Flour quality detection method and system based on optical analysis

Abstract

The invention relates to the technical field of optical detection, in particular to a flour quality detection method and system based on optical analysis. The method comprises the following steps: firstly, acquiring a Raman spectrum image corresponding to each local detection area of a flour sample by utilizing a Raman spectrometer comprising a plurality of intelligent sensors; according to the morphological distribution characteristics of the to-be-analyzed fluctuation peak in the Raman spectrum image and the overlap ratio of the to-be-analyzed fluctuation peak and the preset frequency shift standard range corresponding to each flour component, acquiring a component fluctuation peak and a flour component corresponding to the component fluctuation peak; according to the impurity possibility degree of the component fluctuation peaks, impurity fluctuation peaks are screened out from the component fluctuation peaks; and obtaining the flour quality of the flour sample according to the overall level condition and the difference condition of the impurity measurement corresponding to all the local detection areas of the flour sample. By deeply analyzing the characteristics of the fluctuation peaks corresponding to the impurities in the flour, the fluctuation peaks corresponding to the impurities are more accurately detected, and the flour quality detection effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optical detection, and in particular to a flour quality detection method and system based on optical analysis. Background Art

[0002] Flour is the basic raw material of the food industry. The quality of flour is directly related to the safety of the final product. In order to ensure the quality and safety of the product, flour quality testing is required. By timely testing the quality of flour, problems in the flour production process can be discovered and solved in a timely manner, helping factories optimize the production process to produce products that better meet market demand.

[0003] In flour quality testing, Raman spectral imaging technology is an advanced non-destructive testing technology. The Raman spectral image of flour can reflect the existence and distribution of various chemical components in flour. The existing technology uses the Raman spectral image of flour to detect flour quality. However, in the process of using the Raman spectral image of flour to detect flour quality, the similar molecular structure of flour and impurities makes the recognition effect of the fluctuation peak corresponding to the impurity poor, making it difficult to ensure the accuracy of flour quality testing. Summary of the invention

[0004] In order to solve the technical problem that the prior art is difficult to ensure the accuracy of flour quality detection, the purpose of the present invention is to provide a flour quality detection method and system based on optical analysis. The technical solution adopted is as follows:

[0005] A flour quality detection method based on optical analysis, the method comprising:

[0006] Obtaining Raman spectrum images corresponding to each local detection area of ​​the flour sample;

[0007] In the Raman spectrum image, all the fluctuation peaks to be analyzed of each spectrum line are obtained according to the fluctuation of each spectrum line; according to the morphological distribution characteristics of the fluctuation peaks to be analyzed and the overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard range corresponding to each flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and the flour components corresponding thereto;

[0008] Any component fluctuation peak in the Raman spectrum image is used as the impurity peak to be analyzed; the impurity possibility of the impurity peak to be analyzed is obtained according to the overlap difference between each component fluctuation peak in the Raman spectrum image to which the impurity peak to be analyzed belongs and the corresponding preset frequency shift standard range, and the area difference between the impurity peak to be analyzed and all its corresponding component fluctuation peaks; according to the impurity possibility of the component fluctuation peak, the impurity fluctuation peak is screened out from the component fluctuation peak;

[0009] According to the proportion of the impurity fluctuation peaks in the Raman spectrum image, the impurity measurement of the local detection area is obtained; according to the overall level and difference of the impurity measurement corresponding to all the local detection areas of the flour sample, the flour quality index of the flour sample is obtained.

[0010] Furthermore, the method for obtaining the fluctuation peak to be analyzed includes:

[0011] Take any spectrum line as the target spectrum line, obtain all peak points and all valley points of the target spectrum line; take the target spectrum line corresponding to the valley point before each peak point to the valley point after each peak point as each fluctuation peak to be analyzed of the target spectrum line.

[0012] Furthermore, the method for obtaining the component fluctuation peak includes:

[0013] Obtaining a first degree of probability of a component of the fluctuation peak to be analyzed according to distribution characteristics of the peak point and the valley point in the fluctuation peak to be analyzed;

[0014] According to the overlap between the fluctuation peak to be analyzed and the preset frequency shift standard range corresponding to each flour component, obtaining the second possible degree of the component of the fluctuation peak to be analyzed and the corresponding flour component;

[0015] Obtaining the component confidence of the fluctuation peak to be analyzed according to the first component possibility and the second component possibility;

[0016] According to the component confidence of the fluctuation peak to be analyzed and its corresponding flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and their corresponding flour components.

[0017] Furthermore, the method for obtaining the first possible degree of the component includes:

[0018] The interval between the horizontal coordinate values ​​of the two valley points corresponding to the fluctuation peak to be analyzed is taken as the total width of the fluctuation peak to be analyzed;

[0019] The interval between the maximum ordinate value and the minimum ordinate value corresponding to the fluctuation peak to be analyzed is taken as the total height of the fluctuation peak to be analyzed;

[0020] The interval between the abscissa values ​​of the peak point and the previous valley point is taken as the first width of the fluctuation peak to be analyzed;

[0021] The interval between the abscissa values ​​of the peak point and the next valley point is taken as the second width of the fluctuation peak to be analyzed;

[0022] Calculate the absolute value of the difference between the first width and the second width to obtain an asymmetry parameter;

[0023] Calculate the sum of the asymmetry parameter and the preset denominator adjustment factor, calculate the product of the total width of the fluctuation peak to be analyzed and the total height of the fluctuation peak to be analyzed, calculate the ratio of the product to the sum, and obtain the first possibility degree of the component of the fluctuation peak to be analyzed.

[0024] Furthermore, the method for obtaining the second possible degree of the component of the fluctuation peak to be analyzed and the corresponding flour component includes:

[0025] The interval corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the fluctuation peak to be analyzed is used as the displacement interval of the fluctuation peak to be analyzed;

[0026] Obtain the displacement interval of the fluctuation peak to be analyzed and the overlapping interval corresponding to the preset frequency shift standard range of each flour component; use the interval between the minimum horizontal coordinate value and the maximum horizontal coordinate value corresponding to the largest overlapping interval as the second possible degree of the component of the fluctuation peak to be analyzed; use the flour component corresponding to the largest overlapping interval as the flour component corresponding to the component fluctuation peak.

