A method and system for detecting the ripeness of an olive fruit

Abstract

The application discloses an olive fruit maturity detection method and system, first constructs a first standard model and a second standard model, then obtains a comparison image and an actual hardness calculation parameter of an olive fruit to be detected, calculates a color degree score of the olive fruit according to the comparison image and the first standard model, calculates a hardness score according to the actual hardness calculation parameter and the second standard model, and judges the maturity of the olive fruit according to the color degree score and the hardness score. The olive fruit corresponds to different color changes and different hardness changes at different maturity stages. The application reflects the surface change of the fruit through the color change, and reflects the internal change of the fruit through the fruit hardness. The fruit is evaluated from the two aspects of inside and outside, the false judgment caused by the premature color change or abnormal change of the fruit can be effectively avoided, the accuracy of the maturity detection is improved, the judgment standard of the fruit maturity is standardized, and the dependence of the fruit maturity judgment on the artificial is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fruit detection, in particular to an olive fruit maturity detection method and system. BACKGROUND

[0002] The maturity determination of olives is crucial for the harvesting time and oil quality. Generally, high-quality extra virgin olive oil requires harvesting within the appropriate maturity period and physical pressing within 6 hours after harvesting. The maturity of olives directly affects the acidity, polyphenol content, and flavor of (extra virgin) olive oil or related products. Unripe or overripe fruits greatly affect their natural nutritional components and product quality.

[0003] The maturity of olives is generally determined by the color change and / or surface gloss of the fruits. The industry generally uses a four-level maturity grading system (green, turning, ripe, overripe), i.e., the olives at different maturity stages correspond to different color changes. Specifically, when unripe, the color is generally fresh green or dark green, then turns yellow-green, and becomes purple-black or dark black when fully ripe.

[0004] However, the maturity times of olive fruits from different plants vary greatly, such as different varieties, different light intensities, and different water irrigation conditions, which greatly affect the maturity of olive fruits in the same plot or region. Therefore, some olive fruits may appear to have completed the color change or turned color early, but they are not actually ripe. On the other hand, some olives may not appear to have completed the color change or ripening, but the fruits are actually ripe. Thus, the maturity of olive fruits cannot be scientifically determined solely by the color change of the fruits.

[0005] In addition to the color change of the fruits, the change in fruit hardness also directly affects the maturity of the fruits. As the fruits continue to ripen, their hardness decreases. However, the color change of olives under different varieties, different light intensities, and different water irrigation conditions is not directly positively correlated with the hardness.

[0006] Currently, the maturity of fruits is generally determined by manual judgment, and the harvesting time is arranged accordingly. However, manual visual judgment of fruit maturity can only be based on the observation of fruit skin color and is also affected by the experience of workers. Although there are methods for detecting the maturity of olives by machines in the prior art, the detection index is only color, and the detection accuracy is low. SUMMARY

[0007] The main purpose of the present application is to provide an olive fruit maturity detection method and system to solve the problem of low detection accuracy in the prior art.

[0008] The application achieves the above-mentioned purposes through the following technical solutions:

[0009] A method for detecting the maturity of olive fruit, comprising the following steps:

[0010] A first standard model and a second standard model for judging the maturity of olive fruit are constructed;

[0011] An image for comparison and actual hardness calculation parameters of the olive fruit to be detected are obtained;

[0012] A color degree score of the olive fruit to be detected is calculated according to the image for comparison and the first standard model;

[0013] A hardness score of the olive fruit to be detected is calculated according to the actual hardness calculation parameters and the second standard model;

[0014] The maturity of the olive to be detected is determined according to the color degree score and the hardness score.

[0015] Optionally, the first standard model for judging the maturity of olive fruit is constructed, comprising the following steps:

[0016] A plurality of mature olive fruits are obtained as standard fruits;

[0017] Standard images of the standard fruits are respectively obtained;

[0018] Standard hue values and standard saturation values are generated according to the standard images;

[0019] A color difference value calculation formula is generated according to the standard hue values and the standard saturation values;

[0020] A color score calculation formula is generated according to the color difference value, and the color score calculation formula is output as the first standard model.

