CN106970074A - The Urine test paper image-recognizing method of ability is corrected with color - Google Patents

Abstract

The invention relates to a urine test paper image recognition method with color correction capability. After using the test paper for urine test, the urine test paper and the standard color card are used together to generate a correction model, and the image of the test paper is automatically collected through the mobile phone, uploaded to the cloud platform, and then the Harris corner point detection calibration image is performed, and the cloud platform restores the color, after processing After that, the recognition result will be returned to the mobile phone. This recognition method first obtains the test paper image; then generates a color correction model based on the color data of the color correction color card and the standard color card data in the image, uploads it to the cloud platform, and then performs Harris corner detection and calibration of the image, and adjusts the brightness of the test paper image. Color correction, accurate color restoration, and finally, the recognition result is obtained and returned to the mobile phone. The method has high efficiency, simple operation, low cost, avoids the problems of ambient light interference and low accuracy of human eye recognition, and can be used to screen patients with early chronic kidney disease and reduce the risk of disease.

Description

Urine test paper image recognition method with color correction ability

technical field

The invention belongs to the category of image recognition, and in particular relates to a urine test paper image recognition method with color correction capability, which is used for urine detection of patients in hospitals, or urine detection by patients themselves.

Background technique

In the medical field, the diagnosis of many diseases usually needs to refer to multiple medical parameters for disease diagnosis. Using test strips to detect medical parameters is one of the more extensive and easy-to-operate detection methods. Among many tests, urinalysis is an important evaluation and analysis method for many diseases, and the medical parameters of urine are of great significance in clinical diagnosis. At present, many electronic devices have entered the medical field, and urine analyzers have also appeared one after another. Urine analyzers generally have a dedicated reagent strip, and the reagent strip row contains several reagent blocks, which are equidistantly distributed on the test paper. The test paper blocks are coated with chemical reagents specially used to detect corresponding items, and the number of reagent blocks determines the number of test items. The reagent cubes are coated with chemicals that measure the corresponding item, and react in color when in contact with urine. According to the degree of color change of the reagent block, the concentration of the corresponding substance in the urine can be judged and the detection result can be obtained.

Urinalysis is widely used in the diagnosis of urinary system diseases, curative effect observation and prognosis, and diagnosis of metabolic system diseases. Using traditional methods for urine testing is complicated and takes a long time. Although urine analyzers can quickly and accurately measure various indicators of urine, most urine analyzers are too expensive and have a limited detection range, so matching test strips must be used for detection. However, the traditional human eye contrast recognition method is inefficient and is easily affected by the subjective factors of the staff. In order to solve these problems, a urine test strip image recognition method with color correction capability is proposed, which can be performed on mobile devices. Routine urine testing helps users to perform urine self-test at home, adopts the method of urine dry chemical analysis, uses the mobile device camera to scan the test paper and correct the color card to get the color value of the test paper image, analyze the index concentration, and has low cost, detection Fast, easy to use and other advantages.

Contents of the invention

The invention aims to provide a urine test paper image recognition method with color correction capability, which is low in cost, simple and intuitive, shortens the detection time and has high accuracy.

The present invention is to provide a kind of urine test paper image recognition method with color correction capability, comprising the following steps:

Step 1, obtaining the image of the urine test strip;

Step 2. Generate a color correction model from the urine test strip and standard color card data, and upload it to the cloud platform;

Step 3, the cloud platform Harris corner detection calibration image, the cloud platform for color restoration;

Step 4, the cloud platform sends the recognition result back to the mobile phone.

Description of drawings

Fig. 1 is a structural schematic diagram of the urine test paper.

Figure 2 is a color correction model generated from urine test paper and standard color card data.

Fig. 3 is a flowchart of the operation of the urine test paper color correction capability.

detailed description

The urine test paper image recognition method based on the color correction mode provided by the present invention will be described in detail below in conjunction with the accompanying drawings.

Step 1: Describe in detail in conjunction with Figure 1. Figure 1 is a schematic diagram of the structure of the urine test paper, which includes two parts: the detection area numbers 2, 3, and 4 coated with specific detection reagents, and the number 1 area of the handle part of the test paper. For the urine sample, hold the part of the detection handle with the right hand, drop the detection area coated with the specific detection reagent into the urine, and obtain the urine test paper sample to be tested after the reaction is complete.

Step 2: Describe in detail in conjunction with Figure 2. Figure 2 is the correction model, which consists of two parts. The model is divided into upper and lower parts. The card has 5 color standard area blocks (area numbers 6, 7, 8, 9, 10).

Step 3: Take a picture of the model with a mobile phone, upload the captured image to the cloud platform, and perform Harris corner detection on the cloud platform. The Harris corner detection calibration image is used to eliminate the influence of shaking during the shooting process on the image acquisition results. After Harris processes the image, it performs accurate color reproduction on the test paper to be tested according to the standard color card.

Step 4: Store the image after color restoration in jpg format, and send it back to the mobile client for patients to view the results.

Claims (2)

1. a urine test paper image recognition method with color correction capability, is characterized in that, comprises the following steps: step 1, obtains urine test paper image; Step 2, generates color correction model with urine test paper and standard color card data, uploads To the cloud platform; step 3, Harris corner detection and calibration image; step 4, after the cloud platform obtains the corrected model, use the standard color card as the contrast color model, adjust the brightness and color correction of the urine test paper image provided by the patient, and then Based on the color restoration results, the cloud platform determines which urine test items in the urine test strip image provided by the patient exceed the standard. 2. A urine test paper image recognition method with color correction capability according to claim 1, characterized in that: the urine test paper of the patient to be detected is placed in the upper area of the model, and the standard color card is placed inside the model In the lower area, a color correction model is generated and uploaded to the cloud platform. The cloud platform uses Harris corner detection to calibrate the image. After that, the standard color card is used as a comparison color model to adjust the brightness and color correction of the urine test strip image provided by the patient, and then Based on the color restoration results, the cloud platform determines which urine test items in the urine test strip image provided by the patient exceed the standard.