CN108022239B - Bubbling wine browning process detection device and method based on machine vision - Google Patents

Abstract

The invention provides a device and a method for detecting a browning process of sparkling wine based on machine vision, which are used for solving the problems of complex detection process, high cost and poor applicability in the prior art; the method comprises the steps of collecting a sample placed on a diffuse light source panel at the bottom of a collection box by using a camera of a smart phone to obtain a digital image of the sparkling wine, carrying out graying, binaryzation, corrosion and other treatment on the digital image by using machine vision and image processing technologies, analyzing three channels of RGB (red, green and blue) of the image, and taking the attenuation percentage of a blue channel as a quality mark of the sparkling wine, wherein the attenuation percentage is highly related to the absorbance at 420nm and the content of 5-hydroxymethyl-2-furfural. The method only needs to obtain the transmission images of the sparkling wine samples in different browning stages, can simultaneously analyze a plurality of brands of sparkling wine samples, avoids complex sample processing, can analyze a plurality of samples, and has the advantages of high speed, low cost and no need of expensive professional instruments and other chemical reagents.

Description

Bubbling wine browning process detection device and method based on machine vision

Technical Field

The invention relates to the technical field of foaming wine browning and image processing, in particular to a device and a method for detecting a browning process of foaming wine based on machine vision.

Background

At the present time, sparkling wines are almost all produced around the world, and consumer enjoyment and demand for sparkling wines is increasing. The foaming principle is that sugar and yeast are added into the brewed wine to perform the second alcoholic fermentation in a closed container, and carbon dioxide generated in the fermentation process is limited in the bottle to be the source of bubbles in the wine (Serra-Cayuela A, Journal M, Riu-Austell M, et al. kinetics of fermentation, phenolics, and 5-hydroxymethane fuel in commercial specialty fibers [ J ]. Journal of agricultural & Food Chemistry,2014,62(5 1159-. The added yeast converts the added sugar into alcohol and carbon dioxide, causing the bubbles to tumble, which is one of the most important features of sparkling wine.

Sparkling wine consumption has increased rapidly, according to the statistics of the international wine organization, sparkling wine production has increased by 40% in recent years, sparkling wine accounts for 8% of the global wine production. China and the united states have become the prime forces driving this growth.

Spanish slips and french champagne are the best known brands of sparkling wine. Slips are high quality sparkling wines produced by traditional methods protected by the place of origin naming system. The grapes used in kava are carefully selected and care must be taken during the juicing process to obtain the best juice at the desired maturity. Then pouring the grape juice into a stainless steel barrel for low-temperature fermentation, standing, tasting to determine the quality of the grape juice, and selectively blending. After the final blending, the wine is bottled and placed in a wine cabinet for at least 9 months, but generally this shelf life is longer. During this time, the wine will undergo secondary fermentation in the bottle, forming the wine's complex organoleptic properties such as aroma, color and foaming properties, becoming sparkling wine and producing yeast sediment. After the aging period, the yeast can be carefully taken out, the bottle mouth is filled with the same batch of wine, the bottle mouth is sealed by a cork stopper, and a seal is added. Furthermore, there are two different categories depending on the duration of ageing in the bottle: at least 15 months of Reserva, at least 30 months of Gran Reserva (Serra-Cayuela A, Aguilra-Curie M A, Riu-Austell M, et al, browning, biological imaging and commercial storage of the Cava sparking line and the use of5-HMF as a quality marker [ J ]. Food research International,2013,53(1): 226-). 231. Besides improving the quality of the grape, the production cost is also influenced by the aging time, and the final price of the aged grape wine is higher than that of the new grape wine.

Wine is a dynamic product in terms of physicochemical and organoleptic properties, and therefore undergoes complex chemical changes during biological ageing and storage. These chemical changes may cause changes in sensory characteristics, particularly aroma, flavor, and color (royal jade peak. study of factors affecting the aroma of wine [ D ]. denna: eastern Shandong light industry academy, 2010).

Browning, which is an oxidation process involving sugars, lipids, amino acids and phenols (Li H, Guo a, Wang H. mechanismso acidic browning of wine [ J ]. Food chemistry,2008,108(1):1-13.), reduces the organoleptic quality of wine (changes in color, flavor and aroma, and increase in astringency), and must therefore be controlled during processing and storage. Once the bottle is sealed, browning cannot be regulated anymore. Therefore, breweries must find markers and parameters that indicate browning of sparkling wines and detect browning of sparkling wines by technical means. There is a great need in actual production to develop a fast and reliable method of monitoring the degree of browning and to define parameters indicative of the quality of sparkling wines.

Prior studies have proposed several methods for quantifying and characterizing the browning process of sparkling wines based on different quality marking and measuring techniques. Such as Ultraviolet-visible spectroscopy (UV-VIS) and High Performance Liquid Chromatography (HPLC) (Serra-Cayuela A, Aguilra-Curie M A, Riu-Automatell M, et al, browning and compacting biological imaging and commercial of Cava spackling wire and the use of5-HMF as a quality marker [ J ] Food Research International,2013,53(1):226 storage 231.).

Absorbance at 420nm wavelength (A)₄₂₀) Used as a parameter for monitoring browning of white wine (Kallithraka S, Salacha M I, Tzourou I. Change in phenolic composition and antioxidant activity of white wine reduced bottle storage J. corrected browning test for white wine].Food Chemistry,2009,113(2):500-505.)，A₄₂₀The increase in value is directly related to the browning process (Ibarz A, Pagan J, Garza S. kinetic models of non-enzymatic browning initial pure [ J.)].Journal of the Science of Food&Agriculture,2000,80(8): 1162-. However, in previous studies, A was used as a quality marker for kava sparkling wines₄₂₀The parameters proved to have low sensitivity and low specificity, after which the 5-hydroxymethyl-2-furfural (5-HMF) content was used instead as a more efficient marker (Serra-Cayuela A, Aguilera-Curie M A, Riu-Austell M, et al, browning during biological labeling and commercial storage of Cava spackling wire and the use of5-HMF as quality marker [ J]Food Research International 2013,53(1): 226-.

Among the existing research methods, the successful use of fluorescence excitation-emission spectroscopy in combination with parallel factor analysis for monitoring the browning process of four sparkling wines has been identified as a method for monitoring A₄₂₀Or a rapid alternative method for realizing browning detection by using the content of 5-HMF. In order to investigate better alternatives, researchers have proposed a new method based on colorimetric techniques for monitoring the browning process in kava sparkling wines in accelerated browning tests. The degree of Browning was measured using a Lab color pattern defined by the International Commission on illumination (CIE) or a Lab color pattern created by Richard. S.Hunter (Raquel P FG, Joao Barroca M.evaluation of the Browning Kinetics for Browning dynamics and PearsSubmitted to conductive Drying [ J]Current Biochemical Engineering,2014,1:165- & 172.), but these methods require the use of a dedicated colorimeter or spectrophotometer.

