Leaf image mode classification method and system for double cropping rice ear fertilization

Abstract

The invention provides a leaf image mode classification method and system for double cropping rice spike fertilization, and the method comprises the steps: collecting a first leaf image parameter array and a second leaf image parameter array at a preset time window of target double cropping rice and at a plurality of positions of a first leaf and a second leaf; carrying out image parameter discrete analysis on the parameter arrays to obtain a first dispersion and a second dispersion, and calculating to obtain a leaf pollution degree by combining a preset dispersion; and carrying out averaging processing and leaf pattern classification on the parameter array, and respectively obtaining two leaf pattern arrays based on the image parameters and the pollution degree, thereby determining a proper leaf pattern and carrying out double cropping rice panicle fertilizer application. The technical problem that in the prior art, due to the fact that the test data amount is insufficient, the fertilization recommendation accuracy on different field parcels is not high is solved, and the technical effects that through analysis of the double cropping rice leaf image parameters and the mode classification of the pollution degree, accurate regulation and control of the panicle fertilizer are achieved, and the fertilization recommendation accuracy is improved are achieved.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a leaf image pattern classification method and system for double-cropping rice ear fertilization. Background Art

[0002] Currently, commonly used fertilization recommendation methods are primarily based on years of field trial data, using yield response and agronomic efficiency models to calculate crop fertilizer dosages. However, due to insufficient experimental data, the effectiveness of these methods varies significantly across different fields, affecting the accuracy of fertilization recommendations and making it difficult to meet the precision agriculture fertilization management requirements of farmers. This is particularly true for double-season rice. Due to the differences in the growing environments and nutrient requirements of early and late rice, fertilizer dosages calculated solely based on recommended fertilization methods often fail to adapt to the actual nutrient conditions in the field, leading to inappropriate fertilization and impacting yield and quality. Summary of the Invention

[0003] The present invention addresses the technical problem in the prior art of inaccurate fertilizer recommendations on different fields due to insufficient test data. Based on the recommended fertilization method, a leaf image pattern classification method and system for double-season rice ear fertilization are provided to solve the problem, thereby improving the accuracy of the recommended fertilization method.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a leaf image pattern classification method for double-season rice panicle fertilization, comprising: collecting and obtaining a first leaf image parameter array and a second leaf image parameter array at multiple positions of the first leaf and the second leaf in a preset time window of the target double-season rice; performing image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discrete degree and a second discrete degree, and calculating and obtaining a first leaf contamination degree and a second leaf contamination degree by combining the preset first discrete degree and the preset second discrete degree; performing averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and performing leaf pattern classification based on the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array; processing and obtaining leaf patterns based on the first leaf pattern array and the second leaf pattern array to apply double-season rice panicle fertilizer.

[0005] In a second aspect, the present invention provides a leaf image pattern classification system for double-season rice panicle fertilization, comprising: a leaf acquisition module, for acquiring a first leaf image parameter array and a second leaf image parameter array at multiple positions of the first leaf and the second leaf in a preset time window of the target double-season rice; a pollution degree analysis module, for performing image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discrete degree and a second discrete degree, and calculating the first leaf pollution degree and the second leaf pollution degree in combination with the preset first discrete degree and the preset second discrete degree; a leaf pattern classification module, for performing averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and performing leaf pattern classification based on the first leaf pollution degree and the second leaf pollution degree to obtain a second leaf pattern array; and a fertilization decision module, for processing the obtained leaf pattern based on the first leaf pattern array and the second leaf pattern array to apply double-season rice panicle fertilizer.

[0006] The beneficial effects of the present invention are: During a preset time window for the target double-cropping rice crop, image parameter arrays of the first and second leaves were acquired at multiple locations. Furthermore, at the critical time point of the second leaf emerging from the tip, SPAD values (chlorophyll content parameters) were collected from multiple locations on the third and fourth leaves (first and second leaves) to form parameter arrays, providing basic data for subsequent analysis. Because SPAD values naturally vary at different leaf locations (such as the tip and base), multiple locations were collected to form the arrays. Image parameter dispersion analysis was performed on the first and second leaf image parameter arrays to obtain first and second dispersions. Combining these two preset dispersions, the contamination degree of the first and second leaves was calculated. The leaf contamination degree was calculated by analyzing the dispersion of the SPAD values for the two leaves and comparing them with a preset normal leaf dispersion (e.g., a 10%-15% difference in SPAD values between the center and edge of a leaf). When the surface of double-crop rice leaves is contaminated by dust and other foreign matter, it interferes with the SPAD instrument's accurate measurement of chlorophyll content, leading to deviations in the measured values. Dust and other contaminants covering the leaf surface can cause the SPAD value to be low, and the degree of contamination varies at different locations on the leaf, increasing the dispersion of the SPAD values.