[0021] Optionally, the expression of the color difference value calculation formula is: The expression of the first standard model is: Wherein H0 represents the standard hue value, S0 represents the standard saturation value, E max represents the theoretical maximum value of the color difference value, H represents the actual hue value, and S represents the actual saturation value.

[0022] Optionally, the second standard model for judging the maturity of olive fruit is constructed, comprising the following steps:

[0023] A plurality of mature olive fruits are obtained as standard fruits;

[0024] Standard hardness values, standard density values and standard sound speed values of the standard fruits are respectively detected;

[0025] According to each standard hardness value, standard density value and standard sound speed value, a least square method fitting is performed to generate an actual hardness value calculation formula;

[0026] According to the actual hardness value, a hardness score calculation formula is generated, and the hardness score calculation formula is output as a second standard model.

[0027] Optionally, an expression of the actual hardness value calculation formula is: wherein k, m and b are constants, p represents an actual density value of the olive fruit to be detected, V s represents an actual sound speed value; and an expression of the second standard model is: wherein ΔQ max represents a maximum variation of the hardness value, and a calculation expression of ΔQ max = Q1-Q0, Q represents an actual hardness value of the olive fruit to be detected, Q0 represents an ideal hardness value of the mature fruit, and Q1 represents a maximum hardness value of the olive fruit.

[0028] Optionally, a color degree score of the olive fruit to be detected is calculated according to the comparison image and the first standard model, including the following steps:

[0029] The comparison image is obtained, the comparison image is divided into a plurality of standard squares, and a standard square completely filled with the olive fruit image is output as a unit comparison image;

[0030] A unit actual hue value and a unit actual saturation value of each unit comparison image are obtained respectively;

[0031] A weight coefficient is generated for each unit comparison image according to a classification condition, the unit actual hue value and the unit actual saturation value;

[0032] An actual hue value and an actual saturation value are calculated according to each unit actual hue value, unit actual saturation value and weight coefficient of each unit comparison image;

[0033] A color degree score is calculated according to the actual hue value, actual saturation value and first standard model.

[0034] Optionally, a calculation formula of the actual hue value is ; and a calculation formula of the actual saturation value is ; wherein n represents a number of the unit comparison images, i represents a number of each unit comparison image, W i represents the weight coefficient of each unit comparison image, and has a value; Δs i represents the unit actual hue value, Δh i represents the unit actual saturation value, and p i represents an area of the unit comparison image.

[0035] Optionally, the hardness score of the olive fruit to be detected is calculated according to the actual hardness calculation parameter and a second standard model, including the following steps:

[0036] The actual hardness calculation parameter is obtained, and the actual hardness calculation parameter includes an actual density value and an actual sound speed value;

[0037] The actual hardness value is calculated according to the actual density value, the actual sound speed value and a hardness value calculation formula;

[0038] The second standard calculation model is called;

[0039] The hardness score is calculated according to the actual hardness value and the second standard calculation model.

[0040] Optionally, the calculation formula of the maturity is Q = αA + βB, wherein α and β both represent weight values, and α + β = 1.

[0041] Correspondingly, the application also discloses a detection system based on the detection method, which comprises:

[0042] A standard model generation module is configured to construct a first standard model and a second standard model for judging the maturity of the olive fruit;

[0043] A parameter acquisition module is configured to acquire a comparison image of the olive fruit to be detected and an actual hardness calculation parameter;

[0044] A first calculation module is configured to calculate a color degree score of the olive fruit to be detected according to the comparison image and the first standard model;

[0045] A second calculation module is configured to calculate a hardness score of the olive fruit to be detected according to the actual hardness calculation parameter and the second standard model;

[0046] A judgment module is configured to judge the maturity of the olive to be detected according to the color degree score and the hardness score.