In recent years, as the performance of sensors of smartphones is improved, the research on applications based on smartphones is also increasing. Compared with professional instruments and equipment in a laboratory, the smart phone has the advantages of low cost, convenience in carrying, capability of acquiring and analyzing on site, easiness in sharing results and the like.

Disclosure of Invention

Aiming at the technical problems that a special colorimeter or a spectrophotometer is needed to be used for browning detection of the existing sparkling wine, the detection process is complex, and the applicability is not strong, the invention provides the device and the method for detecting the browning process of the sparkling wine based on machine vision.

In order to achieve the purpose, the technical scheme of the invention is realized as follows: a sparkling wine browning process detection device and method based on machine vision comprises the following steps:

the method comprises the following steps: building an experimental device and preparing a sample;

step two: acquiring a sample image by using a camera of a smart phone, and acquiring an RGB image IG_iCarrying out graying and binarization processing to obtain a binary image BIN_i，i＝1,2,…,6；

Step three: BIN image_iAll the pixels in the image are inverted to obtain an image IR_i(ii) a Using pairs of structural elements IR_iCorroding to obtain an image IER_iObtaining a constricted region of the well containing the sample;

step four: image IER_iCarrying out connected region marking, and identifying each type of sample according to the connected region marking;

step five: by image IG₁The average of the R channel, G channel and B channel of the area of the contracted sample well of the standard original sample of (1) is taken as a reference, and a correction factor is calculated for the image IG_iColor correction is carried out on each channel to obtain a corrected image IGC_i，i＝2,…6；

Step six: computingCorrected image IGC_iSelecting a channel B as a browning parameter according to the average value of R, G, B channels in the area of the shrinkage hole of each brand sample;

step seven: calculating the color invariant of the B channel and the blue decay percentage, wherein the blue decay percentage has a linear relation with time, and the blue decay percentage is consistent with the browning process of the sparkling wine and is used as a quality mark for browning detection.

The samples are four popular brands of kava foaming wine of Brut, Brut Reserva, Brut Gran Reserva and Semiseco, and the four wines have different sugar contents and production years; 10mL of each of the solutions were taken and charged into 420 mL amber vials in N₂Degassing under airflow; placing the 4 amber vials containing different brands of sparkling wine in a dark environment and maintaining the ambient temperature at 8 ℃; the different brands of sparkling wines in the 4 bottles were used as standard samples for the subsequent 10-day experiment, and the 4 amber vials containing the standard samples were named Bottle1, Bottle2, Bottle3, Bottle 4; then, 10mL of each of the four brands of sparkling wine was filled into 4 amber vials of 20mL and placed in N₂Degassing under airflow; placing the 4 amber vials filled with sparkling wines of different brands in a completely dark environment, then placing the vials in an oven, setting the constant temperature of 65 +/-1 ℃, and performing an accelerated browning test; the 4 amber vials containing the accelerated browning samples were designated Bottle5, Bottle6, Bottle7, Bottle 8; collecting sample information at sampling time points of 0, 2, 4,6, 8 and 10 days, wherein the collection time interval is 48 hours; at each sampling time point, (1) 1 part of each standard sample of Brut, BrutReserva, Brut Gran Reserva and Semiseco is extracted firstly, placed in the holes in the middle of a 96-hole plate from top to bottom in sequence, vertically arranged in 1 row and named as the 1 st row; (2) then 4 parts of samples of Brut, Brut Reserva, Brut GranReserva and Semiseco which accelerate browning are extracted, and then 1 column of each brand is put into the 2 nd to 5 th columns of a 96-well plate in sequence.

The experimental device comprises a collection box and a light source, wherein the light source is arranged below the collection box, a pore plate used for containing a sample is arranged on the lower portion of the collection box, a collection hole is formed in the top of the collection box, and the collection hole is located right above the pore plate.

The collecting box is made of a black foam core plate, and matte black velvet paper covers the inside of the collecting box; the collecting box is of a cuboid structure with the height of 80cm, and the difference between a diagonal line and a central vertical light path is less than 5%; the light source is a diffuse reflection light source with controllable intensity; the pore plate is a 96 pore plate, is made of imported optical transparent pure polystyrene and is sterilized by gamma rays.

The method for acquiring the sample image comprises the following steps: arranging the kava sparkling wine samples in the middle of a pore plate by using a 0.3ml micropipette, placing the pore plate on a panel of a light source, covering an acquisition box on the pore plate, positioning an acquisition hole above the middle of the pore plate, placing a smart phone on the acquisition hole at the top of the acquisition box, and obtaining an image with the highest resolution by using a built-in camera of the smart phone and storing the image as JPEG; the standard raw samples are arrayed in a well plate and all samples are taken in the same image.

The method for carrying out graying and binarization processing on the obtained RGB image comprises the following steps:

IG (image group) of RGB (Red Green blue) image obtained by smart phone_iThe average value of R, G, B three components of each pixel is used as the Gray value of the image, i.e. Gray_i(x,y)＝(R_IG,i(x,y)+G_IG,i(x,y)+B_IG,i(x, y))/3 to obtain a Gray image Gray_i；

For Gray scale image Gray_iAn optimal threshold T is calculated using Otsu's algorithm, which is a gray value gt that maximizes σ: assuming that the gray level of the gray image is L, the gray range is [0, L-1]]The optimal threshold for calculating the gray level image by using the Ostu method is as follows: max [ w [ ]₀(gt)×(u₀(gt)-u)^2+w₁(gt)×(u₁(gt)-u)^2)]Wherein w is₀As a foreground proportion, u₀Is the mean value of the gray levels of the foreground, w₁As background proportion, u₁Is the background gray level mean value, and u is the mean value of the whole gray level image.

T is the optimal threshold value of the segmentation image, the gray level image is segmented into 2 parts according to the optimal threshold value T, and the binary image BIN is obtained_i(x,y)：

Wherein, Gray_i(x, y) is the value of the pixel at (x, y) in the grayscale image;

BIN binary image_iThe binary image IR is obtained by inversion (pixel value becomes 0 when 1, and pixel value becomes 1 when 0)_i(ii) a Adopting imeriode function in Matlab to carry out IR on binary image_iCarrying out corrosion operation: IER_i＝imerode(IR_i,D₁) Wherein, IER_iRepresenting a binarized image IR_iCircular structural element D with diameter of 8₁The image obtained after etching, i ═ 1,2,3, ·, 6; d₁Stral ('disk',4), disk denotes a circular shape.

Image IER_iThe method for marking the connected region comprises the following steps: adopting a connected region mark function bwleabel in Matlab: [ LJ_i,LNUM_i]＝bwlabel(IER_i8), wherein, LNUM_iRepresentation image IER_iNumber of interconnected regions, LJ_iRepresentation and image IER_iMatrices of equal size, the matrix LJ_iContains a label image IER_iClass label for each connected region, the labels having values of 1,2, …, LNUM_iAnd 8, searching a connected region according to 8 neighborhoods;

the method for identifying the position of each type of sample comprises the following steps: the connected regions labeling treats each contracted sample region as a connected region, using, for each connected region, the regionprops function in Matlab: STATS_i＝regionprops(LJ_i'Central'), the 'Central' attribute is the Centroid of the connected region, STATS_iContains an image IER_iOf (a) each connected region (centroid coordinates (RX)_i,nu,LY_i,nu) And the subscript nu has a value of 1-20.

