Unlock instant, AI-driven research and patent intelligence for your innovation.

Test strip color detection method based on deep neural network

A deep neural network and color detection technology, which is applied in the field of test strip color detection, can solve problems such as low stability and inaccurate test strip positioning, and achieve high stability.

Pending Publication Date: 2022-01-14
珠海市一杯米科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the prior art, the positioning of the test paper is inaccurate and the stability 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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below.

[0043] The technical scheme that this embodiment mode adopts is: it comprises the following steps:

[0044] 1. Place the test strip: Connect the urine sugar detector to the smart phone through the OTG data cable; the top of the urine sugar detector box is equipped with a camera and LED fill light; the camera is directly facing the bottom; pull out the side of the urine sugar detector The slot on the wall is used to place test strips. There is a vertical groove in the middle of the slot. Place the test strip in the groove and close the slot; control urine sugar through the pre-installed APP on the smartphone The detector takes pictures and detects; there are four test strips on the test strip, all of which are coated with chemical reagents, which can react chemically to protein, glucose, ketone bodies, and microalbumin in urine; The four test paper blocks will show different colors; by analyzing the color value of...

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 discloses a test strip color detection method based on a deep neural network. The test strip color detection method comprises the following steps: 1, placing a test strip; 2, carrying out early warning on an abnormal condition without insertion of the test strip; 3, carrying out abnormal situation early warning when data abnormity occurs during image shooting; 4, realizing the positioning of the test strip by adopting a yov5 algorithm; 5, carrying out early warning on abnormal conditions that the insertion positions of the test strips are not standard; and 6, segmenting the test paper blocks by adopting a segmentation network Unet. The test strip provided by the invention is accurate in positioning; and with high stability, positioning and segmentation of pixels on each test paper block are realized, and an abnormal condition automatic early warning function is realized.

Description

technical field [0001] The invention relates to a test strip color detection method, in particular to a test strip color detection method based on a deep neural network. Background technique [0002] The detection of urine sugar concentration based on test strips is very important for diabetics. The technology allows diabetics to get a rough estimate of whether their sugar intake is excessive without pricking their fingers and enduring the pain. The method of automatically detecting the concentration level corresponding to each test paper block based on the camera shooting urine sugar test paper is a new technology that has emerged in recent years. However, in the prior art, the positioning of the test paper is inaccurate and the stability is not high. Contents of the invention [0003] The purpose of the present invention is to aim at the defects and insufficiencies of the prior art, to provide a test strip color detection method based on deep neural network, accurately...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/90G06N3/04G06N3/08
CPCG06T7/0002G06T7/11G06T7/90G06N3/082G06T2207/10004G06T2207/20021G06T2207/20081G06T2207/20084G06N3/045
Inventor 邓宏平陈波杜伟杰唐瑛
Owner 珠海市一杯米科技有限公司