Areca nut screening method based on image recognition

Abstract

The invention relates to the technical field of fruit screening, in particular to an areca nut screening method based on image recognition, and the method comprises the steps: determining a screening strategy according to a defect index; based on a comparison result that the defect index is smaller than a preset defect index, judging a defect type through image recognition, and determining an execution scheme according to the defect type, including direct elimination, or judging whether the areca nut appearance meets a preset standard according to a skin color variation coefficient; when it is judged that the areca nut appearance does not meet the preset standard, whether the areca nut appearance meets the preset standard or not is judged secondarily according to the chromaticity difference value; under the condition that the appearance of the areca nuts meets the preset standard, whether the hardness of the areca nuts meets the preset standard or not is judged according to the hardness value; judging whether the water content of the areca nuts meets a preset standard or not according to the density value; the areca nuts with the water content meeting the preset standard are classified according to the weight, and screening is completed. The areca nut screening device improves the areca nut screening efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of fruit screening, and particularly to a screening method for betel nuts based on image recognition. Background Art

[0002] Due to the coarse and hard fibers of traditional betel nut products, long-term chewing may have adverse effects on oral health, such as oral submucous fibrosis, tooth wear, etc. With the improvement of health awareness, consumers' demand for betel nut products has gradually shifted to products that are healthier, softer, and have a better taste.

[0003] Chinese Patent Application Publication No.: CN113976475A, discloses a system and method for preferentially screening fruits and vegetables, belonging to the technical field of image processing. Specifically, it includes: a transmission component includes a feeding end and a sorting end, and a shooting area is provided at the middle position of the transmission component; the shooting end of the imaging device faces the shooting area; a robotic arm is arranged at the sorting end; a plurality of soft suction cups are all connected to a walker, the walker is connected to one side of a fixing plate, and the other side of the fixing plate is connected to the clamping end of the robotic arm; the imaging device, the robotic arm, and the soft adsorption claw are all electrically connected to a controller.

[0004] However, the following problems exist in the prior art: The prior art only detects the outer surface of the fruit and does not consider the impact of possible problems inside the fruit on the quality. Summary of the Invention

[0005] Therefore, the present invention provides a screening method for betel nuts based on image recognition to overcome the problem in the prior art that the detection of fruits is limited to whether there are defects on the fruit surface.

[0006] To achieve the above object, the present invention provides a screening method for betel nuts based on image recognition, including: Rotating and conveying the betel nuts through an optical sorting device to complete multi-angle shooting, and determining a screening strategy based on the defect index of the betel nut surface obtained from the collected images; Based on the comparison result that the defect index is less than a preset defect index, determining the defect type through image recognition and determining an execution plan according to the defect type, including directly rejecting, or determining whether the appearance of the betel nut meets the preset standard according to the epidermal color variation coefficient; When it is determined that the appearance of the betel nut does not meet the preset standard, secondarily determining whether the appearance of the betel nut meets the preset standard according to the chromaticity difference; Under the condition that the appearance of the betel nut meets the preset standard, measuring the hardness of the fruit using a hardness tester and determining whether the hardness of the betel nut meets the preset standard according to the hardness value; Weighing the betel nuts that meet the hardness standard, measuring the volume to calculate the density, and determining whether the water content of the betel nuts meets the preset standard according to the density value; Classify betel nuts with water content meeting the preset standard by weight and complete the screening.

[0007] Further, determine the screening strategy according to the defect index of a single betel nut. Among them, if the defect index is less than the preset defect index, determine the implementation plan according to the defect type; If the defect index is greater than or equal to the preset defect index, lock the betel nut and directly reject it.

[0008] Further, determine the implementation plan according to the defect type. Among them, if the defect is rot or mold, directly reject the betel nut with the defect; If the defect is a slight scratch or depression on the surface, determine whether the appearance of the betel nut meets the preset standard according to the epidermal color variation coefficient.

[0009] Further, under the condition that the epidermal color variation coefficient is less than the first preset variation coefficient, determine that the appearance of the betel nut meets the preset standard, and determine whether the hardness of the betel nut meets the preset standard according to the hardness value.

[0010] Further, under the condition that the epidermal color variation coefficient is greater than or equal to the first preset variation coefficient, determine that the appearance of the betel nut does not meet the preset standard. And, if the epidermal color variation coefficient is greater than or equal to the first preset variation coefficient and less than the second preset variation coefficient, re-determine whether the appearance of the betel nut meets the preset standard according to the chromaticity difference; If the epidermal color variation coefficient is greater than or equal to the second preset variation coefficient, reject the betel nut.

