information to determine a clustering of bounding boxes that have an above threshold probability of including words that when read in order make sense semantically. For example, systems herein can determine whether words in a cluster correspond to a line of text.

公开(公告)号：US10423827B1

公开(公告)日：2019-09-24

申请号：US15641774

申请日：2017-07-05

Applicant: Amazon Technologies, Inc.

Inventor： Jonathan Wu ,  Meng Wang ,  Wei Xia ,  Ranju Das

IPC: G06K9/00 ,  G06T7/11 ,  G06K9/66

Abstract: A method and system for analyzing text in an image. Classification and localization information is identified for the image at a word and character level. A detailed profile is generated that includes attributes of the words and characters identified in the image. One or more objects representing a predicted source of the text are identified in the image. In one embodiment, neural networks are employed to determine localization information and classification information associated with the identified object of interest (e.g., a text string, a character, or a text source).

公开(公告)号：US10019463B2

公开(公告)日：2018-07-10

申请号：US14747232

申请日：2015-06-23

Applicant: Amazon Technologies, Inc.

Inventor： Yi Li ,  Tianqiang Liu ,  Hao Chen ,  Meng Wang

IPC: G06F17/30 ,  G06K9/00 ,  G06K9/52 ,  G06K9/62

Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.