A method for detecting edible rate of grapefruit pulp quality based on X-ray images

Abstract

The present invention discloses a method for detecting the edible rate of grapefruit pulp quality based on X-ray images. The longitudinal and transverse X-ray images A of the grapefruit are collected, and the enhanced X-ray images B are obtained by noise reduction and grayscale stretching respectively. The enhanced X-ray images B are processed to obtain the longitudinal and transverse two-dimensional pulp quality, and a prediction model of the actual grapefruit pulp quality is established. The longitudinal and transverse two-dimensional pulp quality is input into the prediction model to obtain the predicted pulp quality; the fruit weight of the whole grapefruit is weighed, and the edible rate of the grapefruit fruit is calculated. The present invention can non-destructively detect the grapefruit pulp quality by combining X-ray images with image processing technology, so as to achieve rapid detection that saves a lot of time and labor costs, and improve the accuracy of grapefruit pulp quality prediction.

Description

Technical Field

[0001] The present invention relates to a method for detecting the edible rate of grapefruit pulp quality based on X-ray images, which is mainly used in the post-harvest commercial processing process of grapefruit, and is used to grade grapefruit according to its internal quality (pulp quality), thereby creating a superior fruit brand effect and improving the economic benefits of the grapefruit industry. Background Art

[0002] my country is a major producer of pomelo, with total output ranking first in the world, accounting for more than half of the global total output. Many studies and practices have shown that the detection and grading technology of the internal and external quality of fruits plays an important role in improving the economic benefits of the fruit industry.

[0003] Flesh quality is one of the important indicators of the internal quality of pomelo. It is difficult to distinguish the quality of the internal flesh from the appearance alone. Research on pomelo flesh quality detection methods is very rare at home and abroad.

[0004] Pomelos with low flesh quality often have problems such as thick skin and incomplete flesh, which reduces the consumer's purchasing experience. Traditional manual measurement methods are extremely time-consuming and labor-intensive. According to the Guanxi Pomelo national standard GB / T27633-2011, destructive methods are required for measurement, which is also difficult to meet the industry needs of online detection.

[0005] The prior art lacks a non-destructive, rapid and effective method for detecting pulp quality. Summary of the invention

[0006] In order to solve the problems and needs existing in the background technology, the present invention provides a method for detecting the edible rate of grapefruit pulp quality based on X-ray images, which detects the pulp quality by computerized image processing, thereby achieving non-destructive, rapid and effective pulp quality detection.

[0007] The technical solution adopted by the present invention is as follows:

[0008] 1) Image acquisition: Using X-ray image acquisition equipment, collect original X-ray images A of grapefruit in the longitudinal and transverse directions respectively;

[0009] The transverse direction is parallel to the equatorial plane of the pomelo, and the longitudinal direction is perpendicular to the equatorial plane of the pomelo.

[0010] 2) Image enhancement: Denoise and grayscale stretch the original X-ray image A in the longitudinal and transverse directions to obtain enhanced X-ray images B that are clear and have high contrast in both longitudinal and transverse directions;

[0011] 3) Acquisition of two-dimensional pulp quality: The longitudinal and transverse enhanced X-ray images B are processed separately to obtain the longitudinal two-dimensional pulp quality and the transverse two-dimensional pulp quality;

[0012] 4) Based on the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass, a prediction model for the actual pomelo pulp mass is established to predict the pulp mass, and the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass of the actual pomelo to be tested are input into the prediction model to obtain the predicted pulp mass;

[0013] 5) Weigh the fruit mass of the entire pomelo again, and calculate the edible rate of the pomelo fruit mass by integrating the fruit mass of the entire pomelo: edible rate of pomelo fruit mass = predicted pulp mass / whole pomelo fruit mass.

[0014] In the step 3), threshold segmentation is performed on both the longitudinal and transverse enhanced X-ray images B, and the images are segmented into three parts: background area, peel area (including sponge layer) and pulp area using two preset thresholds. The extracted pulp area is subjected to specific image processing to obtain two-dimensional pulp mass. The two-dimensional pulp mass corresponding to the longitudinal and transverse enhanced X-ray images B is used as the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass, respectively.