[0027] Furthermore, the method for obtaining the impurity possibility includes:

[0028] In the Raman spectrum image to which the impurity peak to be analyzed belongs, according to the difference in the degree of overlap between the fluctuation peaks of each component and the corresponding preset frequency shift standard range, the overall parameter of the overlap difference of the impurity peak to be analyzed is obtained;

[0029] In all Raman spectrum images, the component fluctuation peak that is the same as the flour component of the impurity peak to be analyzed is used as the reference component peak of the impurity peak to be analyzed; according to the area difference between the impurity peak to be analyzed and all its corresponding reference component peaks, the overall parameter of the area difference of the impurity peak to be analyzed is obtained;

[0030] The impurity possibility of the impurity peak to be analyzed is obtained according to the overlap difference overall parameter and the area difference overall parameter; the overlap difference overall parameter and the area difference overall parameter are both positively correlated with the impurity possibility.

[0031] Furthermore, the method for obtaining the overall parameters of the overlap difference includes:

[0032] In the Raman spectrum image to which the impurity peak to be analyzed belongs, the range corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the component fluctuation peak is taken as the first range of the component fluctuation peak; the preset frequency shift standard range of the flour component corresponding to the component fluctuation peak is taken as the second range of the component fluctuation peak; the overlapping range corresponding to the first range and the second range is taken as the third range; the ratio of the horizontal coordinate interval of the third range to the horizontal coordinate interval of the first range is calculated to obtain the standard overlap of the component fluctuation peak; the absolute value of the difference between the impurity peak to be analyzed and the standard overlap of each component fluctuation peak is calculated to obtain the overlap difference local parameter of the component fluctuation peak; the mean value of all overlap difference local parameters is calculated to obtain the overlap difference global parameter.

[0033] Furthermore, the method for obtaining the area difference overall parameter includes:

[0034] The absolute value of the difference between the area of ​​the impurity peak to be analyzed and the area of ​​each component fluctuation peak is calculated to obtain the area local difference parameter of each component fluctuation peak; the mean of all the local area difference parameters is calculated to obtain the area difference overall parameter.

[0035] Furthermore, the method for obtaining the flour quality index of the flour sample includes:

[0036] Calculating the mean of the impurity metrics corresponding to all the local detection areas of the flour sample to obtain the overall impurity parameter;

[0037] Calculate the absolute value of the difference between the impurity metrics corresponding to each two of the local detection areas to obtain the impurity difference parameter corresponding to each two of the local detection areas; calculate the mean of all impurity difference parameters to obtain the overall impurity fluctuation parameter;

[0038] The product of the overall impurity parameter and the overall impurity fluctuation parameter is calculated, and the product is inversely normalized to obtain a flour quality index.

[0039] The present invention proposes a flour quality detection system based on optical analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the flour quality detection method based on optical analysis are implemented.

[0040] The present invention has the following beneficial effects:

[0041] First, a Raman spectrometer containing multiple intelligent sensors is used to obtain Raman spectral images corresponding to each local detection area of ​​the flour sample to provide data support for subsequent analysis. Considering that the fluctuation of the spectral line reflects the different flour components in the flour sample, all the fluctuation peaks to be analyzed for each spectral line are obtained to provide data support for subsequent analysis. First, the morphological distribution characteristics of the fluctuation peaks to be analyzed corresponding to the flour components are taken into account, that is, the fluctuation peaks to be analyzed corresponding to the flour components generally have larger amplitudes, wider wavelength ranges, and symmetrical shapes. It is also considered that different flour components have their specific frequency shift ranges in the Raman spectrum. By analyzing the overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard ranges corresponding to each flour component, the fluctuation peaks generated by the flour components can be obtained and the corresponding flour components can be determined. In order to more accurately screen out the fluctuation peaks corresponding to impurities from the Raman spectrum image, considering that the shift of the fluctuation peak caused by impurities is more local and specific, impurities will cause the corresponding fluctuation peak to shift and change the shape of the fluctuation peak. First, any component fluctuation peak in the Raman spectrum image is used as the impurity peak to be analyzed. By analyzing the characteristics of the fluctuation peak caused by impurities, the impurity fluctuation peak is screened out from the component fluctuation peak, so that the impurity fluctuation peak more accurately reflects the fluctuation peak corresponding to the impurity.

[0042] Considering that the number of impurity fluctuation peaks directly reflects the impurity content in the area, the impurity metric of the local detection area is constructed to reflect the impurity degree of the local area. The larger the impurity metric value, the higher the impurity degree of the local detection area; considering that the larger the corresponding impurity metric of all local detection areas of the flour sample, the higher the overall impurity content of the impurity flour sample; at the same time, considering that large impurities in flour tend to sink and gather under the action of gravity, the impurity distribution corresponding to different local detection areas of the flour sample is uneven, resulting in differences in the impurity metric corresponding to the local detection area, and finally obtaining the flour quality index of the flour sample. The higher the flour quality index, the less impurities there are in the flour, and the better the flour quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flowchart of a flour quality detection method based on optical analysis provided by one embodiment of the present invention;

[0045] Figure 2 A flow chart of a method for obtaining a component fluctuation peak provided by one embodiment of the present invention;

[0046] Figure 3 A flow chart of a method for obtaining the impurity probability provided by one embodiment of the present invention;

[0047] Figure 4 A structural diagram of a flour quality detection system based on optical analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a flour quality detection method and system based on optical analysis proposed by the present invention, its specific implementation, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0049] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0050] The specific scheme of a flour quality detection method and system based on optical analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0051] The present invention provides a flour quality detection method and system based on optical analysis. Figure 1 , which shows a flow chart of a flour quality detection method based on optical analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0052] Step S1: obtaining Raman spectrum images corresponding to each local detection area of ​​the flour sample.