The method for acquiring the corrected image comprises the following steps: by image IG₁Of the standard original sample, the R channel, the G channel and the B channel of the area of the constricted sample wellValue R_1，ave、G_1，aveAnd B_1，aveFor reference, the mean value of the R channel, the G channel and the B channel of the area of the contracted sample hole where the standard original sample in the images acquired by the subsequent different time sampling points is R_i，ave、G_i，_aveAnd B_i，aveFor reference, three correction factors C are calculated_i,R、C_i,GAnd C_i,B：

Wherein, C_i,R、C_i,G、C_i,BAs an image IG_iI ═ 2,3, …, 6;

image IG_iR channels R of all pixel points_IG，iMultiplying by C_i,RG channel G_IG，iMultiplying by C_i,GThe B channel B_IG，iMultiplying by C_i,BI 2,3, …,6, obtaining new RGB three channels, and forming a corrected image IGC_i。

Image IER₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4The pixel point of the connected region is set to 1, and other pixel points are set to 0 to obtain a matrix JZ₁Original image IG₁The values of the R channels of all the pixel points in (1) are used as a matrix R_IG,1Original image IG₁The values of the G channels of all the pixel points in (1) are used as a matrix G_IG,1Original image IG₁The values of the B channels of all the pixel points in (1) are used as a matrix B_IG,1(ii) a Will matrix JZ₁Dot-by-dot matrix R_IG,1Obtaining a matrix DCR₁Will matrix JZ₁Dot-product matrix G_IG,1Obtaining a matrix DCG₁Will matrix JZ₁Dot-by-dot matrix B_IG,1Obtaining a matrix DCB₁；

R_1，ave＝sum(sum(DCR₁))/sum(MJ₁)，

G_1，ave＝sum(sum(DCG₁))/sum(MJ₁)，

B_1，ave＝sum(sum(DCB₁))/sum(MJ₁)，

Of these, sum (DCR)₁) Is a matrix DCR₁Sum of all the element values in (1), sum (DCG)₁) Is a matrix DCG₁Sum of all the element values in (1), sum (DCB)₁) Is a matrix DCB₁Sum of all element values in, sum (MJ)₁) Is an image IER₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4Total number of pixels of connected region, MJ₁＝regionprops(JZ₁The 'Area' attribute is the number of pixels in each Area of the image.

IGC sample image_iThe B channel of (a) is converted to a corresponding color invariant: b_i＝B_IGC,i,ave/(R_IGC,i,ave+G_IGC,i,ave+B_IGC,i,ave) Calculating the blue decay percentage% B_t：

Wherein, b_t0B channel invariant when t is 0, B_tIs the color invariant of the B channel at time t; percentage of blue decay% B_tThe browning process is shown as follows: y ═ Y₀+kt，

Wherein Y is the absorbance at 420nm or the 5-HMF content or% B_t，Y₀Is the absorbance at 420nm or the 5-HMF content or% B_tT is time and k is the velocity constant.

The invention has the beneficial effects that: placing a foaming wine sample in a hole in the middle of a 96-hole plate, placing the hole plate on a diffuse light source panel at the bottom of an acquisition box, taking a smart phone as image acquisition equipment, obtaining a digital image of the foaming wine from the acquisition hole at the top of the acquisition box, performing digital image processing and analysis, detecting the browning of the foaming wine in an RGB color space, and determining the browning degree of the foaming wine; in comparison to two widely used methods of studying absorbance at 420nm and obtaining 5-HMF content, the percentage of blue channel decay is highly correlated with the commonly used browning index and is a new marker for browning of sparkling wines. The invention can simultaneously analyze the browning samples of the foaming wines of a plurality of brands by only acquiring the transmission images of the foaming wine samples at different browning stages, avoids complex sample processing, can synchronously analyze a plurality of samples, has high speed and low device price, and does not need expensive professional instruments and other chemical reagents.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flow chart of the present invention.

Fig. 2 is a schematic mechanism diagram of the image capturing apparatus of the present invention.

FIG. 3 shows the arrangement sequence of the samples according to the invention.

Fig. 4 is a grayscale image of a sample of the invention.

FIG. 5 is a binarized image of a sample of the present invention.

FIG. 6 is an image after etching according to the present invention.

Fig. 7 is a schematic representation of the mean change of the R, G, B channels for each brand sample area due to accelerated browning.

Fig. 8 is a percentage image of B-channel decay versus heating time for each brand sample.

FIG. 9 is an image of absorbance at 420nm versus percent blue channel attenuation for each brand sample.

FIG. 10 is a graph of5-HMF content versus percent blue channel decay for each brand sample.

Figure 11 is a qualitative comparison of several algorithms.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.

As shown in fig. 1, a machine vision-based foamed wine browning process detection device and method includes the following steps:

the method comprises the following steps: and (4) building an experimental device and preparing a sample.

Four marketable brands of kava sparkling wines were used as subjects, including Brut, Brut Reserva, Brut Gran Reserva and Semiseco, with the four wines having different sugar contents and production years. The quality parameters for each type of kava wine at the initial sampling are shown in table 1. The content of sugar, alcohol, pH, free and total sulfur dioxide of each sample was measured using the standard methods of the international grape and wine organization. Wherein the alcohol content meets the value marked on the kava wine bottle.

TABLE 14 quality parameters of Cava sparkling wines of the brands

Four brands of sparkling wine, 10mL each, were filled into 420 mL amber vials in N₂Degassing under a gas stream. The 4 amber vials containing different brands of sparkling wine were then placed in a dark environment and stored at an ambient temperature of 8 ℃ for a period of 10 days with negligible browning. Different brands of sparkling wine in the 4 bottles were used as standard samples for subsequent experiments, and the 4 amber vials containing the standard samples were named Bottle1, Bottle2, Bottle3, Bottle 4.

Next, 10mL of each of the four brands of sparkling wine was placed in 4 amber vials of 20mL and placed in N₂Degassing under a gas stream. The 4 amber vials containing different brands of sparkling wine were placed in a completely dark environment and then placed in an ovenA constant temperature of 65. + -. 1 ℃ was set, and an accelerated browning test was conducted. And the 4 amber vials containing the accelerated browning samples were designated Bottle5, Bottle6, Bottle7, Bottle 8.