[0015] In step 3), the gray value G of each pixel in the pulp area is calculated. i The sum of the logarithms with base e is taken as the 2D flesh mass of grapefruit, and the calculation formula is as follows;

[0016]

[0017] Among them, G i represents the gray value of the i-th pixel in the pulp area, and n represents the total number of pixels in the pulp area.

[0018] The processing of the pulp region in the longitudinal enhanced X-ray image B and the processing of the pulp region in the transverse enhanced X-ray image B are the same.

[0019] After step 4), the method further sets different ranges of grapefruit pulp quality, and uses the obtained predicted pulp quality to determine the grapefruit pulp quality grade.

[0020] The prediction model in step 4) is established as the following formula:

[0021] y=A+Bx 1 +Cx 2

[0022] Among them, y represents the predicted pulp mass, x1 represents the longitudinal two-dimensional pulp mass, x2 represents the transverse two-dimensional pulp mass, and A, B, and C represent the first, second, and third fitting parameters of the prediction model, respectively.

[0023] The first, second and third fitting parameters A, B and C can all be obtained through prior test calibration fitting.

[0024] The present invention utilizes an X-ray imaging system to collect original longitudinal and transverse grayscale images of pomelo, obtains clear and high-contrast pomelo X-ray images after noise reduction and grayscale stretching, then obtains the two-dimensional pulp quality of the pomelo X-ray image, and establishes a prediction model for the pomelo pulp quality based on the two-dimensional pulp quality, which can be used for the detection and classification of pomelo pulp quality.

[0025] The present invention has the following beneficial effects:

[0026] The present invention can realize nondestructive online detection by combining X-ray images with image processing technology, so as to achieve rapid detection which saves a lot of time and labor costs. At the same time, it introduces images in both longitudinal and transverse directions to further improve the accuracy of grapefruit pulp quality prediction, and can provide technical support for the high-quality screening of grapefruit. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is the overall flow chart of the present invention;

[0028] Figure 2 is the original longitudinal X-ray image of grapefruit of the present invention;

[0029] Figure 3 is the original transverse X-ray image of grapefruit of the present invention;

[0030] Figure 4 The present invention Figure 2 Enhanced image;

[0031] Figure 5 The present invention Figure 3 Enhanced image;

[0032] Figure 6 It is a scatter plot of the prediction model of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] The present invention selects honey pomelo as an embodiment:

[0035] like Figure 1 As shown, the present invention comprises the following steps:

[0036] 1) Image acquisition: Figure 2 and Figure 3 As shown, using an X-ray image acquisition device, the original longitudinal and transverse X-ray images A of the grapefruit are acquired;

[0037] 2) Image enhancement: such as Figure 4 and Figure 5As shown, the obtained grapefruit X-ray original images A in two directions are subjected to denoising and grayscale stretching respectively. The denoising method is to use a Wiener filter with a window size of 9×9. The grayscale stretching method is to linearly and smoothly stretch the grayscale range of the transverse image A from 30-109 to 38-251, and the grayscale range of the longitudinal image A from 29-112 to 34-253, so as to obtain a clear and high-contrast enhanced X-ray image B.

[0038] 3) Two-dimensional pulp quality acquisition:

[0039] The enhanced X-ray image B is segmented by an adaptive threshold. The adaptive threshold segmentation method is to first find the peak value I with the grayscale closest to 255 in the grayscale histogram corresponding to the enhanced X-ray image B. 1 , the gray value is greater than I 1 The pixel point is defined as the background, that is, the gray value is adjusted to 255; then the proportion of each gray value in the foreground in the total matrix and the gray mean of the foreground are calculated, and the gray value I is searched cyclically starting from gray value 0. 2 Used to segment the foreground, I 2 The two parts after foreground segmentation have the largest inter-class variance; finally, the gray value is less than I 2 The pixel point is defined as the pulp area, its grayscale value remains unchanged, and the grayscale of other pixels is adjusted to 0.