[0047] Compared with the prior art, the application has the following beneficial effects:

[0048] The application firstly constructs the first standard model and the second standard model, then acquires the comparison image of the olive fruit to be detected and the actual hardness calculation parameter, calculates the color degree score of the olive fruit according to the comparison image and the first standard model, calculates the hardness score according to the actual hardness calculation parameter and the second standard model, and comprehensively judges the maturity of the olive fruit according to the color score and the hardness score.

[0049] The olive fruit corresponds to different color changes and different hardness changes at different maturity stages. Specifically, when unripe, the color is generally fresh green or dark green, then turns yellow-green, and after complete maturity, it is purple-black or dark black. Correspondingly, in terms of hardness, as the fruit continues to mature, the hardness will continue to decrease, and when the hardness reaches 3kg / cm 2 The present application determines standard color and hardness values by using standard ripe fruits, and then establishes a first standard model and a second standard model, which can standardize the determination of fruit maturity, reduce the dependence on artificial determination of fruit maturity, effectively reduce the interference of subjective factors in the determination process, and more objectively and scientifically evaluate the maturity of the fruit, thereby improving the accuracy of the evaluation.

[0050] Compared with the method of simply determining maturity by color, the present application combines hardness determination on the basis of color determination. The change in fruit hardness is directly related to the change in the density of the inside of the fruit, that is, the present application reflects the surface change of the fruit through color change, and reflects the internal change of the fruit through fruit hardness, so that the maturity of the fruit is evaluated from the inside and outside, and thus the present application can effectively avoid misjudgment caused by premature color change or abnormal change of fruit color, and improve the accuracy of fruit maturity detection. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 A flowchart of an olive fruit maturity detection method provided for Embodiment 1 of the present application;

[0052] Figure 2 A calculation principle diagram of color difference value;

[0053] Figure 3 A calculation principle diagram of actual hue value;

[0054] Figure 4 A structural schematic diagram of a detection system provided for Embodiment 2 of the present application;

[0055] The object implementation, functional characteristics and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0057] It should be noted that all the direction indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, motion condition and the like between components in a certain specific posture (as shown in the drawings), and if the specific posture changes, the direction indications will also change accordingly.

[0058] In the present application, unless otherwise explicitly specified and limited, the terms "connection", "fixation" and the like should be understood in a broad sense, for example, "fixation" can be fixed connection, or detachable connection, or integral; can be mechanical connection, or electrical connection; can be direct connection, or indirect connection through an intermediate medium; can be internal communication of two elements or interaction relationship between two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0059] In addition, if the present application embodiments involve "first", "second" and the like, the "first", "second" and the like are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. For example, "A and / or B" includes A solution or B solution or A and B solution. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection claimed by the present application.

[0060] Embodiment 1:

[0061] Referring to Figures 1 to 3 The present embodiment discloses an olive fruit maturity detection method, comprising the following steps:

[0062] S1, constructing a first standard model and a second standard model for judging the maturity of olive fruit;

[0063] S101, obtaining a plurality of mature olive fruits as standard fruits;

[0064] The plurality of olive fruits are selected as standard fruits from the olive fruits by artificial, and it should be noted that all the standard fruits are olive fruits of the same variety, and the first standard model and the second standard model corresponding to different types of olive fruits are respectively established;

[0065] S102, obtaining a standard image of each standard fruit respectively;

[0066] The selected standard fruits are respectively placed on the detection table, and the standard images of the standard fruits are respectively acquired by the industrial cameras;

[0067] Since the whole olive fruit is a cylindrical structure, in the actual shooting process, 2-3 industrial cameras can be used, and a splicing line can be drawn on the olive fruit to splice the images collected by the multiple industrial cameras to obtain the standard image of the whole fruit surface;

[0068] Secondly, the shooting area can be switched without interruption by rotating the olive fruit at a specified angle, and the standard image of the whole fruit surface can be obtained by image splicing, wherein the rotation angle is determined according to the technical parameters of the industrial camera;

[0069] S103, generating standard hue value and standard saturation value according to each standard image;

[0070] Each standard image is retrieved, and the area that can best reflect the maturity of the fruit is manually calibrated on the standard image according to experience. After calibration, the hue value and saturation value of each calibrated area are automatically extracted by the computer;

[0071] Then, the selected hue value and saturation value are integrated to determine the standard hue value and saturation value by calculating the average value or manually calibrating.