Sample information was collected on days 0, 2, 4,6, 8 and 10 (6 sampling time points) at 48 hour intervals. At each sampling time point, (1) 1 part of each standard sample of Brut, Brut Reserva, Brut Gran Reserva and Semiseco is extracted firstly, placed in the holes in the middle of a 96-hole plate from top to bottom in sequence, vertically arranged in 1 row and named as the 1 st row; (2) then, 4 parts of samples of Brut, Brut Reserva, Brut Gran Reserva and Semiseco which accelerate browning are extracted, and then 1 column of each brand is put into the 2 nd to 5 th columns of a 96-well plate in sequence, as shown in figure 3. Thus, a total of 120 samples (6 sampling time points × 4 Cava brands × 5 parts (4 accelerated browning samples and 1 standard sample)) were analyzed.

The experimental device comprises a collection box 2 and a light source 4, wherein the light source 4 is arranged below the collection box 2, a 96-hole plate 3 used for containing a sample is arranged on the lower portion of the collection box 2, a collection hole 1 is formed in the top of the collection box 2, and the collection hole 1 is located right above the hole plate 3. The collection box 1 is made of a black foam core board, and is covered with matte black velvet paper to eliminate internal light reflection. The collection box 1 is a cuboid with a height of 80cm such that the difference between the diagonal and central vertical light paths is less than 5% in order to reduce the difference caused by light rays passing through different paths. The light source 4 is a diffuse reflective light source with controllable intensity. The well plate 3 is a 96 well plate made of imported optical transparent pure polystyrene and sterilized by gamma ray.

Step two: and acquiring a sample image by using a camera of the smart phone, and carrying out graying and binarization processing on the acquired RGB image.

Slips-bubbled wine samples were arrayed in wells in the middle of well plate 3 using micropipettes (0.3ml), 0.15ml sample was added per well, well plate 3 was placed on the face plate of light source 4, collection box 2 was covered on well plate 3, and collection well 1 was located directly above well plate 3. The smartphone was placed on the acquisition hole 1 at the top of the acquisition box, and the image was obtained at the highest resolution (3888 × 5152-20030976 pixels) using the built-in camera of the smartphone and saved in JPEG format. When the samples are collected every time, all the samples in the pore plate are obtained to be in the same image, so that the influence caused by the fluctuation of an illumination source or the shaking of the smart phone is avoided. To improve efficiency and allow comparison between different sample images, each time an image is taken, a standard primary sample is placed in column 1 of the well plate, taken from either of the dotted 1, dotted 2, dotted 3, and dotted 4 at each time point used.

The samples were placed in the center of a 96-well plate and arranged in order from left to right, with column 1 being the standard raw sample (1 for each sparkling wine, 4 from Bottle1, Bottle2, Bottle3 and Bottle4, respectively), column 2 being the Brut sample 4 (from Bottle5), column 3 being the Brut Reserva sample 4 (from Bottle6), column 4 being the Brut GranReserva sample 4 (from Bottle7), and column 5 being the Semiseco sample 4 (from Bottle8), as shown in FIG. 3.

Images of samples containing both the accelerated browning sparkling wine and the standard sparkling wine were first acquired, and images containing both the browning samples and the standard samples were collected at subsequent sampling time points. By acquiring 6 images at 6 sampling time points, at 1 st, an image IG of the standard sample in the well plate and the sample subjected to accelerated browning for 0 day was acquired₁(ii) a At pass 2, images IG of the standard sample in the well plate and the sample with accelerated browning over 2 days were taken₂(ii) a At pass 3, images IG of the standard sample in the well plate and the sample with accelerated browning over 4 days were taken₃(ii) a At 4 th time, images IG of the standard sample in the well plate and the sample with accelerated browning over 6 days were taken₄(ii) a At the 5 th time, images IG of the standard sample in the well plate and the sample with accelerated browning over 8 days were obtained₅(ii) a At the 6 th time, an image IG of the standard sample in the well plate and the sample subjected to accelerated browning for 10 days was obtained₆. Before images are acquired at each sampling time point, samples are taken from the Bottle 1-Bottle 8 and placed in the corresponding positions in the well plate, as shown in fig. 3. When the image of the sample is collected, each column with the sample is ensured to be in a vertical state in a preview window of the camera to the greatest extent, so that the obtained image is close to the ideal position for placing the sample in the image 3, and the subsequent images are convenient to useAnd (6) image processing.

Uniformity of illumination and measurement was studied using a white board, which was placed on a diffuse reflective light source, and an image IB (3888 × 5152 — 20030976 pixels) was obtained at the highest resolution using a built-in camera of a smartphone, and the image IB was equally divided into 322 × 243 — 78246 blocks (each block represented as BK)_num1，num2Num1 has a value of 1 to 322, num2 has a value of 1 to 243), and the size of each block is 16 × 16 to 256 pixels. Statistics BK_num1，num2RGB three-channel mean value BK_{num1，num2，ave}。

Wherein R is_IB(x,y)、G_IB(x, y) and B_IB(x, y) respectively represent the value of the R channel, the value of the G channel, and the value of the B channel at the pixel point (x, y) in the image IB. The value range of x is 0-3887, and the value range of y is 0-5151.

Statistics BK_{num1，num2，ave}MAX of (3)_bkAnd minimum MIN_bkCalculated, maximum difference (MAX)_bk-MIN_bk)/MAX_bkLess than 1% indicates less influence of external illumination, satisfying the requirement of the present invention for uniformity of illumination. The present invention uses image data of the center position of the aperture plate to minimize errors.

IG (image group) of RGB (Red Green blue) image obtained by smart phone_i(value of i is 1-6) converting the image into a Gray image Gray_iAnd adopting an average value method, namely extracting the average value of RGB three channels as a gray value:

Gray_i(x,y)＝(R_IG,i(x,y)+G_IG,i(x,y)+B_IG,i(x,y))/3

wherein R is_IG,i(x,y)、G_IG,i(x,y)、B_IG,i(x, y) are each an image IG_iThe value of the R, G, B channel at pixel point (x, y) in (a); gray_i(x, y) represents the gray value of the gray image at the pixel point (x, y), as shown in fig. 4.

The threshold needs to be determined to be able to apply to the Gray image Gray_iCarry out binarizationThe maximum inter-class variance method (Ostu) is simple, stable and effective in processing, and is a method for determining a threshold value frequently adopted in practical application. The Ostu algorithm is considered as a better algorithm for selecting the threshold value in image segmentation, and the algorithm is not influenced by the brightness and the contrast of an image, so the Ostu algorithm is widely applied to digital image processing. The Ostu algorithm divides an image into a background part and a foreground part according to the gray characteristic of the image. The larger the inter-class variance between the background and the foreground is, the larger the difference between two parts constituting the image is, and when part of the foreground is wrongly classified as the background or part of the background is wrongly classified as the foreground, the difference between the two parts is reduced, so that the segmentation with the largest inter-class variance means the probability of wrong classification is the smallest.

Assuming that the gray level of the gray image is L, the gray range is [0, L-1], and the optimal threshold of the gray image is calculated by using the Ostu algorithm as follows:

σ＝Max[w₀(gt)×(u₀(gt)-u)^2+w₁(gt)×(u₁(gt)-u)^2)]

wherein, w₀As a foreground proportion, u₀Is the mean value of the gray levels of the foreground, w₁As background proportion, u₁And u is the average value of the whole gray image, so that the gray value gt with the maximum sigma is the optimal threshold value T of the segmentation image.