[0040] Then calculate the gray value of each pixel in the pulp area (G i The sum of the logarithms of ) with base e (as shown in formula 1) is the two-dimensional pulp mass, Figure 5 The corresponding two-dimensional pulp mass is 5.38×10 6 , similarly, by Figure 4 The mass of the two-dimensional pulp of the grapefruit is 4.51×10 6 ;

[0041]

[0042] 4) If Figure 6 As shown in Figure 2, a total of 98 red-fleshed honey pomelo and 104 Guanxi honey pomelo were selected to measure the longitudinal two-dimensional pulp mass and transverse two-dimensional pulp mass, of which the calibration set and prediction set accounted for 70% and 30% of the total number of pomelo, respectively. A multiple linear regression model of the actual pulp mass of pomelo was established (as shown in Formula 2). The determination coefficient R p 2 is 0.888, the root mean square error RMSEP of the prediction set is 57.43g, and the relative analytical error RPD of the model is 2.87;

[0043] y=-107.4210+x 1 ×8.9658×10 -5 +x 2×1.1204×10 -4 (2)

[0044] Among them, y represents the predicted pulp quality of grapefruit, x1 represents the grayscale logarithm sum of the pulp area in the longitudinal X-ray image, and x2 represents the grayscale logarithm sum of the pulp area in the transverse X-ray image.

[0045] 5) Grading of grapefruit pulp quality: Specifically, grapefruit pulp with a mass greater than 1100 g is set as grade 1, grapefruit pulp with a mass between 700 g and 1100 g is set as grade 2, and grapefruit pulp with a mass less than 700 g is set as grade 3, and the grapefruit pulp mass predicted in step 4) is used for grading;

[0046] 6) Combined with the weight of the whole grapefruit obtained by weighing, the edible rate of grapefruit fruit mass can also be calculated, that is, the predicted pulp mass / whole fruit mass.

[0047] It can be seen from the implementation that the present invention can realize the detection and grading of the quality of pomelo pulp, can solve the problems of traditional detection methods being time-consuming, labor-intensive and destructive, achieve rapid non-destructive detection that saves a lot of time and labor costs, improve the efficiency of the pomelo industry, and also can realize the detection of edible rate.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any slight modification, equivalent substitution and improvement made to the above embodiment based on the technical essence of the present invention should be included in the protection scope of the technical solution of the present invention.

Claims

1. A method for detecting edible rate of grapefruit pulp quality based on X-ray images, characterized in that: The method comprises the following steps: 1) Image acquisition: Using X-ray image acquisition equipment, collect original X-ray images A of grapefruit in the longitudinal and transverse directions respectively; 2) Image enhancement: Denoise and grayscale stretch the original X-ray image A in the longitudinal and transverse directions to obtain enhanced X-ray images B in the longitudinal and transverse directions; 3) Acquisition of two-dimensional pulp quality: The longitudinal and transverse enhanced X-ray images B are processed separately to obtain the longitudinal two-dimensional pulp quality and the transverse two-dimensional pulp quality; 4) Based on the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass, a prediction model for the actual grapefruit pulp mass is established, and the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass of the actual grapefruit to be tested are input into the prediction model to obtain the predicted pulp mass; 5) Weigh the fruit mass of the entire pomelo again, and calculate the edible rate of the pomelo fruit mass by integrating the fruit mass of the entire pomelo: edible rate of pomelo fruit mass = predicted pulp mass / whole pomelo fruit mass.

2. The method for detecting edible rate of grapefruit pulp quality based on X-ray images according to claim 1, characterized in that: In the step 3), threshold segmentation is performed on both the longitudinal and transverse enhanced X-ray images B, and the images are segmented into three parts: a background area, a peel area, and a pulp area using a preset threshold. The extracted pulp area is subjected to specific image processing to obtain a two-dimensional pulp mass. The two-dimensional pulp masses corresponding to the longitudinal and transverse enhanced X-ray images B are respectively used as the longitudinal two-dimensional pulp mass and the transverse two-dimensional pulp mass.

3. The method for detecting edible rate of grapefruit pulp quality based on X-ray images according to claim 1, characterized in that: In step 3), the gray value G of each pixel in the pulp area is calculated. i The sum of the logarithms with base e is taken as the 2D flesh mass of grapefruit, and the calculation formula is as follows; Among them, G i represents the gray value of the i-th pixel in the pulp area, and n represents the total number of pixels in the pulp area.

4. The method for detecting edible rate of grapefruit pulp quality based on X-ray images according to claim 1, characterized in that: After step 4), the method further sets different ranges of grapefruit pulp quality, and uses the obtained predicted pulp quality to determine the grapefruit pulp quality grade.

Images