[0011] Further, under the condition that the chromaticity difference is less than the preset chromaticity difference, re-determine that the appearance of the betel nut meets the preset standard and conduct a hardness test.

[0012] Further, under the condition that the chromaticity difference is greater than or equal to the preset chromaticity difference, screen out and store the betel nut. When the chromaticity difference of the stored betel nut is less than the preset chromaticity difference, continue to send it to the subsequent hardness test link.

[0013] Further, under the condition that the hardness value is less than the preset hardness value, determine that the hardness of the betel nut does not meet the preset standard and cut it open for internal quality inspection.

[0014] Further, under the condition that the hardness value is greater than or equal to the preset hardness value, determine that the hardness of the betel nut meets the preset standard, and determine whether the water content of the betel nut meets the preset standard according to the density value.

[0015] Further, under the condition that the density value is greater than or equal to the preset density value, it is determined that the water content of the betel nut meets the preset standard, and the betel nuts with water content meeting the preset standard are classified by weight and then the screening is completed.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows. The present invention comprehensively screens betel nuts through multi-dimensional detection, including appearance detection, hardness detection and density detection. Through the multi-dimensional and multi-level screening method, the overall control of the quality of betel nuts is realized, the screening efficiency and product quality are significantly improved, and at the same time, resource waste is reduced.

[0017] Further, the present invention formulates different implementation plans according to the defect index and defect type, avoiding a one-size-fits-all screening method. In the case of determining non-compliance with the standard, a secondary determination is made through the chromaticity difference, reducing the misjudgment rate.

[0018] Further, the present invention stores and reinspects the betel nuts with excessive chromaticity difference to avoid resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flowchart of the betel nut screening method according to an embodiment of the present invention; Figure 2 is a flowchart of determining an implementation plan according to a defect type in an embodiment of the present invention; Figure 3 is a flowchart of determining whether the appearance of a betel nut meets a preset standard in an embodiment of the present invention; Figure 4 is a flowchart of secondary determination of whether the appearance of a betel nut meets a preset standard in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to make the purpose and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0022] It should be noted that the data in this embodiment are all obtained through comprehensive analysis and evaluation of the historical detection data and corresponding historical detection results of the present invention in the three months before this detection. Those skilled in the art can understand that the determination method of the above single parameter of the present invention can be to select the value with the highest proportion according to the data distribution as the preset standard parameter, use weighted summation to take the obtained value as the preset standard parameter, substitute each historical data into a specific formula and take the value obtained by using this formula as the preset standard parameter, or other selection methods, as long as it meets the requirement that the present invention can clearly define different specific situations in the single-item determination process through the obtained values.

[0023] Please refer to Figures 1 to 4 as shown, which are respectively the flowcharts of the betel nut screening method in the embodiment of the present invention; the flowchart of determining the execution plan according to the defect type; the flowchart of determining whether the appearance of the betel nut meets the preset standard; the flowchart of secondary determination of whether the appearance of the betel nut meets the preset standard in the embodiment of the present invention.

[0024] The betel nut screening method based on image recognition in the embodiment of the present invention includes: Step S1, rotating and conveying the betel nuts through an optical sorting device, taking multi-angle photos, and determining the screening strategy based on the defect index of the betel nut surface obtained from the collected images; Step S2, based on the comparison result that the defect index is less than the preset defect index, determining the defect type through image recognition and determining the execution plan according to the defect type, including directly rejecting, or determining whether the appearance of the betel nut meets the preset standard according to the epidermal color variation coefficient; Step S3, when it is determined that the appearance of the betel nut does not meet the preset standard, secondarily determining whether the appearance of the betel nut meets the preset standard according to the chromaticity difference; Step S4, under the condition that the appearance of the betel nut meets the preset standard, measuring the fruit hardness with a hardness tester and determining whether the hardness of the betel nut meets the preset standard according to the hardness value; Step S5, weighing the betel nuts with qualified hardness, measuring the volume to calculate the density, and determining whether the water content of the betel nut meets the preset standard according to the density value; Step S6, classifying the betel nuts with qualified water content according to weight and completing the screening.