For Gray scale image Gray_i(x, y) using the above criteria to find the optimal threshold T, dividing the image into 2 parts, and obtaining the binary image BIN_i(x,y)。

Wherein, Gray_i(x, y) is a Gray image Gray_iThe value of the pixel at the middle (x, y) position, the value of i is 1-6 (6 images are collected in total, 1 image is obtained each time), and the image BIN after binarization_i(x, y) is shown in FIG. 5.

Step three: BIN image_iAll the pixels in the image are inverted to obtain a binary image IR_i(ii) a Using structural elements for IR images_iCorroding to obtain an image IER_iObtaining a sample containingThe constricted region of the well prevents the edges of the well containing the sample from interfering with the image processing of the sample.

D₁A circular structural element with a diameter of 4 is represented, whose creation function is:

D₁＝strel('disk',4)

meaning that a circular structuring element is created with a radius of 4 (i.e. a diameter of 8), disk representing a circular shape. The function of the strel function is to construct a structural element (so-called structural element), which can be regarded as a small image, and is usually used for morphological operations (such as expansion, erosion, opening and closing operations) of the image.

BIN image_iAll the pixels in the image are inverted to obtain an image IR_i. Namely image BIN_iIf the value of the original pixel point is 0, the value is changed into 1; the original pixel value is 1, which becomes 0.

Adopting imeriode function in Matlab to carry out IR on binary image_iThe etching operation in the morphological treatment is carried out by the following specific operation method:

IER_i＝imerode(IR_i,D₁)

wherein, IER_iRepresenting a binarized image IR_iCircular structural element D with diameter of 8₁The image obtained after etching, i ═ 1,2, ·, 6. As shown in fig. 6. Using circular structural elements D₁For the binary image IR_iAnd performing morphological corrosion treatment to remove the boundaries of the empty holes not containing the samples in the image and simultaneously remove the boundaries of the holes containing the samples to obtain the image of the central area of the sample, namely the contraction area of the holes containing the samples, so as to prevent the edges of the holes containing the samples from interfering the image treatment of the samples. In the area of the hole containing the sample in the image, the sample area in the image is corroded by a morphological corrosion method (the purpose of shrinking the sample area is achieved), and only the pixels inside the hole are used, so that the influence of the boundary of the hole is removed.

Step four: image IER_iAnd carrying out connected region marking, and identifying the position of each type of sample according to the connected region marking.

Image IER_iConnected region labeling is performed for processing images of wells containing different samples. If E is communicated with F and F is communicated with G, E is communicated with G. Visually, the dots that are connected to each other form one area, while the dots that are not connected form a different area. Such a set of all points that are connected to each other is called a connected region. The most important method for analyzing the binary image is connected region marking, each single connected region forms an identified block through marking white pixels (targets) in the binary image, and geometric parameters such as areas, outlines, circumscribed rectangles, centroids and invariant moments of the blocks can be further obtained.

The invention adopts a connected region marking function bwleabel in Matlab: [ LJ_i,LNUM_i]＝bwlabel(IER_i8), wherein LNUM_iRepresentation image IER_iThe number of interconnected regions, LNUM because there are 20 samples in each image_i＝20。LJ_iRepresentation and IER_iBeing matrices of equal size, LJ_iThe matrix contains the label image IER_iClass label for each connected region, the labels having values of 1,2, …, LNUM_iAnd 8 in the formula is to search a connected region according to 8 neighborhoods.

The algorithm of the function bwleael is to traverse the image once and note down the equivalent pairs of consecutive blobs and labels in each row (or column), and then relabel the original image by the equivalent pairs. The algorithm is one of the high efficiency at present, a sparse matrix is used in the algorithm, and a Dulmage-Mendelsohn decomposition algorithm is used for eliminating equivalence pairs.

Image IER_iPerforming connected region labeling, wherein each contracted sample region is used as a connected region, and for each connected region, adopting a regionprops function in Matlab: STATS_i＝regionprops(LJ_i'Centroid'), the 'Centroid' attribute is the Centroid of the region (i.e., the Centroid of the connected region).

STATS calculated according to regionprops function_iContains an image IER_iEach of (1) toCentroid coordinates (RX) of each connected region (i.e., each sample region)_i,nu,LY_i,nu) Wherein nu is 1-20. The centroids of the connected regions are arranged as LY according to the column coordinate from small to large_i,1～LY_i,20With the smallest column coordinate LY_i,1～LY_i,4The 4 sample regions are standard sample regions in the sample image (the column has four samples, namely, a Brut standard sample, a BrutReserva standard sample, a Brut Gran Reserva standard sample and a Semiseco standard sample from top to bottom); column coordinate is LY_i,5～LY_i,8The 4 sample regions are Brut sample regions in the sample image; column coordinate is LY_i,9～LY_i,12The 4 sample regions are Brut Reserva sample regions in the sample image; column coordinate is LY_i,13～LY_i,16The 4 sample regions are Brut Gran Reserva sample regions in the sample image; column coordinate is LY_i,17～LY_i,20These 4 sample regions are referred to as semisecoco sample regions in the sample image.

Step five: by image IG₁The average of the R channel, G channel and B channel of the area of the contracted sample well of the standard original sample of (1) is taken as a reference, and a correction factor is calculated for the image IG_iColor correction is carried out on each channel to obtain a corrected image IGC_i，i＝2,…6。

Image IER₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4The pixel point of the connected region is set to 1, and other pixel points are set to 0 to obtain a matrix JZ₁Then the original image IG₁The values of the R channels of all the pixel points in (1) are used as a matrix R_IG,1Original image IG₁The values of the G channels of all the pixel points in (1) are used as a matrix G_IG,1Original image IG₁The values of the B channels of all the pixel points in (1) are used as a matrix B_IG,1. Will JZ₁Dot multiplied by R_IG,1Obtaining the DCR₁A JZ₁Dot-ride G_IG,1To obtain DCG₁A JZ₁Dot-by-dot B_IG,1To obtain DCB₁。

The regionprops function in matlab is used: MJ₁＝regionprops(JZ₁'Area'), calculating image IG₁The mean of the R channels of the area of the shrinkage cavity of the standard sample. The 'Area' attribute contained in the function is the total number of pixels in each Area of the image.

R_1，ave＝sum(sum(DCR₁))/sum(MJ₁)，

G_1，ave＝sum(sum(DCG₁))/sum(MJ₁)，

B_1，ave＝sum(sum(DCB₁))/sum(MJ₁)，

Of these, sum (DCR)₁) Is a matrix DCR₁Sum of all the element values in (1), sum (DCG)₁) Is a matrix DCG₁Sum of all the element values in (1), sum (DCB)₁) Is a matrix DCB₁Sum of all element values in, sum (MJ)₁) Is an image IER₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4Total number of pixels of the connected component. In the same way, G is obtained by calculation_1，aveAnd B_1，ave。

Similarly, calculating to obtain an image IG_iThe mean value R of R channel, G channel and B channel of the area of the constricted sample well of the standard sample_i，ave、G_i，aveAnd B_i，aveWhere i is 2,3, …, 6.