[0053] In order to subsequently detect the quality of the flour sample, it is first necessary to obtain the Raman spectrum images corresponding to each local detection area of ​​the flour sample. The specific steps include: first, the flour sample is evenly placed in each local detection area on the sample table of the Raman spectrometer. Before the Raman spectrum detection, the parameters of the Raman spectrometer containing multiple intelligent sensors are reasonably set to obtain the best Raman spectrum image. Raman spectrum detection is performed on each local detection area, and the spectrum data of each local detection area is recorded by the Raman spectrometer, and the Raman spectrum images corresponding to each local detection area of ​​the flour sample are generated. It should be noted that the method for obtaining the Raman spectrum image is a technical means well known to those skilled in the art, and is only briefly described here. It should be noted that the horizontal axis of the Raman spectrum image represents the Raman frequency shift, that is, the wave number difference of the scattered light relative to the incident light, and different flour components in the flour sample will produce different Raman frequency shifts. The vertical axis of the Raman spectrum image represents the Raman scattered light intensity. The Raman scattering intensity reflects the scattering ability of a specific flour component in the flour sample to the incident light, which is related to the concentration of the flour component.

[0054] It should be noted that, in order to facilitate calculation, all indicator data involved in the calculation in the embodiment of the present invention are preprocessed to eliminate the dimension effect. The specific means of eliminating the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0055] In order to accurately detect the quality of flour, the present invention combines the characteristics of impurities to more accurately screen out the fluctuation peaks corresponding to impurities from the Raman spectrum image to determine the impurity content in the local area, and then combines the distribution characteristics of the flour impurity content of flour samples with higher impurity content in different local detection areas to more accurately detect the flour quality of the flour samples.

[0056] Step S2: In the Raman spectrum image, according to the fluctuation of each spectral line, all the fluctuation peaks to be analyzed of each spectral line are obtained; according to the morphological distribution characteristics of the fluctuation peaks to be analyzed, and the degree of overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard range corresponding to each flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and their corresponding flour components.

[0057] Considering that the fluctuation of the spectral line reflects the different flour components in the flour sample, all the fluctuation peaks to be analyzed for each spectral line are obtained to provide data support for subsequent analysis. First, the morphological distribution characteristics of the fluctuation peaks to be analyzed corresponding to the flour components are taken into account, that is, the fluctuation peaks to be analyzed corresponding to the flour components often have large amplitudes, wide wavelength ranges, and symmetric shapes. It is also considered that different flour components have their specific frequency shift ranges in the Raman spectrum. By analyzing the overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard ranges corresponding to each flour component, the fluctuation peaks generated by the flour components can be obtained and the corresponding flour components can be determined.

[0058] In order to preliminarily identify the fluctuation peak corresponding to the suspected flour component, preferably, in one embodiment of the present invention, the method for obtaining the fluctuation peak to be analyzed includes:

[0059] Take any spectrum line as the target spectrum line, obtain all peak points and all valley points of the target spectrum line; take the target spectrum line corresponding to the valley point before each peak point to the valley point after each peak point as each fluctuation peak to be analyzed of the target spectrum line.

[0060] Regarding the above steps, considering that the Raman spectrum image contains a large number of data points, these data points constitute the spectrum lines in the Raman spectrum image. The flour components contained in the flour sample will cause the spectrum lines to produce fluctuation peaks, that is, the molecular structure contained in the flour will cause the spectrum lines to produce fluctuation peaks. The fluctuation of the spectrum line reflects the vibration of different flour components in the flour sample. In order to extract the fluctuation peaks that may represent the flour components from the spectrum line, it is necessary to analyze each spectrum line in detail, identify all the peak points and valley points, and use the target spectrum line corresponding to the previous valley point to the next valley point of each peak point as the fluctuation peaks to be analyzed of the target spectrum line. The fluctuation peaks to be analyzed preliminarily reflect the fluctuation peaks corresponding to the suspected flour components.

[0061] In one embodiment of the present invention, any one spectrum line is taken as the target spectrum line, and the AMDP peak detection algorithm (Amplitude Modulation Depth Peak Detection Algorithm) is used to obtain all peak points in the target spectrum line, and the data point corresponding to the minimum value between adjacent peak points is taken as the valley point; for any peak point in the target spectrum line, the valley point adjacent to the front side of the peak point is taken as the previous valley point of the peak point; the valley point adjacent to the back side of the peak point is taken as the next valley point of the peak point; the target spectrum line corresponding to the previous valley point to the next valley point is taken as the peak point corresponding to the fluctuation peak to be analyzed; all peak points in the target spectrum line are counted to correspond to the fluctuation peak to be analyzed, and all the fluctuation peaks to be analyzed of the target spectrum line are obtained. It should be noted that the AMDP peak detection algorithm is a prior art well known to those skilled in the art, and will not be described in detail here. It should be noted that the minimum value before the first peak point in the target spectrum line is taken as the first valley point; the minimum value after the last peak point in the target spectrum line is taken as the last valley point.

[0062] To more accurately identify the fluctuation peaks of flour composition, please refer to Figure 2 , which shows a flow chart of a method for obtaining a component fluctuation peak in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining a component fluctuation peak includes:

[0063] Step S201: Obtain the first probability degree of the components of the fluctuation peak to be analyzed according to the distribution characteristics of the peak points and valley points in the fluctuation peak to be analyzed.

[0064] Considering that the fluctuation peaks to be analyzed corresponding to flour components often have large amplitudes, wide wavelength ranges, and symmetrical shapes, the first probability degree of the components of the fluctuation peaks to be analyzed is obtained. The larger the value of the first probability degree of the components, the greater the possibility that the fluctuation peaks to be analyzed correspond to flour components.

