Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system of identifying target object in image, and method and system of identifying food in refrigerator

A target object and image recognition technology, which is applied in the field of image recognition, can solve problems such as low recognition rate of image recognition and unsatisfactory test data performance, and achieve the effect of reducing parameter space, improving accuracy, and achieving consistency

Inactive Publication Date: 2017-03-22
HEFEI MIDEA INTELLIGENT TECH CO LTD
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the different images used for training and use, this difference causes the learned information to only reflect part of the characteristics of the data, so the performance on the test data is not ideal, and the recognition rate of image recognition is not high.

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
  • Method and system of identifying target object in image, and method and system of identifying food in refrigerator
  • Method and system of identifying target object in image, and method and system of identifying food in refrigerator
  • Method and system of identifying target object in image, and method and system of identifying food in refrigerator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0025] Such as figure 1 As shown, the embodiment of the present invention provides a method for recognizing a target object in an image, including the following steps:

[0026] S110, the training phase acquires training images, performs normalization processing on the training images, and uses the training images to establish an image recognition model;

[0027] S120, acquiring a test image in the test phase, performing normalization processing on the test image, matching the test image with the image recognition model, and realizing the recognition of the target object in the test image;

[0028] The training images acquired in the training phase and the test images acquired in the testing phase are normalized, an...

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

The invention relates to a method and system of identifying a target object in an image, and a method and system of identifying food in a refrigerator. The method of identifying a target object in an image includes the steps: acquiring a training image, utilizing the training image to establish an image identification model; and acquiring a test image, matching the test image with the image identification model, and realizing identification of a target object in the test image, wherein performing normalization processing on the acquired training image and the acquired test image, and mapping the training image and the test image to a unified space; and / or performing regularization processing during the process of establishing the image identification model to enable the image identification model to express full sample distribution. The method of identifying a target object in an image enables expression on the test data of the image identification model to approach to the expression on the training data as possible, thus realizing consistency of image identification and improving image identification accuracy.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a target object recognition method in an image, a food recognition method and a system in a refrigerator. Background technique [0002] In the existing image processing technology, the consistency of the collected image and the collected image cannot be guaranteed. This difference causes the learned information to intelligently reflect some characteristics of the data, so the performance on the test data is not ideal, and the recognition rate of image recognition is relatively low. Low. [0003] Especially in the field of image recognition technology in refrigerators, there are many types of refrigerators. If each refrigerator is photographed separately for image recognition, the difference in image quality will affect the recognition rate. The images taken by different models of refrigerators are inconsistent, and the images taken by food placed in different positions...

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): G06K9/00
CPCG06V20/36
Inventor 杨世清徐达唐军
Owner HEFEI MIDEA INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products