[0007] The first leaf image parameter array and the second leaf image parameter array were averaged and classified into leaf patterns to obtain a first leaf pattern array. Leaf pattern classification was then performed based on the first and second leaf contamination levels to obtain a second leaf pattern array. When the ratio of the first and second leaf image parameters was greater than 1, it indicated that nitrogen was shifting to the third leaf (new leaves), and it was necessary to apply ear fertilizer or increase the amount of ear fertilizer applied. When the ratio was less than 1, it indicated that the SPAD value of the fourth leaf was higher than that of the third leaf, indicating that nitrogen nutrition was sufficient or excessive, and it was necessary to reduce or not apply ear fertilizer. At the same time, by analyzing the ratio of the pollution degree of the first leaf to the second leaf, when the ratio is greater than 1, it indicates that the pollution degree of the third leaf is higher than that of the fourth leaf. This indicates that the third leaf is more susceptible to dust absorption, has a rougher surface, and has a lower nitrogen content than the fourth leaf. However, the fourth leaf has an excess of nitrogen, and the transfer rate to the third leaf is low. This leads to a phenomenon of leaf tanning, and it is necessary to reduce or eliminate ear fertilizer application. When the ratio is less than 1, it indicates that the third leaf is less polluted than the fourth leaf. This indicates that the third leaf is less susceptible to dust absorption and has good nitrogen nutrition. Nitrogen transfer from the fourth leaf to the third leaf is normal, and yellowing occurs. Topdressing ear fertilizer is necessary to meet growth needs. Based on the first and second leaf pattern arrays, leaf patterns are obtained and ear fertilizer application for double-cropping rice is performed. By combining the classification results of the two patterns, the mode is taken as the final leaf pattern, and the ear fertilizer application rate for double-cropping rice is determined based on this. Based on different leaf patterns, it is possible to decide whether to apply normal fertilizer, increase fertilizer application, reduce fertilizer application, or even eliminate fertilizer application, thereby achieving precise regulation of fertilization.

[0008] Through the above-mentioned technical solution, this application overcomes the technical problem in the existing technology of insufficient accuracy of fertilizer recommendations on different fields due to insufficient test data, and achieves the technical effect of accurately regulating ear fertilizer and improving the accuracy of fertilizer recommendations by analyzing the pattern classification of double-season rice leaf image parameters and pollution levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a leaf image pattern classification method for double-cropping rice ear fertilization provided by the present invention; Figure 2 This is a structural schematic diagram of a leaf image pattern classification system for double-season rice ear fertilization provided by the present invention.

[0010] In the accompanying drawings, the components represented by the reference numerals are as follows: Leaf collection module 11, pollution analysis module 12, pattern classification module 13, and fertilization decision module 14. DETAILED DESCRIPTION

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0014] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a leaf image pattern classification method for double-cropping rice ear fertilization, the method comprising: S100: In a preset time window of the target double-season rice, a first leaf image parameter array and a second leaf image parameter array are acquired at multiple positions of the first leaf and the second leaf.

[0015] Specifically, when the target double-season rice grows to a specific stage (i.e., a preset time window), the first leaf and the second leaf of the double-season rice plant are selected, and the SPAD value is measured at multiple different positions of the first leaf and the second leaf respectively by a SPAD instrument, and a set of leaf image parameters (SPAD value) is obtained respectively to form a first leaf image parameter array and a second leaf image parameter array. Among them, the SPAD value represents a non-destructive measurement index of chlorophyll content, which can reflect the nitrogen nutritional status of the plant. The higher the SPAD value of the leaf, the higher the chlorophyll content, which means the better the nitrogen nutritional status of the plant. The first leaf image parameter array refers to an ordered data set composed of SPAD values measured at multiple positions of the first leaf (the third leaf), for example, it can be expressed as {SPAD 11 , SPAD 12 ,...,SPAD 1n}, where each SPAD value corresponds to a specific position on the leaf; similarly, the second leaf image parameter array refers to an ordered data set consisting of SPAD values measured at multiple positions on the second leaf (the fourth leaf), for example, it can be expressed as {SPAD 21 , SPAD 22 ,...,SPAD 2m}.

[0016] The first leaf refers to the third leaf from the top of a double-cropping rice plant, which is the third leaf from the top of the rice plant. The second leaf refers to the fourth leaf from the top of a double-cropping rice plant, which is the fourth leaf from the top of the rice plant. The physiological status of these two leaves can reflect the nitrogen nutritional status of the rice. Multiple locations refer to selecting different sampling points on the same leaf, such as the base, middle, and top of the leaf, or different areas near the main vein and leaf edge. This allows for comprehensive information on leaf nutritional status, avoiding errors that may be caused by single-point measurement, and providing more reliable basic data for subsequent leaf pattern classification.

[0017] By collecting the image parameter arrays of the first and second leaves in the preset time window, basic data is provided for subsequent analysis of the nitrogen nutritional status of double-season rice and determination of panicle fertilizer application strategies.

[0018] S200: Perform image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discreteness and a second discreteness, and calculate a first leaf contamination degree and a second leaf contamination degree by combining a preset first discreteness and a preset second discreteness.

[0019] Specifically, first, a discrete analysis calculation is performed on the acquired first and second leaf image parameter arrays, respectively, to obtain a first and second discreteness that reflects the degree of data dispersion. This discrete analysis is performed by calculating the standard deviation of multiple leaf image parameters within the first and second leaf image parameter arrays. Specifically, the first and second discretenesses are obtained by calculating the standard deviation of multiple SPAD values within the first and second leaf image parameter arrays. A larger standard deviation indicates a greater difference in SPAD values at different locations on the leaf, and a higher degree of dispersion.

[0020] The calculated first dispersion is then compared with a preset first dispersion, and the deviation of the first dispersion from the preset first dispersion is calculated to obtain the first leaf contamination degree. Simultaneously, the second dispersion is compared with a preset second dispersion, and the deviation of the second dispersion from the preset second dispersion is calculated to obtain the second leaf contamination degree. The preset first dispersion refers to the standard dispersion value expected for the first leaf (the third leaf) under normal growth conditions, unaffected by external factors such as dust. The preset second dispersion refers to the standard dispersion value expected for the second leaf (the fourth leaf) under normal growth conditions, unaffected by external factors such as dust. The first leaf contamination degree reflects the roughness and dust adsorption of the first leaf surface due to insufficient nitrogen fertilizer. Under normal circumstances, the SPAD value between the center (near the main vein) and the edge of the leaf can differ by 10%-15%. This is due to differences in the structure and physiological state of different leaf parts. When the leaf surface becomes rough and easily attracted by dust due to insufficient nitrogen fertilizer, this natural difference will change, affecting the dispersion measurement results. The second leaf contamination degree reflects the roughness and dust adsorption on the second leaf surface due to insufficient nitrogen fertilizer. The principle is the same as that of the first leaf contamination degree.