[0072] S104, generating a color difference value calculation formula according to the standard hue value and the standard saturation value;

[0073] The expression of the color difference value calculation formula is: wherein H0 represents the standard hue value, S0 represents the standard saturation value, H represents the actual hue value, and S represents the actual saturation value;

[0074] After the fruit is mature, the olive fruit is purple black or dark black, and the color difference value is calculated according to the standard hue value H0 and the standard saturation value S0. Figure 2 In the figure, the diagonal section line is represented, wherein the points calibrated by H0 and S0 represent the points closest to the origin in the qualified area;

[0075] The points calibrated by the actual hue value H and the actual saturation S represent the actual points of the olive fruit, and the distance between the points (H0, S0) is the color difference value;

[0076] The greater the color difference value, the farther the actual point is from the mature area, that is, the worse the maturity, and vice versa. When the color difference value is 0, it means that the fruit is mature;

[0077] S105, generating a color score calculation formula according to the color difference value, and outputting the color score calculation formula as a first standard model.

[0078] The expression of the first standard model is: ; wherein E max represents the theoretical maximum value of the color difference value, E max According to the actual situation, the difference between the color value of the unripe fruit and the color value of the fully ripe fruit is set as E max , E max In essence, it represents the range of color difference value changes;

[0079] Since the higher the maturity, the closer the color difference value is to 0, at this time the color score tends to 100, and vice versa, the above establishes a positive correlation between the color score and the maturity, which objectively reflects the maturity of the fruit.

[0080] S106, respectively detecting the standard hardness value, the standard density value and the standard sound speed value of each standard fruit;

[0081] First, measure the weight of the standard fruit, then measure its volume by the drainage method, and calculate the standard density value according to the density calculation formula;

[0082] After completing the calculation of the standard density value, place the standard fruit on the detection table, and measure the hardness of the standard fruit by destructive puncture method, and at the same time, use ultrasonic emission device to irradiate the standard fruit, and measure the sound speed value of ultrasonic shear wave synchronously;

[0083] Repeat the above steps to obtain several sets of parameter values (Q', ρ', V s ')1, (Q', ρ', V s ')2, (Q', ρ', V s ')3,..., (Q', ρ', V s ') e , wherein e represents the number;

[0084] S107, according to each standard hardness value, standard density value and standard sound speed value, fitting to generate an actual hardness value calculation formula by least square method;

[0085] The actual hardness value calculation formula is: , wherein k, m and b are constants, ρ represents the actual density value of the olive fruit to be detected, and V s represents the actual sound speed value;

[0086] Substitute several sets of standard hardness value, standard density value and standard sound speed value to calculate each constant in the actual hardness calculation formula by least square method, that is, determine the constants k, m and b respectively, and then the actual hardness value calculation formula can be obtained;

[0087] The propagation speed of ultrasonic waves in the pulp is directly related to the density of the fruit, and the density is positively correlated with the hardness of the fruit. Through the above relationship, the propagation speed of ultrasonic waves can be related to the hardness of the fruit. However, unlike materials such as concrete, the arrangement of pulp cells inside the fruit, and the inconsistent degradation speed of cell walls accompanying the softening of the pulp will result in a nonlinear mapping relationship between the hardness of the fruit and its density. The present application represents the above nonlinear mapping through a power relationship, which can more accurately reflect the change relationship between the hardness of the fruit and the density and the actual speed value, thereby improving the accuracy of the maturity determination of the fruit.

[0088] S108, generating a hardness score calculation formula according to the actual hardness value, and outputting the hardness score calculation formula as a second standard model.

