Supercharge Your Innovation With Domain-Expert AI Agents!

Image processing for automated object identification

An image and identification technology, applied in the field of image processing

Pending Publication Date: 2020-02-21
ACCENTURE GLOBAL SOLUTIONS LTD
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The one or more processors may generate a set of candidate images for object identification based on the images and using the image generation model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing for automated object identification
  • Image processing for automated object identification
  • Image processing for automated object identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] Example Embodiment 1: An apparatus comprising: one or more memories; and one or more processors communicatively coupled to the one or more memories, the one or more processors to: obtain an image; based on the image and using the image generation model to generate a set of candidate images for object recognition; determining based on the set of candidate images and using the image evaluation model that one or more candidate images in the set of candidate images were processed during image generation and using the image generation model to improve the resolution of the image; for one or more candidate images and based on the image, determine an image embedding; for one or more candidate images, determine an embedding error based on the image embedding and the image; determine an image embedding based on the image embedding and the embedding error Identification of features; back-propagating the embedding error into the image generation model to generate an updated image g...

Embodiment 2

[0096] Example embodiment 2: The apparatus according to example embodiment 1, wherein the one or more processors are further to: use the updated image generation model to generate other sets of candidate images based on other images; and determine based on the other set of candidate images Other identification of other features of other images.

Embodiment 3

[0097] Example embodiment 3: The apparatus according to example embodiment 1, wherein the one or more processors are further configured to: use the updated image evaluation model to evaluate other one or more candidate images related to other images; Multiple candidate images to determine other identities of other features of other images.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Embodiments of the present invention relate to image processing for automated object identification. A device obtains an image and generates, based on the image and using an image generation model, aset of candidate images for object recognition. The device determines, based on the set of candidate images and using an image evaluation model, that one or more candidate images, of the set of candidate images, are processed during image generation and using the image generation model to improve a resolution of the image. The device determines image embeddings for the one or more candidate imagesand based on the image, and determines an embeddings error for the one or more candidate images based on the image embeddings and the image. The device determines an identification of a feature of the image based on the image embeddings and the embeddings error, and performs an action relating to the identification of the feature based on determining the identification of the feature.

Description

technical field [0001] Embodiments of the present disclosure relate to image processing, and more particularly, to image processing for automatic object identification. Background technique [0002] Image capture devices such as cameras, video cameras, etc. may be used to capture images. For example, a user device may include a camera to capture images of the user. Similarly, autonomous vehicles may include cameras to capture video of the environment in which the autonomous vehicle is operating. The image capture device may provide the image to a processing device, such as a user device, for processing and / or utilization. For example, the user device may use facial recognition technology to determine the identity of the user of the user device. In this case, the user device may determine, based on analyzing the captured image of the user, that the user of the user device is an authorized user, and the user device may support user access to the user device. Similarly, the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T1/20G06T1/60G06T7/246G06V10/764
CPCG06T1/20G06T1/60G06T7/246G06T2207/10016G06T2207/20081G06T2207/30204G06V10/993G06V10/82G06V10/764G06T7/11G06N20/00G05D1/0246G06T3/40G06T5/50G06T7/0002G06T2207/20084G06T2207/30168G06T2207/30252G06V2201/08
Inventor M·F·扎曼P·拉莫斯C·奥哈根
Owner ACCENTURE GLOBAL SOLUTIONS LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More