[0021] By obtaining the first leaf contamination degree and the second leaf contamination degree, the nitrogen nutritional status of the leaves can be evaluated, providing a reference for subsequent fertilization decisions.

[0022] S300: Perform averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and perform leaf pattern classification based on the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array.

[0023] Specifically, first, the first leaf image parameter array and the second leaf image parameter array are averaged to obtain the first leaf image parameter and the second leaf image parameter. Averaging involves calculating the average of the SPAD values collected at multiple locations to obtain a single parameter that represents the overall nitrogen status of the entire leaf. For example, the first leaf image parameter is the average of all SPAD values in the first leaf image parameter array; the second leaf image parameter is the average of all SPAD values in the second leaf image parameter array.

[0024] Then, the ratio of the first leaf image parameters to the second leaf image parameters is calculated, and leaf pattern classification is performed to obtain a first leaf pattern array. The ratio of the first leaf image parameters to the second leaf image parameters reflects the nitrogen distribution relationship between the inverted third and inverted fourth leaves. When this ratio is greater than 1, it indicates that nitrogen is being transferred to the new leaves (inverted third), and the plant is growing normally or lacking fertilizer, requiring normal application of ear fertilizer or increased ear fertilizer. When the ratio is less than 1, nitrogen may be sufficient or excessive, and the application of ear fertilizer should be appropriately reduced or omitted. At the same time, the ratio of the first leaf contamination degree to the second leaf contamination degree is calculated, and leaf pattern classification is performed to obtain a second leaf pattern array. The ratio of the first leaf contamination degree to the second leaf contamination degree reflects the difference in surface state between the inverted third and inverted fourth leaves due to differences in nitrogen nutrition. When the ratio is larger, it shows that the inverted third leaf is more likely to absorb dust than the inverted fourth leaf, indicating that the surface of the inverted third leaf is rougher and the nitrogen is insufficient, while the inverted fourth leaf has sufficient nitrogen. The nitrogen is mainly concentrated in the old leaves and the proportion transferred to the new leaves is small. It is necessary to reduce or not apply ear fertilizer; when the ratio is smaller, it shows that the inverted third leaf is less likely to absorb dust than the inverted fourth leaf, indicating that the surface of the inverted third leaf is relatively smooth and the nitrogen nutrition status is good. Nitrogen is transferring from the old leaves to the new leaves, and additional fertilization is needed to meet growth needs.

[0025] By obtaining leaf pattern classification in two different dimensions based on SPAD value ratio and pollution degree ratio, the nitrogen nutritional status of double-season rice can be comprehensively evaluated from multiple angles, providing a comprehensive and accurate reference basis for subsequent panicle fertilizer application decisions.

[0026] S400: Processing and obtaining leaf patterns according to the first leaf pattern array and the second leaf pattern array, and applying double-season rice ear fertilizer.

[0027] Specifically, the fused leaf pattern is first determined by selecting the leaf pattern with the highest frequency of occurrence from both the first and second leaf pattern arrays. This selection method is similar to a voting mechanism: the leaf pattern with the highest frequency of occurrence in each of the two pattern arrays is used as the basis for the final leaf pattern decision. Selecting the leaf pattern with the highest frequency of occurrence reduces errors caused by single-factor decisions and improves decision reliability.

[0028] Then, based on the obtained fused leaf pattern, the application strategy for panicle fertilizer for double-season rice is determined. For example, for double-season early rice, when the fused leaf pattern shows that the leaf color of the lower third and lower fourth are similar (SPAD value within ±5%), panicle fertilizer is applied normally according to the original calculated value. When the fused leaf pattern shows that the leaf color of the lower third is lighter than that of the lower fourth (SPAD value is 5%-15% lower), 50% of the original calculated value is applied as panicle fertilizer. When the fused leaf pattern shows that the leaf color of the lower third is lighter than that of the lower fourth (SPAD value is more than 15% lower), no panicle fertilizer is applied. When the fused leaf pattern shows that the leaf color of the lower third is darker than that of the lower fourth (SPAD value is 5%-15% higher), 120% of the original calculated value is applied as panicle fertilizer. When the fused leaf pattern shows that the leaf color of the lower third is darker than that of the lower fourth (SPAD value is more than 15% higher), 140% of the original calculated value is applied as panicle fertilizer. The fertilization strategy for double-season late rice is similar, but the specific thresholds and fertilizer application rates vary. Among them, the original calculated value refers to the recommended application amount of ear fertilizer calculated based on parameters such as soil nutrient content, target yield, and planting density.

[0029] Through the leaf pattern-based fertilization decision-making method, precise fertilization can be carried out according to the actual nitrogen nutrition status of double-season rice, avoiding the blindness that may be caused by traditional experience-based fertilization, and making up for the limitations of existing fertilization systems in different field applications. It improves the accuracy and targeting of double-season rice ear fertilizer application, which is conducive to improving fertilizer utilization and double-season rice yield.