[0025] Specifically, the optical sorting device is, for example, a drum type fruit sorter, a conveyor belt type fruit sorter, an air flow type fruit sorter, etc., and is not specifically limited, as long as the device has the capabilities of rolling conveyance, image recognition and screening.

[0026] Specifically, the optical sorting device captures images of the areca nut surface through an industrial-grade digital camera and obtains the defect index, the coefficient of variation of the skin color, and the chromaticity difference through visual algorithm analysis.

[0027] Specifically, in the step S1, an image is captured every time the areca nut rotates by a preset angle of 30°. The defect index on the surface of the areca nut is the ratio of the area of the defect to the surface area of the areca nut.

[0028] In the embodiment of the present invention, the preset angle is 30°, but the above value is not limited thereto, and those skilled in the art can adjust this value according to actual needs.

[0029] Specifically, in the step S5, an electronic scale is provided at the end of the conveying module of the optical sorting device to weigh the areca nuts and upload the weight data to the control system. At the same time, a 3D camera or a multi-angle camera is used to capture the areca nuts, and a three-dimensional model is reconstructed through point cloud data and the volume is calculated.

[0030] Specifically, a screening strategy is determined according to the defect index of a single areca nut. Among them, if the defect index is less than the preset defect index of 5%, the execution plan is determined according to the defect type; If the defect index is greater than or equal to the preset defect index, the areca nut is locked and directly removed.

[0031] In the embodiment of the present invention, the preset defect index is 5%, but the above value is not limited thereto, and those skilled in the art can adjust this value according to actual needs.

[0032] Specifically, the execution plan is determined according to the defect type, where If the defect is rot or mold, the areca nuts with defects are directly removed; If the defect is a slight scratch or depression on the surface, it is determined whether the appearance of the areca nut meets the preset standard according to the coefficient of variation of the skin color.

[0033] Specifically, the coefficient of variation of the skin color is the ratio of the area of the abnormally colored area of the skin to the surface area of the areca nut.

[0034] Specifically, under the condition that the coefficient of variation of the skin color is less than the first preset coefficient of variation of 8%, it is determined that the appearance of the areca nut meets the preset standard, and it is determined whether the hardness of the areca nut meets the preset standard according to the hardness value.

[0035] Specifically, under the condition that the coefficient of variation of the skin color is greater than or equal to the first preset coefficient of variation, it is determined that the appearance of the betel nut does not meet the preset standard. And, if the coefficient of variation of the skin color is greater than or equal to the first preset coefficient of variation and less than 15% of the second preset coefficient of variation, then the appearance of the betel nut is secondarily determined whether it meets the preset standard according to the chromaticity difference; If the coefficient of variation of the skin color is greater than or equal to the second preset coefficient of variation, the betel nut is removed.

[0036] In the embodiment of the present invention, the value of the first preset coefficient of variation is 8%, and the value of the second preset coefficient of variation is 15%. However, the above values are not limited to this, and those skilled in the art can adjust this value according to actual needs.

[0037] Specifically, under the condition that the chromaticity difference is less than the preset chromaticity difference of 3.5, it is secondarily determined that the appearance of the betel nut meets the preset standard, and the hardness detection is carried out.

[0038] Specifically, under the condition that the chromaticity difference is greater than or equal to the preset chromaticity difference, the betel nut is screened out and stored. When the chromaticity difference of the stored betel nut is less than the preset chromaticity difference, it is continuously sent to the subsequent hardness detection link.

[0039] In the embodiment of the present invention, the value of the preset chromaticity difference is 3.5. However, the above value is not limited to this, and those skilled in the art can adjust this value according to actual needs.

[0040] Specifically, under the condition that the hardness value is less than the preset hardness value of 2 kgf / cm², it is determined that the hardness of the betel nut does not meet the preset standard, and it is cut open for internal quality detection.

[0041] In the embodiment of the present invention, the value of the preset hardness value is 2 kgf / cm². However, the above value is not limited to this, and those skilled in the art can adjust this value according to actual needs.

[0042] Specifically, under the condition that the hardness value is greater than or equal to the preset hardness value, it is determined that the hardness of the betel nut meets the preset standard, and whether the water content of the betel nut meets the preset standard is determined according to the density value.

[0043] Specifically, under the condition that the density value is greater than or equal to the preset density value of 0.9 g / cm³, it is determined that the water content of the betel nut meets the preset standard, and the betel nuts with water content meeting the preset standard are classified by weight and then the screening is completed.