[0089] The expression of the second standard model is: where ΔQ max represents the maximum change of the hardness value, and the calculation expression is ΔQ max =Q1-Q0, Q represents the actual hardness value of the olive fruit to be detected, Q0 represents the ideal hardness value of the mature fruit, and Q1 represents the maximum hardness value of the olive fruit.

[0090] The construction principle of the second standard model is the same as that of the first standard model, that is, the closer the actual hardness value is to the ideal hardness value, the closer the hardness score is to 100, and vice versa.

[0091] It should be noted that Q0 represents the ideal hardness value of the mature fruit, which can directly use the standard hardness value in step S106, or can be detected or set separately; Q1 represents the maximum hardness value of the olive fruit, that is, the olive fruit that is not mature or early fruit is artificially selected for actual measurement, and the measurement method is preferably destructive puncture method.

[0092] S2, obtaining a comparison image and an actual hardness calculation parameter of the olive fruit to be detected;

[0093] The olive fruit to be detected is photographed to obtain a comparison image;

[0094] The actual density value of the olive fruit is measured by the drainage method, and the actual speed value of the olive fruit to be detected is measured by the ultrasonic wave emission device. The actual speed value and the actual density value are the actual hardness calculation parameters;

[0095] S3, calculating the color degree score of the olive fruit to be detected according to the comparison image and the first standard model;

[0096] S31, acquire the comparison image, divide the comparison image into several standard squares, and output the standard squares completely filled with the oil olive fruit image as unit comparison images;

[0097] Referring to Figure 3 , call the comparison image obtained by shooting and cutting the comparison image into several standard squares;

[0098] It should be noted that the size of each standard square is determined according to actual conditions, and the minimum area is one pixel unit;

[0099] Since the outer contour line of the oil olive is a curve, there is a deletion area between the background area and the oil olive fruit image after cutting. The standard square of the deletion area contains both the background image and the oil olive fruit image. The standard square of the deletion area is output, and the remaining standard square completely filled with the oil olive fruit image is output as a unit comparison image;

[0100] Calculating the area in the curve region will occupy a large amount of computing power, and the above-mentioned region is small. Taking it out will not affect the final determination result, and can effectively improve the determination efficiency;

[0101] S32, acquire the unit actual hue value and the unit actual saturation value of each unit comparison image respectively;

[0102] The computer reads the unit actual hue values Δs1, Δs2,..., Δs i of each unit comparison image respectively;

[0103] The unit actual saturation values Δh1, Δh2,..., Δh i are also acquired respectively;

[0104] S33, generate a weight coefficient for each unit comparison image according to the classification condition, the unit actual hue value and the unit actual saturation value;

[0105] The classification condition refers to the condition for classifying each unit comparison unit;

[0106] During the growth of the oil olive fruit, the light in some areas is relatively sufficient, which belongs to the light surface; the light in some areas is insufficient, which belongs to the backlight surface; and the remaining areas are transition areas;

[0107] Different light will cause obvious differences in hue value and saturation value in different areas, i.e. the hue value and saturation value of the backlight area will be significantly smaller, and in the generation process of the standard hue value and the standard saturation value, the parameters of the light area are generally used as the standard. Therefore, by classifying and assigning different weight coefficients for adjustment, the calculation error caused by the difference between the hue value and the saturation value is avoided, and the accuracy of the determination is improved;

[0108] It should be noted that the above weight parameters have a total of 3, namely the weight parameter of the light area, the weight parameter of the backlight area and the weight parameter of the transition area, and the above 3 parameters are set by artificial according to the actual situation; for example, the weight parameter of the light area is set to 1, the weight parameter of the backlight area is set to 1.2, and the weight parameter of the transition area is set to 1.1.

[0109] The classification condition is manually determined according to different olive fruit varieties;

[0110] For example, the classification condition is set as follows: the light area has a hue value of 20-60 and a saturation value of not less than 40; the backlight area has a hue value of 90-180 and a saturation value of not greater than 25; and the remaining standard squares are all collected into the transition area.

[0111] S34, according to the actual hue value of each unit, the actual saturation value of each unit and the weight coefficient of each unit compared with the image, the actual hue value and the actual saturation value are calculated respectively.