[0030] Furthermore, in a preset time window of the target double-cropping rice, the first leaf image parameter array and the second leaf image parameter array are acquired at multiple positions of the first leaf and the second leaf, including: S110: selecting multiple positions of the first leaf and the second leaf of the target double-cropping rice at a stage when the second leaf is tip-out, wherein the first leaf is the third leaf and the second leaf is the fourth leaf; S120: Testing and collecting SPAD parameters at multiple positions of the first leaf and the second leaf respectively to obtain a first leaf image parameter array and a second leaf image parameter array.

[0031] In one feasible embodiment, during the tip-out stage of the second leaf of the target double-cropping rice, multiple locations of the first and second leaves are selected on the target double-cropping rice, where the first leaf is the third leaf and the second leaf is the fourth leaf. The tip-out stage of the second leaf refers to the specific period during the growth process of rice when the tip of the second-to-last leaf has just emerged from the leaf sheath. This period is a critical stage in the transition of rice from vegetative growth to reproductive growth. Sampling leaf parameters at this time can more accurately reflect the nitrogen nutritional status of rice. At this stage, the third and fourth leaves are fully expanded and their physiological characteristics are stable, making them ideal sampling targets for assessing the nitrogen status of rice.

[0032] Subsequently, SPAD parameters were tested and collected at multiple locations on the first and second leaves, respectively, to obtain the first leaf image parameter array and the second leaf image parameter array. Specifically, the SPAD instrument was used to perform measurements at multiple selected locations, such as the base, middle, top, or near the main vein and leaf edge, with a SPAD value obtained at each location. These values together constitute the first leaf image parameter array and the second leaf image parameter array. By collecting data at multiple locations, a more comprehensive understanding of the spatial differences in leaf nitrogen distribution can be achieved, providing more reliable basic data for subsequent dispersion analysis and pollution calculations.

[0033] Through the above steps, the SPAD value distribution of double-season rice with three or four leaves in the opposite direction can be obtained within an appropriate time window, providing basic data for subsequent discrete analysis and leaf pattern classification.

[0034] Further, performing image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discreteness and a second discreteness includes: S210: performing image parameter discrete analysis calculation on the first leaf image parameter array to obtain a first discreteness, wherein the image parameter discrete analysis is performed by calculating a standard deviation of a plurality of leaf image parameters in the first leaf image parameter array; S220: Perform image parameter discrete analysis calculation on the second leaf image parameter array to obtain a second discreteness.

[0035] In a preferred embodiment, image parameter dispersion analysis is performed by calculating the standard deviation of multiple leaf image parameters within the first leaf image parameter array to obtain a first dispersion. Specifically, the SPAD values collected at multiple locations on the first leaf (the third leaf) are used as a data set, and the standard deviation of this data set is calculated to obtain the first dispersion. The standard deviation effectively reflects the degree of data dispersion. A larger standard deviation indicates a greater difference in SPAD values between different leaf locations and a higher degree of dispersion. Under normal circumstances, there will be natural differences in SPAD values between the center and the edge of a leaf, and this dispersion analysis can capture the extent of this difference. Simultaneously, image parameter dispersion analysis is performed on the second leaf image parameter array to obtain a second dispersion. Specifically, the standard deviation of the SPAD values collected at multiple locations on the second leaf (the fourth leaf) is calculated to quantify the degree of variation in SPAD values at different locations on the second leaf, providing a data foundation for subsequent analysis of the leaf surface condition.

[0036] Through the above steps, the first discreteness and the second discreteness reflecting the discreteness of the SPAD value distribution of the first leaf and the second leaf were obtained respectively, which will be used to subsequently calculate the leaf contamination degree and then evaluate the nitrogen nutrition status of double-season rice.

[0037] Furthermore, combining the preset first discreteness and the preset second discreteness to calculate and obtain the first leaf contamination degree and the second leaf contamination degree includes: S230: Obtaining the first discreteness and the second discreteness of the same family of double-season rice in a preset time window within a historical period, and obtaining a sample first discreteness set and a sample second discreteness set; S240: Calculate and configure a preset first discreteness and a preset second discreteness according to the sample first discreteness set and the sample second discreteness set; S250: Calculate the magnitudes by which the first dispersion and the second dispersion deviate from the preset first dispersion and the preset second dispersion respectively, and obtain a first leaf contamination degree and a second leaf contamination degree.

[0038] Specifically, first, the SPAD value dispersion data of the inverted third and inverted fourth leaves of the same variety of double-season rice in multiple growing seasons at the stage of the tip of the inverted second leaf are collected to form a sample first dispersion set and a sample second dispersion set. The sample first dispersion set and the sample second dispersion set can reflect the natural discrete state of the SPAD value of the double-season rice leaves under normal growth conditions that are not affected by pollution, and provide a reference basis for determining the preset first dispersion and the preset second dispersion. Then, the sample first dispersion set and the sample second dispersion set are statistically analyzed respectively, such as calculating the mean value or median, etc., to obtain a standard value that can represent the dispersion of the SPAD values of the inverted third and inverted fourth leaves under normal growth conditions, which are used as the preset first dispersion and the preset second dispersion, respectively, representing the natural discrete degree of the leaf SPAD value when not disturbed by pollution.

[0039] Afterwards, the difference amplitude between the first discreteness obtained by the current measurement and the preset first discreteness is calculated to obtain the first leaf contamination degree. Specifically, the degree of contamination of the first leaf can be quantified by calculating the difference between the first discreteness and the preset first discreteness, or the ratio of the two. When the first discreteness is significantly higher than the preset first discreteness, it indicates that the surface of the inverted three-leaf may be rough due to insufficient nitrogen fertilizer and easily absorb dust, thereby increasing the difference in SPAD values at different positions and the first leaf contamination degree is higher. Similarly, the difference amplitude between the second discreteness obtained by the current measurement and the preset second discreteness is calculated to obtain the second leaf contamination degree. When the second discreteness deviates significantly from the preset second discreteness, it indicates that the surface state of the inverted four-leaf is abnormal, and there may be pollution or other influencing factors. By quantifying this degree of deviation, the specific value of the second leaf contamination degree can be obtained.