Color correction is then performed. By image IG₁Of the standard raw sample, the mean value R of the R channel, G channel and B channel of the area of the constricted sample well_1，ave、G_1，aveAnd B_1，aveImage IG collected for reference and subsequent different time sampling points_i(i-2, 3, …,6) of the standard original sample in the well region of the average of R, G and B channels is R_i，_ave、G_i，aveAnd B_i，aveFor reference (where i ═ 2,3, …,6), three correction factors C were calculated_i,R、C_i,GAnd C_i,B(where i ═ 2,3, …, 6).

Wherein, C_i,R、C_i,G、C_i,BAs an image IG_iR channel, G channel, and B channel.

Image IG_iR channels R of all pixel points_IG，iMultiplying by C_i,RG channel G_IGI times C_i,GThe B channel B_IG，iMultiplying by C_i,BObtaining new RGB three channels, and the formed image is named as a correction image IGC_iWhere i is 2,3, …, 6.

Step six: calculating a corrected image IGC_iThe B channel was selected as a browning parameter, as an average of R, G, B channels in the area of the constricting orifice for each brand sample.

Obtaining the corrected image IGC by the previous method_i(i-1, 2, …,6) mean R of R, G, B three channels in the constricted region of accelerated browning samples for each brand_IGC,i,ave、G_IGC,i,ave、B_IGC,i,aveAnd drawing, as shown in fig. 7. Fig. 7 shows the evolution of R, G and B channel values for the sample region with heating time. It can be seen that the acceleration change is mainly reflected in the B channel, while the R and G values remain substantially constant. With increasing heating time, this appears as a darker yellow color, i.e. a change to a lighter brown color. The B channel changes for the Brut and GRes samples were clearly linearly dependent, whereas in Res and SS browning began after 48 hours, after which the blue channel values were again linearly dependent on time. The original sparkling wine samples showed slight differences in their color, as the Brut and Brut Reserva (Res) samples were more similar to each other. Whereas semi secoco (ss) and BrutGran resurva (GRes) showed large differences, the largest difference between samples was in the blue channel.

Step seven: calculating the color invariant and blue decay percentage of the B channel; the percentage of blue decay has a linear relationship with time, consistent with the browning process of sparkling wines.

Except for using R_IGC,i,ave、G_IGC,i,ave、B_IGC,i,aveAnalysis of the change in value, and a study of browning using the R, G, B color invariant was also performed.IGC sample image_iIs converted into a corresponding color invariant (B)_i＝B_IGC,i,ave/(R_IGC,i,ave+G_IGC,i,ave+B_IGC,i,ave) To quantify and compare browning. The B channel color invariant is similar to absorbance and the percentage of blue decay (% B) can be calculated_t). At this time b_iCorresponds to b_t。

Wherein, b_t0B channel invariant when t is 0, B_tIs the color invariant of the B channel at time t. FIG. 8 shows% B of the samples studied_tAs a function of time, it can be seen that the browning is reflected in% B_tIncreasing linearly with time.

For the case of Brut,

R²is 0.99.

For a Brut Reserva,

R²is 0.93.

In the case of the semi secoco, the,

R²is 0.93.

For the Brut gray Reserva,

R²is 0.96.

Wherein x is_dayIn time units (days).

(in Shimadzu ultraviolet spectrophotometer)

UV-3600, duisburg, germany) using a 10mm path length quartz cuvette and double distilled water as reference, measure 4 brands of Cava @Absorbance of the brewed wine at 420 nm. At 420nm (A)₄₂₀) The absorbance value of (A) is multiplied by 1000 times and expressed as milli-absorbance units (mAU). The 5-HMF was determined in each sample according to the International grape and wine organization method, and liquid chromatography analysis of 4 brands of Cava sparkling wine was performed using Hitachi liquid chromatograph (Hitachi) with a four stage L-7100 pump, L-7455 diode array detector, and LaChrom chromatography column. The image acquisition equipment is a gorgeous 7 smart phone, is provided with a 5.2-inch touch display screen, has a resolution of 1920 pixels × 1080 pixels and 2000 ten thousand pixel cameras (5152 × 3888 pixel images), and supports PDAF phase detection quick focusing and an F2.0 aperture.

To evaluate the detection effect of the present invention,% B_tWith other conventional browning monitoring parameters (e.g. A)₄₂₀And 5-HMF content), FIG. 9 shows the concentration at 420nm (A)₄₂₀) Measured absorbance and% B_tThe correlation between them.

Linear regression analysis was performed to determine the relationship between these browning indicators:

for the case of Brut,

R²is 0.98.

For a Brut Reserva,

R²is 0.98.

In the case of the semi secoco, the,

R²is 0.99.

For the Brut gray Reserva,

R²is 0.96.

Wherein x is the sample at 420nm (A)₄₂₀) Absorbance of (a) and y is% B_t。

The results show that,% B_tThe browning index represented by a420 showed a similar tendency. It should be noted that there is a high degree of correlation between the two different methods. Considering that 420nm corresponds to a color in the boundary between blue and violet, the absorption band will yellow to orange/brown the sample and accordingly these changes will be reflected in the B channel of the image. Also significant is the agreement between different samples, which are very similar in slope, especially the Brut, Res and SS samples.

On the other hand, FIG. 10 shows% B_tAnd 5-HMF content. Linear regression analysis was performed to determine the relationship between these browning indicators:

for the case of Brut,

R²is 0.93.

For a Brut Reserva,

R²is 0.97.

In the case of the semi secoco, the,

R²is 0.99.

For the Brut gray Reserva,

R²is 0.91.

Wherein x is the 5-HMF content of the sample and y is% B_t。

It can be seen that there is a high correlation between them, particularly the Brut, Res and SS samples. It should be noted that 5-HMF is not the only compound that indicates browning of the wine, and therefore the difference in the value of the slope can be attributed to the presence of other compounds also affecting the color of the wine.

With respect to% B_t5-HMF content and A₄₂₀The results obtained, which characterize the browning process, can be described by the following equation:

Y＝Y₀+kt (8)

wherein Y is the absorbance (mAU) at 420nm or the 5-HMF content or% B_tT is time (in days) and k is the velocity constant (denoted A)₄₂₀mAU/day, 5-HMF mg/L/day for B_tThe percentage decay of the blue channel per day).