[0065] Preferably, in one embodiment of the present invention, the method for obtaining the first possible degree of a component includes:

[0066] The interval between the horizontal coordinate values ​​of the two valley points corresponding to the fluctuation peak to be analyzed is taken as the total width of the fluctuation peak to be analyzed;

[0067] The interval between the maximum ordinate value and the minimum ordinate value corresponding to the fluctuation peak to be analyzed is taken as the total height of the fluctuation peak to be analyzed;

[0068] The interval between the abscissa values ​​of the peak point and the previous valley point is taken as the first width of the fluctuation peak to be analyzed;

[0069] The interval between the abscissa values ​​of the peak point and the next valley point is taken as the second width of the fluctuation peak to be analyzed;

[0070] Calculate the absolute value of the difference between the first width and the second width to obtain an asymmetry parameter;

[0071] The sum of the asymmetry parameter and the preset denominator adjustment factor is calculated, the product of the total width of the fluctuation peak to be analyzed and the total height of the fluctuation peak to be analyzed is calculated, and the ratio of the product to the sum is calculated to obtain the first possible degree of the component of the fluctuation peak to be analyzed. In one embodiment of the present invention, the preset denominator adjustment factor is used to ensure that the denominator is not 0, and the preset denominator adjustment factor is a number greater than 0. In this embodiment, it is set to 0.001, and the implementer can set it according to the implementation scenario.

[0072] For the above steps, the total width of the fluctuation peak to be analyzed reflects the wavelength range occupied by the fluctuation peak in the Raman spectrum image, and the total height of the fluctuation peak to be analyzed represents the amplitude of the fluctuation peak. The first width of the fluctuation peak to be analyzed and the second width of the fluctuation peak to be analyzed are used to evaluate the symmetry of the fluctuation peak. The asymmetry parameter is obtained by calculating the absolute value of the difference between the first width and the second width. The asymmetry parameter quantifies the asymmetry of the fluctuation peak. The smaller the asymmetry, the better the symmetry of the fluctuation peak. Finally, the first possibility degree of the component of the fluctuation peak to be analyzed is obtained. The larger the value of the first possibility degree of the component, the stronger the correlation between the fluctuation peak and the flour component, and the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component.

[0073] Step S202: according to the overlap between the fluctuation peak to be analyzed and the preset frequency shift standard range corresponding to each flour component, obtain the second possible degree of the component of the fluctuation peak to be analyzed and the corresponding flour component.

[0074] Considering that different flour components have their own specific frequency shift ranges in Raman spectra, the second degree of probability of the component of the fluctuation peak to be analyzed is obtained by analyzing the overlap between the fluctuation peak to be analyzed and the preset frequency shift standard range corresponding to each flour component. The larger the value of the second degree of probability of the component, the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component.

[0075] Preferably, in one embodiment of the present invention, the method for analyzing the second possible degree of the component of the fluctuation peak and its corresponding flour component includes:

[0076] The interval corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the fluctuation peak to be analyzed is used as the displacement interval of the fluctuation peak to be analyzed;

[0077] Obtain the displacement interval of the fluctuation peak to be analyzed and the overlap interval corresponding to the preset frequency shift standard range of each flour component; take the interval between the minimum horizontal coordinate value and the maximum horizontal coordinate value corresponding to the largest overlap interval as the second possible degree of the component of the fluctuation peak to be analyzed; take the flour component corresponding to the largest overlap interval as the flour component corresponding to the component fluctuation peak. In one embodiment of the present invention, the method for obtaining the preset frequency shift standard range corresponding to each flour component is as follows: since different flour components will produce Raman peaks in different frequency shift ranges, obtain the frequency shift range corresponding to each flour component in each flour sample from the flour detection system, and take the frequency shift range corresponding to the flour component as the preset frequency shift standard range corresponding to the flour component. For example, the preset frequency shift standard range of the CH bond of the flour component is 2800-3100, and the preset frequency shift standard range of the C=O bond of the flour component is 1600-1800.

[0078] For the above steps, the displacement interval of the fluctuation peak to be analyzed reflects the frequency shift range corresponding to the fluctuation peak to be analyzed; the preset frequency shift standard range corresponding to the flour component reflects the frequency shift range unique to each flour component in the Raman spectrum. By comparison, find out the overlap interval between the displacement interval of the fluctuation peak to be analyzed and the preset frequency shift standard range corresponding to each flour component. The larger the overlap interval, the higher the degree of matching, and the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component. The interval between the minimum horizontal coordinate value and the maximum horizontal coordinate value corresponding to the largest overlap interval is used as the second possibility degree of the component of the fluctuation peak to be analyzed; the larger the value of the second possibility degree of the component, the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component. The flour component corresponding to the largest overlap interval is used as the flour component corresponding to the component fluctuation peak. This means that according to the analysis results of the Raman spectrum, the component fluctuation peak is most likely to come from this specific flour component.

[0079] Step S203: Obtain the component confidence of the fluctuation peak to be analyzed according to the first component probability and the second component probability.

[0080] The first and second probability degrees of the components are combined, and the morphological distribution characteristics and position information of the fluctuation peak to be analyzed are comprehensively considered to obtain the component confidence of the fluctuation peak to be analyzed. The component confidence more accurately reflects the possibility that the fluctuation peak to be analyzed corresponds to the flour component. The greater the component confidence, the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component.

[0081] In one embodiment of the present invention, the product of the first likelihood of the component and the second likelihood of the component is calculated, and the product is normalized to obtain the component confidence of the fluctuation peak to be analyzed. In one embodiment of the present invention, the normalization method is: normalization is performed using the norm normalization function to limit the value range to between 0 and 1.

[0082] Step S204: According to the component confidence of the fluctuation peak to be analyzed and its corresponding flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and their corresponding flour components.

[0083] Considering that the greater the component confidence, the greater the possibility that the fluctuation peak to be analyzed corresponds to the flour component, all the fluctuation peaks to be analyzed are screened according to the component confidence of the fluctuation peak to be analyzed, and the component fluctuation peaks are screened out and their corresponding flour components are obtained.