[0040] By obtaining the first leaf contamination degree and the second leaf contamination degree, the nitrogen nutritional status of double-season rice can be indirectly evaluated, providing an important basis for subsequent fertilization decisions.

[0041] Further, performing averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and performing leaf pattern classification based on the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array, including: S310: performing averaging calculation processing on the first leaf image parameter array and the second leaf image parameter array respectively to obtain first leaf image parameters and second leaf image parameters; S320: Construct a first leaf pattern classifier, wherein the first leaf pattern classifier includes a plurality of first leaf pattern classification branches, an input feature of each first leaf pattern classification branch is a ratio of a first leaf image parameter to a second leaf image parameter, and an output feature is a first leaf pattern; S330: Calculating a ratio of the first leaf image parameter to the second leaf image parameter, combining the cycle category of the target double-season rice, and inputting the ratio into the first leaf pattern classifier for integrated leaf pattern classification to obtain a first leaf pattern array, wherein the cycle category includes early rice or late rice; S340: Construct a second leaf pattern classifier, wherein the second leaf pattern classifier includes a plurality of second leaf pattern classification branches, an input feature of each second leaf pattern classification branch is a ratio of the first leaf pollution degree to the second leaf pollution degree, and an output feature is a second leaf pattern, and the number of the plurality of second leaf pattern classification branches is less than the number of the plurality of first leaf pattern classification branches; S350: Calculate the ratio of the first leaf contamination degree to the second leaf contamination degree, perform integrated leaf pattern classification, and obtain a second leaf pattern array.

[0042] In a preferred embodiment, the first leaf image parameter array and the second leaf image parameter array are each averaged to obtain the first leaf image parameter and the second leaf image parameter. Specifically, the SPAD values at multiple locations on the first leaf are summed and divided by the number of locations to obtain the first leaf image parameter. Similarly, the SPAD values at multiple locations on the second leaf are summed and divided by the number of locations to obtain the second leaf image parameter. These two parameters represent the average chlorophyll content of the upper third and lower fourth leaves, respectively, and can reflect the overall nitrogen nutritional status of the leaves.

[0043] Subsequently, a first leaf pattern classifier was constructed and used to perform leaf pattern classification. The first leaf pattern classifier comprises multiple first leaf pattern classification branches, each of which takes the ratio of the first leaf image parameter to the second leaf image parameter as input and outputs the corresponding leaf pattern category. By calculating the ratio of the first leaf image parameter to the second leaf image parameter, the nitrogen distribution relationship between the inverted third and inverted fourth leaves can be reflected. When the ratio of the first leaf image parameter to the second leaf image parameter is greater than 1, it indicates that nitrogen is being transferred to the new leaves (inverted third), and the plant may need additional fertilization. When the ratio of the first leaf image parameter to the second leaf image parameter is less than 1, the SPAD value of the inverted fourth leaf is higher than that of the inverted third leaf, indicating sufficient or excessive nitrogen nutrition and the need to reduce or eliminate panicle fertilizer. Leaf pattern classification also requires consideration of the target double-season rice cycle (early rice or late rice), as nitrogen requirements for double-season rice plants vary under the same SPAD ratio. Leaf pattern judgment criteria for early and late rice differ due to their different growing environments and growth characteristics. The calculated ratio is input into a first leaf pattern classifier, and the first leaf pattern array is obtained by integrating the results of a plurality of first leaf pattern classification branches.

[0044] At the same time, a second leaf pattern classifier is constructed and used to perform auxiliary leaf pattern classification. The second leaf pattern classifier also contains multiple second leaf pattern classification branches, but the number of branches is less than that of the first leaf pattern classifier, reflecting its auxiliary nature. Each branch uses the ratio of the first leaf pollution degree to the second leaf pollution degree as an input feature and outputs the corresponding leaf pattern category. By calculating the ratio of the first leaf pollution degree to the second leaf pollution degree, the difference in surface characteristics between the inverted three-leaf and inverted four-leaf due to differences in nitrogen status can be reflected. When the ratio of the first leaf's pollution level to the second leaf's pollution level is greater than 1, the pollution level of the third leaf (first leaf) is higher than that of the fourth leaf (second leaf). This indicates that the third leaf is more susceptible to dust absorption, has a rougher surface, and is nitrogen-deficient, while the fourth leaf is relatively resistant to dust absorption and has sufficient nitrogen. Nitrogen is primarily concentrated in the older leaves, with less transfer to the newer leaves. Therefore, it is necessary to reduce or eliminate ear fertilizer. When the ratio is less than 1, the pollution level of the third leaf is lower than that of the fourth leaf. This indicates that the third leaf is less susceptible to dust absorption and has a good nitrogen nutritional status. Nitrogen is transferring from the older leaves (fourth leaves) to the newer leaves (third leaf), and additional fertilizer is needed to meet growth needs. The calculated pollution level ratio is input into the second leaf pattern classifier. By integrating the results of multiple second leaf pattern classification branches, a second leaf pattern array is obtained.

[0045] Through two leaf pattern classification methods with different dimensions, the nitrogen nutritional status of double-season rice can be comprehensively evaluated from the two perspectives of SPAD value distribution and leaf surface status, providing a comprehensive and accurate basis for subsequent fertilization decisions.