Zero-order kinetics (zero-order kinetics) refers to the elimination of a drug at a constant rate in vivo, i.e., the amount of drug eliminated per unit time is constant regardless of the plasma drug concentration. The main reason for the zero order kinetic process is the saturation process of drug metabolizing enzyme, drug transporter and drug binding with plasma protein, and the zero order kinetic process has the characteristic of active transport. Zero order kinetics are established from natural force systems such as electromagnetic forces, biomechanics, attraction. The zero-order dynamics has rich connotation, natural formation, profound enlightenment and wide application. The invention adopts the related theory of zero-order dynamics to research the browning of the sparkling wine. The formula for the zero order kinetics is the same as above (in this case k is the zero order rate constant, Y₀Initial blood concentration, blood concentration when Y is t). The calculated rate constants and monitoring methods for zero order kinetics for each sample are shown in table 2. It can be seen that% B is used_tZero order kinetics were also observed as a control variable (table 2 and figure 8). Furthermore, although the values of the evaluated browning rate constants differ according to the different methods of use, the relationship between the results does follow the same trend.

TABLE 2 zero order kinetic parameters (A)₄₂₀、5-HMF、％B_t)

As time increases, the sparkling wine is continuously fermented (from Brut Gran Reserva to Brut Reserva), and the rate constant of browning increases with increasing sugar content (from Brut to Semiseco). Shows a constant rate of increase in sugar content, as expected, 5-HMF formation is highly correlated with the initial sugar content, since the rate of5-HMF formation is sugar dependent (Camara J S, Alves M A, Marques J C. changes in volatile composition of microorganisms during oxidation [ J ] analytical Chimica Acta,2006,563(1): 188-. Thus, the sparkling wine that is least affected by the browning process appears to be the highest quality wine (Brut GranReserva, Brut Reserva). Fig. 11 graphically summarizes the results obtained and it can be seen that the present invention allows the browning process to be characterized and is in full accord with known methods.

The invention provides a colorimetric method for monitoring browning process of sparkling wine, which has high speed and low consumption. The camera of the smart phone is used as a collecting device and is used for analyzing the transmission image of the Kawa wine, so that complex sample processing is avoided, and single-step multi-sample analysis can be performed. The present invention proposes a new control parameter, the percentage of blue channels decaying over time, which allows the browning kinetics to be studied and characterized. That is, the R, G channel remains almost unchanged during browning, which is time-dependent and affects mainly the B channel with time. The invention provides that the blue channel attenuation percentage percent Bt is used as a quality marker of sparkling wine, the value is highly related to the absorbance at 420nm and the content of 5-hydroxymethyl-2-furfural, the absorbance at 420nm and the content of 5-hydroxymethyl-2-furfural are common quality markers of wine browning, and the obtained result is completely consistent with the existing research method. Thus, the new parameters are highly correlated with the presence of furfural compounds, reflected in the correlation with a420 and to a lesser extent with the 5-HMF concentration, since this is only one of the colouring compounds involved in the browning process. The result of the invention shows that the percent Bt is a good browning descriptor, the analysis of a plurality of brands of sparkling wine samples can be simultaneously carried out only by acquiring the transmission images of sparkling wine samples at different browning stages, the device has low price, and expensive professional instruments and other chemical reagents are not needed.

The proposed method can be used as an alternative to conventional methods and can be used as a key quality control indicator for sparkling wines. The method proposed by the present invention has proven its usefulness, and therefore further research based on this method would be of great interest.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A method for detecting browning process of sparkling wine based on machine vision is characterized by comprising the following steps:

the method comprises the following steps: building an experimental device and preparing a sample;

step two: acquiring a sample image by using a camera of a smart phone, and acquiring an RGB image IG_iCarrying out graying and binarization processing to obtain a binary image BIN_i，i＝1,2,…,6；

Step three: BIN for binary image by using structural elements_iEtching to obtain image IE_iObtaining a constricted region of the well containing the sample;

step four: image IE_iAll the pixels in the image are inverted to obtain an image IER_i(ii) a Image IER_iCarrying out connected region marking, and identifying each type of sample according to the connected region marking;

step five: by image IG₁The mean value of the R channel, G channel and B channel of the area of the shrinkage hole of the standard original sample as a reference, and calculating a correction factor for the image IG_iColor correction is carried out on each channel to obtain a corrected image IGC_i，i＝2,…6；

Step six: calculating a corrected image IGC_iSelecting a channel B as a browning parameter according to the average value of R, G, B channels in the area of the shrinkage hole of each brand sample;

step seven: calculating the color invariant of the channel B and the blue decay percentage, wherein the blue decay percentage has a linear relation with time, and the blue decay percentage is consistent with the browning process of the sparkling wine and is used as a quality marker for browning detection;

IGC corrected image_iB-channel to B-channel color invariant: b_i＝B_IGC,i,ave/(R_IGC,i,ave+G_IGC,i,ave+B_IGC,i,ave) Calculating the blue decay percentage% B_t：

Wherein, b_t0B is the B channel color invariant when t is 0, B_tIs the B channel color invariant at time t; r_IGC,i,ave、G_IGC,i,ave、B_IGC,i,aveRespectively corrected image IGC_iAccelerated browning of the R, G, B three-channel mean of the constricted region of the sample.

2. A machine vision based detection method of browning process in sparkling wines according to claim 1, characterized in that said samples are Brut, Brut Reserva, Brut Gran Reserva and semi seco four popular brands of kava sparkling wines with different sugar content and production year; 10mL of each of the solutions were taken and charged into 420 mL amber vials in N₂Degassing under airflow; placing the 4 amber vials containing different brands of sparkling wine in a dark environment and maintaining the ambient temperature at 8 ℃; the different brands of sparkling wines in the 4 bottles were used as standard samples for the subsequent 10-day experiment, and the 4 amber vials containing the standard samples were named Bottle1, Bottle2, Bottle3, Bottle 4; then, 10mL of each of the four brands of sparkling wine was filled into 4 amber vials of 20mL and placed in N₂Degassing under airflow; placing the 4 amber vials filled with sparkling wines of different brands in a completely dark environment, then placing the vials in an oven, setting the constant temperature of 65 +/-1 ℃, and performing an accelerated browning test; the 4 amber vials containing the accelerated browning samples were designated Bottle5, Bottle6, Bottle7, Bottle 8; collecting sample information at sampling time points of 0, 2, 4,6, 8 and 10 days, wherein the collection time interval is 48 hours; at each sampling time, (1) 1 part each of the standard samples of Brut, Brut Reserva, Brutgran Reserva and Semiseco was first extracted, and the wells placed in the middle of a 96-well plate in this order from top to bottomIn the column, 1 is vertically arranged and then named as the 1 st column; (2) then 4 parts of samples of Brut, Brut Reserva, Brut Gran Reserva and Semiseco which accelerate browning are extracted, and then 1 column of each brand is put into the 2 nd to 5 th columns of a 96-well plate in sequence.

3. The machine vision-based sparkling wine browning process detection method according to claim 1, wherein the experimental device comprises a collection box (2) and a light source (4), the light source (4) is arranged below the collection box (2), a pore plate (3) for containing a sample is arranged at the lower part of the collection box (2), a collection hole (1) is arranged at the top of the collection box (2), and the collection hole (1) is positioned right above the pore plate (3).