[0112] After the classification is completed, the calculation parameters of each area can be obtained, that is, (W1, Δs1, p1), (W2, Δs2, p2),..., (W i , Δs i , p i ) and (W1, Δh1, p1), (W2, Δh2, p2),..., (W i , Δh i , p i );

[0113] It should be noted that W1, W2,..., W i can only be selected from the weight parameter of the light area, the weight parameter of the backlight area and the weight parameter of the transition area, for example, if the unit comparison image numbered 1 is determined to be in the backlight area, the weight coefficient is changed to the weight coefficient of the backlight area;

[0114] The calculation formula of the actual hue value is ; the calculation formula of the actual saturation value is ; wherein n represents the number of unit comparison images, i represents the number of each unit comparison image, W i represents the weight coefficient of each unit comparison image, which takes a value; Δsi represents the actual hue value of the unit, Δhi represents the actual saturation value of the unit, and pi represents the area of the unit comparison image.

[0115] (W1, Δs1, p1), (W2, Δs2, p2),..., (W i , Δs i , p i ) are substituted into The actual hue value can be calculated by substituting (W1, Ah1, p1), (W2, Ah2, p2),..., (Wn, Ahn, pn) into the formula (1) respectively. i , Ah i , p i ) into the formula (2) respectively. The actual saturation value can be calculated by substituting (W1, Ah1, p1), (W2, Ah2, p2),..., (Wn, Ahn, pn) into the formula (1) respectively.

[0116] In the above calculation method, not only the hue value and the saturation value under different light conditions are adjusted by different weight coefficients to ensure the accuracy of the prediction result, but also the different colors on the surface of the whole fruit are comprehensively calculated by the partition classification calculation method, so as to accurately reflect the correct hue value and saturation value on the surface of the olive fruit and improve the accuracy of the color prediction.

[0117] S35, calculating the color degree score according to the actual hue value, the actual saturation value and the first standard model.

[0118] The actual hue value and the actual saturation value calculated in the obtaining step S34 are obtained, and then the color difference value of the olive fruit to be detected is calculated according to the color difference value calculation formula The color difference value of the olive fruit to be detected is calculated.

[0119] The calculated color difference value is substituted into the first standard model The color degree score can be calculated.

[0120] It should be noted that when calculating the color difference value, when the fruit is overripe, the hue value and the saturation value will exceed the standard hue value and the standard saturation value. There is a comparison step before calculating the color difference value.

[0121] That is, the actual hue value H is compared with the standard hue value H0, and the actual saturation value S is compared with the standard saturation value S0. If H0 < H and S0 < S are satisfied, the color degree score is directly determined as 100.

[0122] S4, calculating the hardness score of the olive fruit to be detected according to the actual hardness calculation parameter and the second standard model.

[0123] S41, obtaining the actual hardness calculation parameter, the actual hardness calculation parameter including the actual density value and the actual sound speed value.

[0124] The actual density value and the actual sound speed value measured in the calling step S2 are obtained.

[0125] S42, calculating the actual hardness value according to the actual density value, the actual sound speed value and the hardness value calculation formula.

[0126] The actual hardness calculation formula fitted and calculated in the calling step S107 is obtained. The actual density value and the actual sound speed value are substituted into the above formula to calculate the actual hardness value of the oil olive fruit to be detected.

[0127] S43, a second standard calculation model is called;

[0128] S44, a hardness score is calculated according to the actual hardness value and the second standard calculation model.

[0129] The expression of the second standard calculation model is The actual hardness value calculated in step S42 is substituted to obtain the hardness score;

[0130] S5, the maturity of the oil olive to be detected is determined according to the color degree score and the hardness score

[0131] The calculation formula of the maturity is Q = αA + βB, wherein α and β both represent weight values, and α + β = 1; α and β can be flexibly adjusted according to actual conditions;

[0132] The calculation results of steps S35 and S44 are substituted into the above formula to obtain the final maturity parameter, and the maturity of the oil olive fruit to be detected can be determined by comparing the pre-set parameter;

[0133] When 120≤Q<140, it is first-class maturity; when 140≤Q<160, it is second-class maturity; when 160≤Q<180, it is third-class maturity; and when 180≤Q, it is fourth-class maturity;

[0134] The determination result can be quickly output by comparing the above parameters.