[0084] In one embodiment of the present invention, the fluctuation peak to be analyzed whose component confidence is greater than a preset confidence threshold is taken as the component fluctuation peak and the flour component corresponding to the component fluctuation peak is determined. In one embodiment of the present invention, the preset confidence threshold is 0.87, and the implementer can set it according to the implementation scenario.

[0085] Considering that the molecular structures of flour and impurities are similar, it is difficult to determine whether flour components are impurities. For example, there are organic whitening agent impurities in flour, and the molecular structure of the organic whitening agent impurities is similar to the molecular structure of natural pigments in flour. In Raman spectroscopy analysis, organic whitening agent impurities and natural pigments may produce similar or overlapping Raman peaks. Due to their similar molecular structures, it is difficult to distinguish whether the component fluctuation peaks are from organic whitening agent impurities or from natural pigments in flour only by corresponding to the flour components through the component fluctuation peaks. It is necessary to further determine the fluctuation peaks corresponding to the impurities based on the characteristics of the fluctuation peaks caused by the impurities.

[0086] Step S3: taking any component fluctuation peak in the Raman spectrum image as the impurity peak to be analyzed; obtaining the impurity possibility of the impurity peak to be analyzed based on the overlap of each component fluctuation peak in the Raman spectrum image to which the impurity peak to be analyzed belongs and the corresponding preset frequency shift standard range, and the area difference between the impurity peak to be analyzed and all its corresponding component fluctuation peaks; and screening out the impurity fluctuation peak from the component fluctuation peaks based on the impurity possibility of the component fluctuation peak.

[0087] Considering that the shift of the fluctuation peak caused by impurities is more local and specific, impurities will cause the corresponding fluctuation peak to shift and change the shape of the fluctuation peak. First, any component fluctuation peak in the Raman spectrum image is used as the impurity peak to be analyzed. By analyzing the characteristics of the fluctuation peak caused by impurities, the impurity fluctuation peak is screened out from the component fluctuation peaks, so that the impurity fluctuation peak can more accurately reflect the fluctuation peak corresponding to the impurity.

[0088] In order to analyze the possibility that the impurity peak to be analyzed is a fluctuation peak caused by impurities, please refer to Figure 3 , which shows a flow chart of a method for obtaining the impurity possibility in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining the impurity possibility includes:

[0089] Step S301: in the Raman spectrum image to which the impurity peak to be analyzed belongs, according to the difference in the degree of overlap between each component fluctuation peak and the corresponding preset frequency shift standard range, the overall parameter of the overlap difference of the impurity peak to be analyzed is obtained.

[0090] In order to more accurately screen out the fluctuation peaks corresponding to impurities from the Raman spectrum image, considering that both impurities and baseline drift will cause the shift of fluctuation peaks, baseline drift will cause all fluctuation peaks in the Raman spectrum image to shift as a whole without changing the shape of a single fluctuation peak; while the shift caused by impurities is more local and specific, that is, impurities will cause the corresponding fluctuation peak to shift, and obtain the overall parameters of the coincidence difference of the impurity peaks to be analyzed. The larger the overall parameters of the coincidence difference, the more different the shift of the impurity peak to be analyzed is from the shift of all fluctuation peaks in the Raman spectrum image, and the more likely the impurity peak to be analyzed is the fluctuation peak caused by impurities.

[0091] Preferably, in one embodiment of the present invention, the method for obtaining the overall parameter of the overlap difference includes:

[0092] In the Raman spectrum image to which the impurity peak to be analyzed belongs, the range corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the component fluctuation peak is used as the first range of the component fluctuation peak; the preset frequency shift standard range of the flour component corresponding to the component fluctuation peak is used as the second range of the component fluctuation peak; the corresponding overlapping range of the first range and the second range is used as the third range; the ratio of the horizontal coordinate interval of the third range to the horizontal coordinate interval of the first range is calculated to obtain the standard overlap of the component fluctuation peak; the absolute value of the difference between the standard overlap of the impurity peak to be analyzed and each component fluctuation peak is calculated to obtain the overlap difference local parameter of the component fluctuation peak; the mean of all the overlap difference local parameters is calculated to obtain the overlap difference overall parameter. It should be noted that the horizontal coordinate interval of the first range is the maximum horizontal coordinate value of the first range minus the minimum horizontal coordinate value, and the horizontal coordinate interval of the third range is the maximum horizontal coordinate value of the third range minus the minimum horizontal coordinate value.

[0093] For the above steps, the larger the third range is, the greater the overlap between the actual frequency shift range of the representative component fluctuation peak and the standard frequency shift range is, and the smaller the representative component fluctuation peak is compared with the standard movement range; calculate the ratio of the abscissa interval of the third range to the abscissa interval of the first range, and use the abscissa interval of the first range to normalize the abscissa interval of the third range to obtain the standard overlap of the component fluctuation peak. The larger the standard overlap is, the smaller the representative component fluctuation peak is compared with the standard movement range. The local parameter of the overlap difference reflects the degree of difference in movement between the impurity peak to be analyzed and the component fluctuation peak, and the overall parameter of the overlap difference comprehensively reflects the overall degree of difference in movement between the impurity peak to be analyzed and all component fluctuation peaks. The larger the overall parameter of the overlap difference is, the more different the shift of the impurity peak to be analyzed is from the shift of all fluctuation peaks in the Raman spectrum image, and the more likely the impurity peak to be analyzed is a fluctuation peak caused by impurities.

[0094] Step S302: In all Raman spectrum images, the component fluctuation peak that is the same as the flour component of the impurity peak to be analyzed is used as the reference component peak of the impurity peak to be analyzed; according to the area difference between the impurity peak to be analyzed and all its corresponding reference component peaks, the overall parameter of the area difference of the impurity peak to be analyzed is obtained.