[0046] Furthermore, a first leaf pattern classifier is constructed, including: S321: Based on historical cultivation data of double-cropping rice of the same family, a sample image parameter ratio set and a sample period category set are collected, and leaf patterns of double-cropping rice under each sample image parameter ratio and sample period category are collected and annotated to obtain a sample first leaf pattern set, wherein the sample image parameter ratio is the ratio of the first leaf image parameter to the second leaf image parameter of the double-cropping rice of the same family; S322: Dividing the sample image parameter ratio set, the sample period category set, and the sample first leaf pattern set to obtain a plurality of first pattern classification training data, wherein there is an intersection between every two first pattern classification training data; S323: using machine learning to construct multiple first leaf pattern classification branches; S324: Using the plurality of first pattern classification training data respectively, train, verify and test the plurality of first leaf pattern classification branches to obtain a first leaf pattern classifier.

[0047] In a preferred embodiment, first, based on the historical cultivation data of the double-season rice of the same family, a sample image parameter ratio set and the corresponding leaf pattern annotation are collected. Specifically, the first leaf image parameters and the second leaf image parameters of the same variety of double-season rice at the tip-out stage of the second leaf in the historical growing season are collected, and the ratio of the first leaf image parameters to the second leaf image parameters is calculated to form a sample image parameter ratio set. At the same time, the period category (early rice or late rice) corresponding to each sample is collected to form a sample period category set. Then, the actual leaf growth state corresponding to each sample ratio is recorded as a leaf pattern label, thereby obtaining a sample first leaf pattern set. These historical data contain the growth performance of double-season rice under different nitrogen distribution states, providing basic data support for training the first leaf pattern classifier.

[0048] Then, the sample image parameter ratio set, the sample period category set and the sample first leaf pattern set are divided to obtain multiple first pattern classification training data. By dividing the sample data into multiple subsets and ensuring that there is a certain intersection between every two subsets, the generalization ability of the model can be enhanced, overfitting can be avoided, and limited historical data can be fully utilized. Then, machine learning technology is used to construct multiple first leaf pattern classification branches. Among them, different first leaf pattern classification branches can be different types of classification algorithms, such as decision trees, support vector machines, neural networks, etc., or different parameter configurations of the same algorithm. The purpose of constructing multiple first leaf pattern classification branches is to form an integrated learning model and improve the overall classification performance by combining the prediction results of multiple basic classifiers.

[0049] Afterwards, multiple first leaf pattern classification branches were trained, validated, and tested using multiple sets of first pattern classification training data. Each classification branch was trained using different training data, and the parameters were adjusted using the validation set. Finally, the performance was evaluated on the test set. After this series of processes, a first leaf pattern classifier capable of accurately identifying different leaf patterns was finally obtained. This first leaf pattern classifier can predict the current leaf pattern of double-season rice based on the ratio of the first leaf image parameters to the second leaf image parameters, providing a scientific basis for fertilization decisions.

[0050] Similar to the construction of the first leaf pattern classifier, the second leaf pattern classifier follows the same approach. First, based on historical cultivation data for double-season rice varieties of the same family, the ratio of the first leaf contamination degree to the second leaf contamination degree is collected to form a sample contamination degree ratio set. Simultaneously, the corresponding cycle category (early rice or late rice) for each sample is collected to form a sample cycle category set. The actual leaf state for each combination of contamination degree ratio and cycle category is recorded as a leaf pattern label to obtain a sample second leaf pattern set. The sample contamination degree ratio set, sample cycle category set, and sample second leaf pattern set are then partitioned to ensure that there is intersection between the training data subsets. Next, machine learning techniques are used to construct multiple second leaf pattern classification branches, using different types of classification algorithms or different parameter configurations for the same algorithm. Each classification branch is then trained, validated, and tested using the partitioned training data. Ultimately, a second leaf pattern classifier is formed that can predict leaf patterns based on the first-to-second leaf contamination degree ratio and cycle category.

[0051] In this way, combining the results of the first leaf pattern classifier and the second leaf pattern classifier, the nitrogen nutritional status of double-season rice can be comprehensively evaluated from the two dimensions of SPAD value and leaf surface status, providing a reliable basis for decision-making on panicle fertilizer application.

[0052] Furthermore, according to the first leaf pattern array and the second leaf pattern array, a fused leaf pattern is obtained by processing to apply double-season rice ear fertilizer, including: S410: Selecting a leaf pattern with the largest number of occurrences in the first leaf pattern array and the second leaf pattern array to obtain a fused leaf pattern; S420: Applying double-season rice ear fertilizer according to the fused leaf pattern.

[0053] In a preferred embodiment, first, the blade pattern with the largest number of occurrences is selected from the first blade pattern array and the second blade pattern array to obtain a fused blade pattern. Specifically, statistics are taken on the various blade patterns in the first blade pattern array, and the blade pattern with the highest frequency is selected as the judgment result of the first dimension; similarly, statistics are taken on the various blade patterns in the second blade pattern array, and the blade pattern with the highest frequency is selected as the judgment result of the second dimension. Then, the blade patterns of these two dimensions are fused to form a final fused leaf pattern. This selection method based on the frequency of occurrence can reduce the risk of misjudgment that may be caused by a single classifier through the integrated judgment of multiple classifiers, and improve the accuracy and stability of leaf pattern classification.