[0135] Example 2:

[0136] Referring to Figure 4 , this embodiment discloses a detection system as another feasible embodiment of the present application, which comprises a standard model generation module, a parameter acquisition module and a first calculation module, the standard model generation module and the parameter acquisition module are independent of each other and are respectively connected in communication with the first calculation module, the detection system further comprises a second calculation module, the second calculation module is independent of the first calculation module, and the standard model generation module and the parameter acquisition module are respectively connected in communication with the second calculation module.

[0137] The detection system further comprises a determination module, the determination module is connected in communication with the first calculation module and the second calculation module respectively, so as to determine the maturity of the oil olive to be detected according to the color degree score and the hardness score.

[0138] The olive fruits correspond to different color changes and different hardness changes at different maturity stages. Specifically, the color is generally fresh green or dark green when unripe, then turns yellow-green, and is purple-black or dark black when fully ripe. Correspondingly, in terms of hardness, the hardness will decrease continuously as the fruit ripens, and the optimal maturity is reached when the hardness reaches 3 kg / cm 2 The present application determines standard color and hardness values by using standard ripe fruits, and then establishes a first standard model and a second standard model, which can standardize the maturity determination of fruits, reduce the dependence on manual work for fruit maturity determination, effectively reduce the interference of subjective factors in the determination process, and more objectively evaluate the maturity of fruits, thereby improving the accuracy of evaluation.

[0139] Secondly, compared with the method of simply determining maturity by color, the present application combines hardness determination on the basis of color determination. The change in fruit hardness is directly related to the change in the density of the inside of the fruit. That is, the present application reflects the surface change of the fruit through color change, and reflects the internal change of the fruit through fruit hardness, so that the fruit is evaluated from the inside and outside. Therefore, it can effectively avoid misjudgment caused by premature color change or abnormal change of fruit color, and improve the accuracy of fruit maturity detection.

[0140] The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for detecting the ripeness of an olive fruit, characterized in that, The method comprises the following steps: Obtain a plurality of mature olive fruits as standard fruits; Obtain standard images of the standard fruits respectively; Generate standard hue values and standard saturation values according to the standard images; Generate a color difference value calculation formula according to the standard hue values and the standard saturation values; According to the color difference value, a color score calculation formula is generated, and the color score calculation formula is output as a first standard model; an expression of the color difference value calculation formula is: ; The expression of the first standard model is: ; where H0represents a standard hue value, S0represents a standard saturation value, E max represents a theoretical maximum value of a color difference value, H represents an actual hue value, and S represents an actual saturation value. Obtain a plurality of mature olive fruits as standard fruits; Detect standard hardness values, standard density values and standard sound speed values of the standard fruits respectively; Generate an actual hardness value calculation formula by least square fitting according to the standard hardness values, the standard density values and the standard sound speed values; Generate a hardness score calculation formula according to the actual hardness values, and output the hardness score calculation formula as a second standard model; The expression of the actual hardness value calculation formula is: ; where k, m and b are constants, p represents the actual density value of the olive fruits to be detected, V s represents the actual sound speed value; the expression of the second standard model is: ; where ΔQ max represents the maximum variation of the hardness value, whose calculation expression is ΔQ max = Q1- Q0, Q represents the actual hardness value of the oil olive fruits to be detected, Q0represents the ideal hardness value of the ripe fruits, and Q1represents the maximum hardness value of the oil olive fruits; Obtain a comparison image and actual hardness calculation parameters of a to-be-detected olive fruit; calculate a color degree score of the to-be-detected olive fruit according to the comparison image and the first standard model; Calculate a hardness score of the to-be-detected olive fruit according to the actual hardness calculation parameters and the second standard model; Determine the maturity of the to-be-detected olive fruit according to the color degree score and the hardness score; The calculation formula of the maturity is Q = αA + βB, wherein α and β represent weight values, and α + β = 1.