[0095] Considering that large impurities in flour tend to sink and aggregate under the action of gravity, the distribution of impurities corresponding to different local detection areas of flour samples is uneven, and the degree of shape change of the fluctuation peaks generated by the same impurity in different local detection areas is different. The reference component peak reflects the fluctuation peak of the same flour component as the impurity peak to be analyzed. According to the area difference between the impurity peak to be analyzed and its corresponding all reference component peaks, the overall parameter of the area difference of the impurity peak to be analyzed is obtained. The larger the overall parameter of the area difference, the more likely the area of ​​the fluctuation peak generated by the flour component corresponding to the impurity peak to be analyzed is different from the area of ​​the fluctuation peak generated by the same flour component, and the more likely the impurity peak to be analyzed is the fluctuation peak caused by the impurity.

[0096] Preferably, in one embodiment of the present invention, the method for obtaining the area difference overall parameter includes:

[0097] Calculate the absolute value of the difference between the area of ​​the impurity peak to be analyzed and each component fluctuation peak to obtain the area local difference parameter of each component fluctuation peak; calculate the mean of all area local difference parameters to obtain the area difference overall parameter. It should be noted that, in one embodiment of the present invention, the method for obtaining the area of ​​the component fluctuation peak includes: calculating the interval between the maximum ordinate value and the minimum ordinate value of the component fluctuation peak to obtain the height of the component fluctuation peak; calculating the interval between the maximum abscissa value and the minimum abscissa value of the component fluctuation peak to obtain the width of the component fluctuation peak; calculating the product of the height of the component fluctuation peak and the width of the component fluctuation peak to obtain the area of ​​the component fluctuation peak. In other embodiments of the present invention, the method for obtaining the area of ​​the component fluctuation peak includes: connecting the two endpoints of the component fluctuation peak to obtain a reference straight line, and taking the area corresponding to the region enclosed by the reference straight line and the corresponding spectral line of the component fluctuation peak as the area of ​​the component fluctuation peak.

[0098] For the above steps, the area local difference parameter reflects the area difference between the impurity peak to be analyzed and the component fluctuation peak. Comprehensive analysis is performed to obtain the area difference overall parameter. The larger the area difference overall parameter, the more likely the impurity peak to be analyzed is a fluctuation peak caused by impurities, which means that the area of ​​the fluctuation peak generated by the flour component corresponding to the impurity peak to be analyzed is different from the area of ​​the fluctuation peak generated by the same flour component.

[0099] Step S303: Obtain the impurity possibility of the impurity peak to be analyzed according to the overall parameter of the overlap difference and the overall parameter of the area difference; the overall parameter of the overlap difference and the overall parameter of the area difference are both positively correlated with the impurity possibility.

[0100] The impurity possibility degree of the impurity peak to be analyzed is obtained by comprehensively considering the overlap difference and area difference. The impurity possibility degree comprehensively reflects the possibility that the peak to be analyzed is an impurity peak. The larger the impurity possibility degree, the more likely it is that the impurity peak to be analyzed is a fluctuation peak caused by impurities.

[0101] Preferably, in one embodiment of the present invention, the product of the overlap difference global parameter and the area difference global parameter is calculated, and the product is normalized to obtain the impurity possibility of the impurity peak to be analyzed. In one embodiment of the present invention, the normalization method is: normalization is performed using the norm normalization function to limit the value range to between 0 and 1.

[0102] Considering that the greater the impurity probability, the more likely the impurity peak to be analyzed is to be a fluctuation peak caused by impurities, the impurity fluctuation peak is screened out from the component fluctuation peaks according to the impurity probability of the component fluctuation peak. Preferably, in one embodiment of the present invention, the method for obtaining the impurity fluctuation peak includes:

[0103] The component fluctuation peak whose impurity probability is greater than the preset impurity measurement threshold is marked as an impurity fluctuation peak. In one embodiment of the present invention, the preset impurity measurement threshold is 0.68, which can be set by the implementer according to the implementation scenario.

[0104] Step S4: Obtain the impurity measurement of the local detection area according to the proportion of the number of impurity fluctuation peaks in the Raman spectrum image; obtain the flour quality index of the flour sample according to the overall level and difference of the corresponding impurity measurement of all local detection areas of the flour sample.

[0105] Through the above steps, the fluctuation peaks corresponding to impurities can be screened out more accurately. Considering that the number of impurity fluctuation peaks directly reflects the content of impurities in the area, the impurity degree of the local area is reflected by constructing the impurity metric of the local detection area. The larger the impurity metric value, the higher the impurity degree of the local detection area; considering that the larger the corresponding impurity metric of all local detection areas of the flour sample, the higher the overall impurity content of the impurity flour sample; at the same time, considering that large particles of flour impurities tend to sink and gather under the action of gravity, the impurity distribution corresponding to different local detection areas of the flour sample is uneven, that is, the impurity metric corresponding to the local detection area is different, and finally the flour quality index of the flour sample is obtained. The higher the flour quality index, the less impurities there are in the flour, and the better the flour quality.

[0106] In order to analyze the impurity level of the local detection area, considering that the number of impurity fluctuation peaks corresponding to the local area with a higher impurity level is higher, the impurity metric of the local detection area is constructed to reflect the impurity level of the local area. Preferably, in one embodiment of the present invention, the method for obtaining the impurity metric includes:

[0107] In the Raman spectrum image corresponding to the local detection area, the ratio of the total number of impurity fluctuation peaks to the total number of all fluctuation peaks to be analyzed is calculated to obtain the impurity measurement of the local detection area.

[0108] For the above steps, considering that the number of impurity fluctuation peaks directly reflects the impurity content in the area, by calculating the ratio of the total number of impurity fluctuation peaks and the total number of all fluctuation peaks to be analyzed, the impurity metric of the local detection area is constructed to reflect the impurity level of the local area. The larger the value of the impurity metric, the higher the impurity level of the local detection area.