[0054] Subsequently, the application strategy for panicle fertilizer for double-season rice was determined based on the obtained fused leaf pattern. Different fused leaf patterns correspond to different fertilization decisions. For example, when the fused leaf pattern shows that the leaf color of the third and fourth leaves are similar, panicle fertilizer is applied normally according to the original calculated value; when the fused leaf pattern shows that the third leaf is lighter than the fourth leaf, the application amount of panicle fertilizer is reduced; when the fused leaf pattern shows that the third leaf is lighter, no panicle fertilizer is applied; when the fused leaf pattern shows that the third leaf is darker than the fourth leaf, the application amount of panicle fertilizer is appropriately increased; and when the fused leaf pattern shows that the third leaf is darker, the application amount of panicle fertilizer is significantly increased.

[0055] Through the precise fertilization method based on leaf patterns, ear fertilizer can be adjusted according to the current actual nitrogen nutrition status of double-season rice, avoiding the fertilizer waste or shortage problems caused by blind experience-based fertilization, and improving the accuracy of double-season rice ear fertilizer application.

[0056] Example 2, as Figure 2 As shown, based on the same inventive concept as the leaf image pattern classification method for double-cropping rice panicle fertilization provided in Example 1, an embodiment of the present invention further provides a leaf image pattern classification system for double-cropping rice panicle fertilization, comprising: The leaf acquisition module 11 is used to acquire a first leaf image parameter array and a second leaf image parameter array at multiple positions of the first leaf and the second leaf during a preset time window of the target double-cropping rice; a pollution degree analysis module 12 configured to perform image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discrete degree and a second discrete degree, and calculate the first leaf pollution degree and the second leaf pollution degree by combining a preset first discrete degree and a preset second discrete degree; a pattern classification module 13 configured to perform averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and perform leaf pattern classification based on the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array; The fertilization decision module 14 is used to process and obtain leaf patterns according to the first leaf pattern array and the second leaf pattern array, and apply double-season rice ear fertilizer.

[0057] Furthermore, the leaf collection module 11 includes the following execution steps: At the stage when the second leaf of the target double-cropping rice is about to emerge, selecting multiple positions of the first leaf and the second leaf of the target double-cropping rice, wherein the first leaf is the third leaf and the second leaf is the fourth leaf; SPAD parameters are tested and collected at multiple positions of the first leaf and the second leaf respectively to obtain a first leaf image parameter array and a second leaf image parameter array.

[0058] Furthermore, the pollution level analysis module 12 includes the following execution steps: performing an image parameter discrete analysis calculation on the first leaf image parameter array to obtain a first discreteness, wherein the image parameter discrete analysis is performed by calculating a standard deviation of a plurality of leaf image parameters in the first leaf image parameter array; Perform image parameter discrete analysis calculation on the second leaf image parameter array to obtain a second discrete degree.

[0059] Furthermore, the pollution level analysis module 12 further includes the following execution steps: Obtain the first discreteness and the second discreteness of the same family of double-season rice in a preset time window within a historical period, and obtain a sample first discreteness set and a sample second discreteness set; Calculate and configure a preset first discreteness and a preset second discreteness according to the sample first discreteness set and the sample second discreteness set; The magnitudes by which the first dispersion and the second dispersion deviate from the preset first dispersion and the preset second dispersion are calculated respectively to obtain a first leaf contamination degree and a second leaf contamination degree.

[0060] Furthermore, the pattern classification module 13 includes the following execution steps: Performing averaging calculation processing on the first leaf image parameter array and the second leaf image parameter array respectively to obtain first leaf image parameters and second leaf image parameters; Constructing a first leaf pattern classifier, wherein the first leaf pattern classifier includes a plurality of first leaf pattern classification branches, an input feature of each first leaf pattern classification branch is a ratio of a first leaf image parameter to a second leaf image parameter, and an output feature is a first leaf pattern; calculating a ratio of the first leaf image parameter to the second leaf image parameter, combining the cycle category of the target double-season rice, and inputting the ratio into the first leaf pattern classifier for integrated leaf pattern classification to obtain a first leaf pattern array, wherein the cycle category includes early rice or late rice; Constructing a second leaf pattern classifier, wherein the second leaf pattern classifier includes a plurality of second leaf pattern classification branches, an input feature of each second leaf pattern classification branch is a ratio of the first leaf contamination degree to the second leaf contamination degree, an output feature is a second leaf pattern, and the number of the plurality of second leaf pattern classification branches is less than the number of the plurality of first leaf pattern classification branches; The ratio of the first leaf contamination degree to the second leaf contamination degree is calculated, and integrated leaf pattern classification is performed to obtain a second leaf pattern array.

[0061] Furthermore, the pattern classification module 13 further includes the following execution steps: Based on historical cultivation data of double-season rice of the same family, a set of sample image parameter ratios and a set of sample period categories are collected. The leaf patterns of double-season rice under each sample image parameter ratio and sample period category are collected and annotated to obtain a set of sample first leaf patterns, wherein the sample image parameter ratio is the ratio of the first leaf image parameter to the second leaf image parameter of the double-season rice of the same family. Dividing the sample image parameter ratio set, the sample period category set, and the sample first leaf pattern set to obtain a plurality of first pattern classification training data, wherein there is an intersection between every two first pattern classification training data; Using machine learning, multiple first leaf pattern classification branches are constructed; The plurality of first pattern classification training data are respectively used to train, verify and test the plurality of first leaf pattern classification branches to obtain a first leaf pattern classifier.

[0062] Furthermore, the fertilization decision module 14 includes the following execution steps: In the first blade pattern array and the second blade pattern array, selecting the blade pattern with the largest number of occurrences to obtain a fused blade pattern; According to the fused leaf pattern, double-season rice panicle fertilizer is applied.