2. The method for detecting the ripeness of olive fruits according to claim 1, characterized in that, The method for calculating the color degree score of the to-be-detected olive fruit according to the comparison image and the first standard model comprises the following steps: Obtain a comparison image, divide the comparison image into a plurality of standard squares, and output a standard square completely filled with an olive fruit image as a unit comparison image; Obtain unit actual hue values and unit actual saturation values of the unit comparison images respectively; Generate weight coefficients for the unit comparison images according to classification conditions, the unit actual hue values and the unit actual saturation values; Calculate actual hue values and actual saturation values according to the unit actual hue values, the unit actual saturation values and the weight coefficients of the unit comparison images respectively; Calculate a color degree score according to the actual hue values, the actual saturation values and the first standard model.

3. The method for detecting the ripeness of olive fruits according to claim 2, characterized in that, The calculation formula of the actual hue value is: ; The calculation formula of the actual saturation value is: ; wherein n represents the number of unit comparison images, i represents the number of each unit comparison image, W i represents the weight coefficient of each unit comparison image, and the value is; Δs i represents the unit actual hue value, Δh i represents the unit actual saturation value, p i represents the area of the unit comparison image.

4. The method for detecting the ripeness of olive fruits according to claim 1, characterized in that, The method for calculating the hardness score of the to-be-detected olive fruit according to the actual hardness calculation parameters and the second standard model comprises the following steps: Obtain actual hardness calculation parameters, wherein the actual hardness calculation parameters comprise actual density values and actual sound speed values; Calculate actual hardness values according to the actual density values, the actual sound speed values and the hardness value calculation formula; Call the second standard calculation model; Calculate a hardness score according to the actual hardness values and the second standard calculation model.

5. A detection system based on the detection method according to any one of claims 1 to 4, characterized in that, The method comprises the following steps: A standard model generation module is configured to obtain a plurality of mature olive fruits as standard fruits; Obtain standard images of the standard fruits respectively; Generate standard hue values and standard saturation values according to the standard images; Generate a color difference value calculation formula according to the standard hue values and the standard saturation values; According to the color difference value, a color score calculation formula is generated, and the color score calculation formula is output as a first standard model; an expression of the color difference value calculation formula is: ; an expression of the first standard model is: ; wherein H0 represents a standard hue value, S0 represents a standard saturation value, E max represents a theoretical maximum value of the color difference value, H represents an actual hue value, and S represents an actual saturation value. Obtain a plurality of mature olive fruits as standard fruits; Detect standard hardness values, standard density values and standard sound speed values of the standard fruits respectively; Generate an actual hardness value calculation formula by least square fitting according to the standard hardness values, the standard density values and the standard sound speed values; According to the actual hardness value, a hardness score calculation formula is generated, and the hardness score calculation formula is output as a second standard model; The expression of the actual hardness value calculation formula is: wherein k, m and b are constants, p represents the actual density value of the oil olive fruits to be detected, V s represents the actual sound speed value; the expression of the second standard model is: wherein ΔQ max represents the maximum change amount of the hardness value, and the calculation expression of ΔQ max =Q1-Q0, Q represents the actual hardness value of the oil olive fruits to be detected, Q0 represents the ideal hardness value of the mature fruits, and Q1 represents the maximum hardness value of the oil olive fruits. A parameter acquisition module is configured to acquire a comparison image of the oil olive fruit to be detected and actual hardness calculation parameters; A first calculation module is configured to calculate a color degree score of the oil olive fruit to be detected according to the comparison image and the first standard model; A second calculation module is configured to calculate a hardness score of the oil olive fruit to be detected according to the actual hardness calculation parameters and the second standard model; A determination module is configured to determine the maturity of the oil olive to be detected according to the color degree score and the hardness score.

Images