[0109] In order to analyze the quality of flour, preferably, in one embodiment of the present invention, the method for obtaining the flour quality index of the flour sample includes:

[0110] Calculate the mean of the impurity metrics corresponding to all local detection areas of the flour sample to obtain the overall impurity parameter;

[0111] Calculate the absolute value of the difference between the impurity metrics of each two local detection areas to obtain the impurity difference parameter of each two local detection areas; calculate the mean of all impurity difference parameters to obtain the overall impurity fluctuation parameter;

[0112] The product of the overall impurity parameter and the overall impurity fluctuation parameter is calculated, and the product is inversely normalized to obtain the flour quality index. The overall level is reflected by the mean, and the difference is reflected by the absolute value of the difference. In one embodiment of the present invention, the inverse normalization method is: the inverse of the product is used as the power of an exponential function with a natural constant as the base to obtain a negative correlation mapping result.

[0113] For the above steps, the overall impurity parameter represents the overall content level of impurities in the flour sample. The larger the overall impurity parameter, the higher the average content of impurities in the flour sample. In order to evaluate the uneven distribution of impurities in the flour sample, the absolute value of the difference between the impurity measurements of each two local detection areas is calculated. The absolute value of the difference reflects the difference in impurity content between different areas. The overall impurity fluctuation parameter is averaged for all the absolute values ​​of the difference. The larger the overall impurity fluctuation parameter, the more uneven the distribution of impurities in the flour sample, that is, there is a situation where the impurity content in some areas is different from that in other areas, which means that the flour sample has a higher possibility of impurities. By calculating the product of the overall impurity parameter and the overall impurity fluctuation parameter, the product takes into account the overall content and uneven distribution of impurities at the same time, reflecting the corresponding impurity content of flour. The larger the product, the higher the impurity content of flour. The product is inversely normalized to obtain the flour quality index. The flour quality index can comprehensively and accurately reflect the quality of the flour sample. The higher the flour quality index, the less impurities there are in the flour and the better the flour quality.

[0114] Specifically, flour samples whose flour quality index is greater than the preset quality parameter are marked as high-quality flour, and flour samples whose flour quality index is not greater than the preset first quality parameter are marked as unqualified flour. Product engineers analyze the reasons for the unqualified products and optimize the production process based on the reasons. In one embodiment of the present invention, the preset quality parameter is set to 0.73, and the implementer can set it according to the implementation scenario.

[0115] The present invention also proposes a flour quality detection system based on optical analysis, please refer to Figure 4 , which shows a structural diagram of a flour quality detection system based on optical analysis provided by an embodiment of the present invention, the system includes: a data acquisition module 101, a component fluctuation peak analysis module 102, an impurity fluctuation peak analysis module 103 and a quality analysis module 104.

[0116] The data acquisition module 101 is used to obtain Raman spectrum images corresponding to each local detection area of ​​the flour sample.

[0117] The component fluctuation peak analysis module 102 is used to obtain all the fluctuation peaks to be analyzed of each spectral line in the Raman spectrum image according to the fluctuation of each spectral line; according to the morphological distribution characteristics of the fluctuation peaks to be analyzed and the degree of overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard range corresponding to each flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and their corresponding flour components.

[0118] The impurity fluctuation peak analysis module 103 is used to take any component fluctuation peak in the Raman spectrum image as the impurity peak to be analyzed; obtain the impurity possibility of the impurity peak to be analyzed based on the overlap difference between each component fluctuation peak in the Raman spectrum image to which the impurity peak to be analyzed belongs and the corresponding preset frequency shift standard range, and the area difference between the impurity peak to be analyzed and all its corresponding component fluctuation peaks; and screen out the impurity fluctuation peak from the component fluctuation peaks based on the impurity possibility of the component fluctuation peak.

[0119] The quality analysis module 104 is used to obtain the impurity measurement of the local detection area according to the number ratio of the impurity fluctuation peaks in the Raman spectrum image; and obtain the flour quality index of the flour sample according to the overall level and difference of the corresponding impurity measurement of all local detection areas of the flour sample.

[0120] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the flour quality detection system based on optical analysis and the flour quality detection method based on optical analysis provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0121] In summary, the embodiment of the present invention provides a flour quality detection method and system based on optical analysis. First, according to the morphological distribution characteristics of the fluctuation peaks to be analyzed and the overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard range corresponding to each flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and the flour components corresponding thereto; according to the impurity possibility of the component fluctuation peaks, the impurity fluctuation peaks are screened out from the component fluctuation peaks; according to the overall level and difference of the impurity measurement corresponding to all local detection areas of the flour sample, the flour quality of the flour sample is obtained. In the embodiment of the present invention, the flour quality is analyzed more accurately by deeply analyzing the influence of flour impurities on the fluctuation peaks.

[0122] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0123] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A flour quality detection method based on optical analysis, characterized in that: The method comprises: Obtaining Raman spectrum images corresponding to each local detection area of ​​the flour sample; In the Raman spectrum image, all the fluctuation peaks to be analyzed of each spectrum line are obtained according to the fluctuation of each spectrum line; according to the morphological distribution characteristics of the fluctuation peaks to be analyzed and the overlap between the fluctuation peaks to be analyzed and the preset frequency shift standard range corresponding to each flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and the flour components corresponding thereto; Any component fluctuation peak in the Raman spectrum image is used as the impurity peak to be analyzed; the impurity possibility of the impurity peak to be analyzed is obtained according to the overlap difference between each component fluctuation peak in the Raman spectrum image to which the impurity peak to be analyzed belongs and the corresponding preset frequency shift standard range, and the area difference between the impurity peak to be analyzed and all its corresponding component fluctuation peaks; according to the impurity possibility of the component fluctuation peak, the impurity fluctuation peak is screened out from the component fluctuation peak; According to the proportion of the impurity fluctuation peaks in the Raman spectrum image, the impurity measurement of the local detection area is obtained; according to the overall level and difference of the impurity measurement corresponding to all the local detection areas of the flour sample, the flour quality index of the flour sample is obtained.