4. The machine vision-based detection method for browning processes of sparkling wine according to claim 3, characterized in that said collection box (2) is made of black foam core board, and the inside of collection box (2) is covered with matt black velvet paper; the collection box (2) is of a cuboid structure with the height of 80cm, and the difference between a diagonal line and a central vertical light path is less than 5%; the light source (4) is a diffuse reflection light source with controllable intensity; the pore plate (3) is a 96 pore plate, and the pore plate (3) is made of imported optical transparent pure polystyrene and is sterilized by gamma rays.

5. A machine vision based detection method for browning processes of sparkling wines according to claim 2 or 3, characterized in that the method of obtaining the image of the sample is: arranging kava bubble grape wine samples in the middle of a pore plate (3) by using a 0.3ml micropipette, placing the pore plate (3) on a panel of a light source (4), covering an acquisition box (2) on the pore plate (3), positioning the acquisition hole (1) right above the pore plate (3), placing a smart phone on the acquisition hole (1) at the top of the acquisition box, and obtaining images at the highest resolution by using a built-in camera of the smart phone and storing the images as JPEG; the standard raw samples are arrayed in a well plate and all samples are taken in the same image.

6. The machine vision-based sparkling wine browning process detection method according to claim 1, wherein the obtained RGB image is subjected to graying and binarization by:

IG (image group) of RGB (Red Green blue) image obtained by smart phone_iThe average value of R, G, B three components of each pixel is used as the Gray value of the image, i.e. Gray_i(x,y)＝(R_IG,i(x,y)+G_IG,i(x,y)+B_IG,i(x, y))/3 to obtain a Gray image Gray_i；

For Gray scale image Gray_iAn optimal threshold T is calculated using Otsu's algorithm, which is a gray value gt that maximizes σ: assuming that the gray level of the gray image is L, the gray range is [0, L-1]]The optimal threshold for calculating the gray level image by using the Ostu method is as follows: max [ w [ ]₀(gt)×(u₀(gt)-u)^2+w₁(gt)×(u₁(gt)-u)^2)]Wherein w is₀As a foreground proportion, u₀Is the mean value of the gray levels of the foreground, w₁As background proportion, u₁Is the background gray level mean value, and u is the mean value of the whole gray level image;

t is the optimal threshold value of the segmentation image, the gray level image is segmented into 2 parts according to the optimal threshold value T, and the binary image BIN is obtained_i(x,y)：

Wherein, Gray_i(x, y) is the value of the pixel at (x, y) in the grayscale image;

BIN binary image_iObtaining a binary image IR by negation_iIR is subjected to the imode function in Matlab_iCarrying out corrosion operation: IER_i＝imerode(IR_i,D₁) Wherein, IER_iRepresenting a binarized image IR_iCircular structural element D with diameter of 8₁The image obtained after etching, i ═ 1,2,3, ·, 6; d₁Stral ('disk',4), disk denotes a circular shape.

7. Machine vision based detection method for browning process of sparkling wine according to claim 6, characterised in that it consists in detecting the browning process of sparkling wineImage IER_iThe method for marking the connected region comprises the following steps: adopting a connected region mark function bwleabel in Matlab: [ LJ_i,LNUM_i]＝bwlabel(IER_i8), wherein, LNUM_iRepresentation image IER_iNumber of interconnected regions, LJ_iRepresentation and image IER_iMatrices of equal size, the matrix LJ_iContains a label image IER_iClass label for each connected region, the labels having values of 1,2, …, LNUM_iAnd 8, searching a connected region according to 8 neighborhoods;

the method for identifying the position of each type of sample comprises the following steps: the connected regions labeling treats each contracted sample region as a connected region, using, for each connected region, the regionprops function in Matlab: STATS_i＝regionprops(LJ_i'Central'), the 'Central' attribute is the Centroid of the connected region, STATS_iContains an image IER_iOf each connected Region (RX)_i,nu,LY_i,nu) And the subscript nu has a value of 1-20.

8. A machine vision based detection method of browning process of sparkling wine according to claim 1, characterized in that the corrected image is obtained by: by image IG₁Of the standard raw sample, the mean value R of the R channel, G channel and B channel of the area of the shrinkage cavity_1，ave、G_1，aveAnd B_1，aveFor reference, the mean value of the R channel, the G channel and the B channel of the area of the shrinkage hole where the standard original sample in the images acquired by the subsequent different time sampling points is R_i，ave、G_i，aveAnd B_i，aveFor reference, three correction factors C are calculated_i,R、C_i,GAnd C_i,B：

Wherein, C_i,R、C_i,G、C_i,BAs an image IG_iOf R channel, G channel and B channelCorrection factors, i ═ 2,3, …, 6;

image IG_iR channels R of all pixel points_IG，iMultiplying by C_i,RG channel G_IG，iMultiplying by C_i,GThe B channel B_IG，iMultiplying by C_i,BI 2,3, …,6, obtaining new RGB three channels, and forming a corrected image IGC_i。

9. Machine vision based detection method for browning processes of sparkling wines according to claim 7 or 8, characterized in that the image IER is₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4The pixel point of the connected region is set to 1, and other pixel points are set to 0 to obtain a matrix JZ₁Original image IG₁The values of the R channels of all the pixel points in (1) are used as a matrix R_IG,1Original image IG₁The values of the G channels of all the pixel points in (1) are used as a matrix G_IG,1Original image IG₁The values of the B channels of all the pixel points in (1) are used as a matrix B_IG,1(ii) a Will matrix JZ₁Dot-by-dot matrix R_IG,1Obtaining a matrix DCR₁Will matrix JZ₁Dot-product matrix G_IG,1Obtaining a matrix DCG₁Will matrix JZ₁Dot-by-dot matrix B_IG,1Obtaining a matrix DCB₁；

R_1，ave＝sum(sum(DCR₁))/sum(MJ₁)，

G_1，ave＝sum(sum(DCG₁))/sum(MJ₁)，

B_1，ave＝sum(sum(DCB₁))/sum(MJ₁)，

Of these, sum (DCR)₁) Is a matrix DCR₁Sum of all the element values in (1), sum (DCG)₁) Is a matrix DCG₁Sum of all the element values in (1), sum (DCB)₁) Is a matrix DCB₁Sum of all element values in, sum (MJ)₁) Is an image IER₁The column coordinate of the centroid coordinate in (1) is LY_1,1～LY_1,4Total number of pixels of connected region, MJ₁＝regionprops(JZ₁,'Area') The 'Area' attribute is the number of pixels in each Area of the image.

10. The machine vision-based sparkling wine browning process detection method of claim 1, wherein said blue decay percent% B_tThe browning process is shown as follows: y ═ Y₀+kt，

Wherein Y is the absorbance at 420nm or the 5-HMF content or% B_t，Y₀Is the absorbance at 420nm or the 5-HMF content or% B_tT is time and k is the velocity constant.

Images