[0044] In the embodiment of the present invention, the value of the preset density value is 0.9 g / cm³. However, the above value is not limited to this, and those skilled in the art can adjust this value according to actual needs.

[0045] Specifically, areca nuts are classified by weight. Among them, if the weight of the areca nut is greater than or equal to 10 g, it is determined as a large fruit; if the weight of the areca nut is greater than or equal to 5 g and less than 10 g, it is determined as a medium fruit; if the weight of the areca nut is less than 5 g, it is determined as a small fruit.

[0046] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0047] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A betel nut screening method based on image recognition, characterized in that: include: The betel nut is rotated and conveyed through an optical sorting device, and multi-angle photography is completed. The defect index of the betel nut surface is obtained based on the collected images to determine the screening strategy; Based on the comparison result that the defect index is less than the preset defect index, the defect type is determined through image recognition and the implementation plan is determined according to the defect type, including direct elimination, or, judging whether the appearance of the betel nut meets the preset standard according to the coefficient of variation of the skin color; When it is determined that the appearance of the betel nut does not meet the preset standard, a second determination is made based on the color difference whether the appearance of the betel nut meets the preset standard; Under the condition that the appearance of the betel nut meets the preset standard, a hardness tester is used to measure the hardness of the betel nut, and whether the hardness of the betel nut meets the preset standard is determined according to the hardness value; Weigh the betel nut fruits that meet the hardness standards, measure the volume and calculate the density, and determine whether the water content of the betel nut fruits meets the preset standards based on the density value; Betel nuts whose moisture content meets the preset standard are classified by weight and screened.

2. The betel nut screening method based on image recognition according to claim 1, characterized in that: The screening strategy is determined based on the defect index of a single betel nut, where: If the defect index is less than the preset defect index, an execution plan is determined according to the defect type; If the defect index is greater than or equal to the preset defect index, the betel nut is locked and directly removed.

3. The betel nut screening method based on image recognition according to claim 2, characterized in that: Determine the execution plan based on the defect type, where: If the defect is rotten or moldy, the betel nut with defects will be directly discarded; If the defect is a slight scratch or dent on the surface, the coefficient of variation of the skin color will be used to determine whether the appearance of the betel nut meets the preset standards.

4. The betel nut screening method based on image recognition according to claim 3, characterized in that: Under the condition that the skin color variation coefficient is less than the first preset variation coefficient, it is determined that the appearance of the betel nut meets the preset standard, and whether the hardness of the betel nut meets the preset standard is determined based on the hardness value.

5. The betel nut screening method based on image recognition according to claim 4, characterized in that: Under the condition that the skin color variation coefficient is greater than or equal to the first preset variation coefficient, determining that the appearance of the betel nut does not meet the preset standard, and, If the skin color variation coefficient is greater than or equal to the first preset variation coefficient and less than the second preset variation coefficient, a secondary determination is made as to whether the appearance of the betel nut meets the preset standard based on the chromaticity difference; If the skin color variation coefficient is greater than or equal to the second preset variation coefficient, the betel nut will be discarded.

6. The betel nut screening method based on image recognition according to claim 5, characterized in that: Under the condition that the chromaticity difference is less than the preset chromaticity difference, it is determined for the second time that the appearance of the betel nut meets the preset standard, and a hardness test is performed.

7. The betel nut screening method based on image recognition according to claim 6, characterized in that: Under the condition that the chromaticity difference is greater than or equal to the preset chromaticity difference, the betel nut fruits are screened out and stored. When the chromaticity difference of the stored betel nut fruits is less than the preset chromaticity difference, they are sent to the subsequent hardness detection link.

8. The betel nut screening method based on image recognition according to claim 6, characterized in that: Under the condition that the hardness value is less than the preset hardness value, it is determined that the hardness of the betel nut does not meet the preset standard, and the betel nut is cut open for internal quality inspection.

9. The betel nut screening method based on image recognition according to claim 8, characterized in that: Under the condition that the hardness value is greater than or equal to the preset hardness value, it is determined that the hardness of the betel nut meets the preset standard, and whether the water content of the betel nut meets the preset standard is determined based on the density value.

10. The betel nut screening method based on image recognition according to claim 9, characterized in that: Under the condition that the density value is greater than or equal to the preset density value, it is determined that the moisture content of the betel nut meets the preset standard, and the betel nut whose moisture content meets the preset standard is classified according to weight to complete the screening.

Images