[0063] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0064] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0068] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0069] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A leaf image pattern classification method for double-season rice ear fertilization, characterized in that: The method comprises: In a preset time window of the target double-cropping rice, collecting and obtaining a first leaf image parameter array and a second leaf image parameter array at multiple positions of the first leaf and the second leaf; Performing image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discreteness and a second discreteness, and calculating a first leaf contamination degree and a second leaf contamination degree by combining a preset first discreteness and a preset second discreteness; performing averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and performing leaf pattern classification according to the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array; According to the first leaf pattern array and the second leaf pattern array, leaf patterns are obtained by processing and double-season rice ear fertilizer is applied.

2. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: In a preset time window of the target double-cropping rice, the first leaf image parameter array and the second leaf image parameter array are acquired at multiple positions of the first leaf and the second leaf, including: At the stage when the second leaf of the target double-cropping rice is about to emerge, selecting multiple positions of the first leaf and the second leaf of the target double-cropping rice, wherein the first leaf is the third leaf and the second leaf is the fourth leaf; SPAD parameters are tested and collected at multiple positions of the first leaf and the second leaf respectively to obtain a first leaf image parameter array and a second leaf image parameter array.

3. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: Performing image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discreteness and a second discreteness includes: performing an image parameter discrete analysis calculation on the first leaf image parameter array to obtain a first discreteness, wherein the image parameter discrete analysis is performed by calculating a standard deviation of a plurality of leaf image parameters in the first leaf image parameter array; Perform image parameter discrete analysis calculation on the second leaf image parameter array to obtain a second discrete degree.

4. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: Calculating the first leaf contamination degree and the second leaf contamination degree by combining the preset first discreteness and the preset second discreteness includes: Obtain the first discreteness and the second discreteness of the same family of double-season rice in a preset time window within a historical period, and obtain a sample first discreteness set and a sample second discreteness set; Calculate and configure a preset first discreteness and a preset second discreteness according to the sample first discreteness set and the sample second discreteness set; The magnitudes by which the first dispersion and the second dispersion deviate from the preset first dispersion and the preset second dispersion are calculated respectively to obtain a first leaf contamination degree and a second leaf contamination degree.

5. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: The method further comprises: performing averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array; and performing leaf pattern classification according to the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array, comprising: Performing averaging calculation processing on the first leaf image parameter array and the second leaf image parameter array respectively to obtain first leaf image parameters and second leaf image parameters; Constructing a first leaf pattern classifier, wherein the first leaf pattern classifier includes a plurality of first leaf pattern classification branches, an input feature of each first leaf pattern classification branch is a ratio of a first leaf image parameter to a second leaf image parameter, and an output feature is a first leaf pattern; calculating a ratio of the first leaf image parameter to the second leaf image parameter, combining the cycle category of the target double-season rice, and inputting the ratio into the first leaf pattern classifier for integrated leaf pattern classification to obtain a first leaf pattern array, wherein the cycle category includes early rice or late rice; Constructing a second leaf pattern classifier, wherein the second leaf pattern classifier includes a plurality of second leaf pattern classification branches, an input feature of each second leaf pattern classification branch is a ratio of the first leaf contamination degree to the second leaf contamination degree, an output feature is a second leaf pattern, and the number of the plurality of second leaf pattern classification branches is less than the number of the plurality of first leaf pattern classification branches; The ratio of the first leaf contamination degree to the second leaf contamination degree is calculated, and integrated leaf pattern classification is performed to obtain a second leaf pattern array.

6. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: Construct the first leaf pattern classifier, including: Based on historical cultivation data of double-season rice of the same family, a set of sample image parameter ratios and a set of sample period categories are collected. The leaf patterns of double-season rice under each sample image parameter ratio and sample period category are collected and annotated to obtain a set of sample first leaf patterns, wherein the sample image parameter ratio is the ratio of the first leaf image parameter to the second leaf image parameter of the double-season rice of the same family. Dividing the sample image parameter ratio set, the sample period category set, and the sample first leaf pattern set to obtain a plurality of first pattern classification training data, wherein there is an intersection between every two first pattern classification training data; Using machine learning, multiple first leaf pattern classification branches are constructed; The plurality of first pattern classification training data are respectively used to train, verify and test the plurality of first leaf pattern classification branches to obtain a first leaf pattern classifier.

7. The leaf image pattern classification method for double-season rice panicle fertilization according to claim 1, characterized in that: Processing the first leaf pattern array and the second leaf pattern array to obtain a fused leaf pattern and applying double-season rice ear fertilizer includes: In the first blade pattern array and the second blade pattern array, selecting the blade pattern with the largest number of occurrences to obtain a fused blade pattern; According to the fused leaf pattern, double-season rice panicle fertilizer is applied.

8. A leaf image pattern classification system for double-season rice ear fertilization, characterized in that: A system for implementing the leaf image pattern classification method for double-season rice panicle fertilization according to any one of claims 1 to 7, comprising: A leaf acquisition module is used to acquire a first leaf image parameter array and a second leaf image parameter array at multiple positions of the first leaf and the second leaf during a preset time window of the target double-cropping rice; a pollution degree analysis module, configured to perform image parameter discrete analysis on the first leaf image parameter array and the second leaf image parameter array to obtain a first discrete degree and a second discrete degree, and calculate the first leaf pollution degree and the second leaf pollution degree by combining a preset first discrete degree and a preset second discrete degree; a leaf pattern classification module, configured to perform averaging processing and leaf pattern classification on the first leaf image parameter array and the second leaf image parameter array to obtain a first leaf pattern array, and perform leaf pattern classification based on the first leaf contamination degree and the second leaf contamination degree to obtain a second leaf pattern array; The fertilization decision module is used to process and obtain leaf patterns according to the first leaf pattern array and the second leaf pattern array, and apply double-season rice ear fertilizer.

Images