2. The flour quality detection method based on optical analysis according to claim 1, characterized in that: The method for obtaining the fluctuation peak to be analyzed comprises: Take any spectrum line as the target spectrum line, obtain all peak points and all valley points of the target spectrum line; take the target spectrum line corresponding to the valley point before each peak point to the valley point after each peak point as each fluctuation peak to be analyzed of the target spectrum line.

3. The flour quality detection method based on optical analysis according to claim 2, characterized in that: The method for obtaining the component fluctuation peak comprises: Obtaining a first degree of probability of a component of the fluctuation peak to be analyzed according to distribution characteristics of the peak point and the valley point in the fluctuation peak to be analyzed; According to the overlap between the fluctuation peak to be analyzed and the preset frequency shift standard range corresponding to each flour component, obtaining the second possible degree of the component of the fluctuation peak to be analyzed and the corresponding flour component; Obtaining the component confidence of the fluctuation peak to be analyzed according to the first component possibility and the second component possibility; According to the component confidence of the fluctuation peak to be analyzed and its corresponding flour component, all the fluctuation peaks to be analyzed are screened to obtain the component fluctuation peaks and their corresponding flour components.

4. The flour quality detection method based on optical analysis according to claim 3, characterized in that: The method for obtaining the first possible degree of the component includes: The interval between the horizontal coordinate values ​​of the two valley points corresponding to the fluctuation peak to be analyzed is taken as the total width of the fluctuation peak to be analyzed; The interval between the maximum ordinate value and the minimum ordinate value corresponding to the fluctuation peak to be analyzed is taken as the total height of the fluctuation peak to be analyzed; The interval between the abscissa values ​​of the peak point and the previous valley point is taken as the first width of the fluctuation peak to be analyzed; The interval between the abscissa values ​​of the peak point and the next valley point is taken as the second width of the fluctuation peak to be analyzed; Calculate the absolute value of the difference between the first width and the second width to obtain an asymmetry parameter; Calculate the sum of the asymmetry parameter and the preset denominator adjustment factor, calculate the product of the total width of the fluctuation peak to be analyzed and the total height of the fluctuation peak to be analyzed, calculate the ratio of the product to the sum, and obtain the first possibility degree of the component of the fluctuation peak to be analyzed.

5. The flour quality detection method based on optical analysis according to claim 3, characterized in that: The method for obtaining the second possible degree of the component of the fluctuation peak to be analyzed and the corresponding flour component includes: The interval corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the fluctuation peak to be analyzed is used as the displacement interval of the fluctuation peak to be analyzed; Obtain the displacement interval of the fluctuation peak to be analyzed and the overlapping interval corresponding to the preset frequency shift standard range of each flour component; use the interval between the minimum horizontal coordinate value and the maximum horizontal coordinate value corresponding to the largest overlapping interval as the second possible degree of the component of the fluctuation peak to be analyzed; use the flour component corresponding to the largest overlapping interval as the flour component corresponding to the component fluctuation peak.

6. The flour quality detection method based on optical analysis according to claim 1, characterized in that: The method for obtaining the impurity possibility includes: In the Raman spectrum image to which the impurity peak to be analyzed belongs, according to the difference in the degree of overlap between the fluctuation peaks of each component and the corresponding preset frequency shift standard range, the overall parameter of the overlap difference of the impurity peak to be analyzed is obtained; In all Raman spectrum images, the component fluctuation peak that is the same as the flour component of the impurity peak to be analyzed is used as the reference component peak of the impurity peak to be analyzed; according to the area difference between the impurity peak to be analyzed and all its corresponding reference component peaks, the overall parameter of the area difference of the impurity peak to be analyzed is obtained; The impurity possibility of the impurity peak to be analyzed is obtained according to the overlap difference overall parameter and the area difference overall parameter; the overlap difference overall parameter and the area difference overall parameter are both positively correlated with the impurity possibility.

7. The flour quality detection method based on optical analysis according to claim 6, characterized in that: The method for obtaining the overall parameters of the overlap difference includes: In the Raman spectrum image to which the impurity peak to be analyzed belongs, the range corresponding to the minimum horizontal coordinate value and the maximum horizontal coordinate value of the component fluctuation peak is taken as the first range of the component fluctuation peak; the preset frequency shift standard range of the flour component corresponding to the component fluctuation peak is taken as the second range of the component fluctuation peak; the overlapping range corresponding to the first range and the second range is taken as the third range; the ratio of the horizontal coordinate interval of the third range to the horizontal coordinate interval of the first range is calculated to obtain the standard overlap of the component fluctuation peak; the absolute value of the difference between the impurity peak to be analyzed and the standard overlap of each component fluctuation peak is calculated to obtain the overlap difference local parameter of the component fluctuation peak; the mean value of all overlap difference local parameters is calculated to obtain the overlap difference global parameter.

8. The flour quality detection method based on optical analysis according to claim 6, characterized in that: The method for obtaining the area difference overall parameter includes: The absolute value of the difference between the area of ​​the impurity peak to be analyzed and the area of ​​each component fluctuation peak is calculated to obtain the area local difference parameter of each component fluctuation peak; the mean of all the local area difference parameters is calculated to obtain the area difference overall parameter.

9. The flour quality detection method based on optical analysis according to claim 1, characterized in that: The method for obtaining the flour quality index of the flour sample comprises: Calculating the mean of the impurity metrics corresponding to all the local detection areas of the flour sample to obtain the overall impurity parameter; Calculate the absolute value of the difference between the impurity metrics corresponding to each two of the local detection areas to obtain the impurity difference parameter corresponding to each two of the local detection areas; calculate the mean of all impurity difference parameters to obtain the overall impurity fluctuation parameter; The product of the overall impurity parameter and the overall impurity fluctuation parameter is calculated, and the product is inversely normalized to obtain a flour quality index.

10. A flour quality detection system based on optical analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the flour quality detection method based on optical analysis as claimed in any one of claims 1 to 9 are implemented.

Images