A visual image quality inspection method and system

Abstract

The present invention provides a method and system for visual image quality inspection, the method comprising: establishing a pure noise data benchmark based on a carrier material; receiving original image data, synthesizing the original image data and the pure noise data benchmark into standard comparison data; using visual acquisition of the image data to be tested, comparing the image data to be tested and the standard comparison data, and obtaining a product inspection judgment result. First, a pure noise data benchmark of the carrier material is established, which includes optical noise in the visual acquisition process, and the original image data contains correct information, with neither environmental noise nor product defects. The original image data and the pure noise data benchmark are synthesized into standard comparison data, which contains the correct information of the original image data and unavoidable optical noise. The standard comparison data is compared with the image data to be tested, and the product defects in the image data to be tested can be clearly identified to avoid misjudgment. The method for establishing the standard comparison data is simple, saves labor costs, has high processing efficiency, and has a low misjudgment rate.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing technology, and in particular relates to a visual acquisition image quality inspection method and system. Background Art

[0002] In the production process of printed products, visual inspection is an important link to determine the quality completion. The current visual inspection method for printed products is: firstly, the finished printed products are collected by machine vision to obtain a small batch of image data, and then a good product is manually selected from this batch of image data as a standard part image, and this standard part image is entered into the processing system as a comparison standard for subsequent inspections.

[0003] This method is suitable for mass production. One standard part image can meet the quality inspection of mass printed products. Compared with mass production, the manual screening in determining the standard part image is acceptable, even though the efficiency is very low in the process of determining the standard part image. However, with the increasing demand for small batches and customization of printed products, the above quality inspection methods with high manual input costs and low efficiency are out of tune. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and to provide a visual image acquisition inspection method and system, which are mainly used to solve the problems of low efficiency, high labor cost, and non-compliance with small batch customized production in the prior art of printed product inspection process.

[0005] In order to achieve the above-mentioned object, in a first aspect, the present invention provides a visual image acquisition inspection method, comprising the following steps:

[0006] Establish a pure noise data baseline based on carrier materials;

[0007] Receiving original image data, and synthesizing the original image data and the pure noise data benchmark into standard comparison data;

[0008] The image data to be tested is collected by vision, and the image data to be tested is compared with the standard comparison data to obtain the product inspection judgment result.

[0009] Furthermore, before establishing a pure noise data benchmark based on a carrier material, environmental factors are first determined, and the environmental factors include but are not limited to visual focus information and visual auxiliary light information.

[0010] Furthermore, when establishing a pure noise data benchmark based on carrier materials, M carrier material noise images are collected under certain environmental factors, and an N1×N2 unit element dot matrix image is established for each carrier material noise image. Matrix analysis algorithm calculations are performed on the same divided areas of the M carrier material noise images, and a pure noise data benchmark for the carrier material is established based on the calculation results of the matrix analysis algorithm.

[0011] Furthermore, the same divided area is a unit cell area of ​​size A×A, where A≥1.

[0012] Furthermore, pure noise data benchmarks are established for different types of carrier materials, and a carrier material data benchmark database is established.

[0013] Furthermore, when receiving the original image data and synthesizing the original image data with the pure noise data benchmark into standard comparison data, the following steps are included:

[0014] Receive a quality inspection task data packet, the quality inspection task data packet includes at least original image data and carrier material information, the original image data is the original design image data, according to the carrier material information, retrieve the corresponding pure noise data benchmark in the carrier material data benchmark database, synthesize the original image data with the retrieved pure noise data benchmark, and obtain standard comparison data.

[0015] Furthermore, when comparing the image data to be tested with the standard comparison data, the following steps are included:

[0016] An N1×N2 unit element dot matrix is ​​established for the image data to be tested and the standard comparison data respectively, matrix values ​​are calculated for the same divided areas of the two unit element dot matrixes respectively, and matrix values ​​belonging to the same divided area are compared.

[0017] Furthermore, when performing matrix value calculation, the unit element dot matrix of the image data to be tested and the standard comparison data is divided into unit element regions of A×A, and matrix value calculation is performed on each unit element region.

[0018] Furthermore, when using vision to collect the image data to be tested, the product to be tested is firstly collected by machine vision, and the collected image is cropped to obtain the image data to be tested.

[0019] In a second aspect, the present invention further provides a visual image quality inspection system for the above-mentioned image acquisition, comprising:

[0020] Data benchmark database, including several pure noise data benchmarks based on carrier materials;

[0021] A preprocessing unit, configured to receive original image data, and synthesize the original image data and the pure noise data benchmark into standard comparison data;

[0022] An acquisition unit, used for visually acquiring image data to be tested;

[0023] The comparison unit is used to compare the image data to be tested with the standard comparison data to obtain a product inspection result.

[0024] Compared with the prior art, the beneficial effects of the present invention include at least:

[0025] First, a pure noise data benchmark is established for the carrier material. This pure noise data benchmark includes optical noise in the visual acquisition process, while the original image data contains correct information, with neither environmental noise nor product defects. Therefore, after the original image data and the pure noise data benchmark are synthesized into standard comparison data, the standard comparison data contains the correct information of the original image data and the unavoidable optical noise. After comparing the standard comparison data with the image data to be tested, the product defects in the image data to be tested can be clearly identified to avoid misjudgment. The establishment of standard comparison data only requires the synthesis of the original image data with the pure noise data benchmark system, which saves labor costs, has high processing efficiency, low misjudgment rate, and good inspection quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0027] Figure 1 It is a flow chart of a visual image acquisition quality inspection method provided by the present invention.

[0028] Figure 2 It is a schematic diagram of the process of establishing the carrier material data reference database in the present invention.

[0029] Figure 3 It is a specific flow chart of comparing the image data to be tested with the standard comparison data in the present invention.

[0030] Figure 4 It is a schematic diagram of a visual image acquisition quality inspection system provided by the present invention. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be described clearly and completely below 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0033] Reference Figures 1 to 3 In a first aspect, the present invention provides a method for visual image acquisition inspection, comprising the following steps:

[0034] Establish a pure noise data benchmark based on carrier materials, which includes optical noise in the visual acquisition process;

[0035] Receiving original image data, the original image data contains correct information, and has neither environmental noise nor product defects, and synthesizing the original image data with the pure noise data benchmark into standard comparison data, so that the standard comparison data contains the correct information of the original image data and unavoidable optical noise;

[0036] The image data to be tested is collected visually and compared with the standard comparison data. Since the same carrier material is used, the optical noise generated by the carrier material in the visual collection process is already included in the standard comparison data. The part of the image data to be tested regarding the optical noise will not cause misjudgment in the comparison process. Only when the image data to be tested includes product defects will they be exposed in the comparison process with the standard comparison data, thereby achieving the distinction between the optical noise and product defects on the product to be tested, and obtaining the inspection judgment result after the comparison.

[0037] The above method can clearly identify product defects in the image data to be tested and avoid misjudgment. The establishment of standard comparison data only requires the synthesis of the original image data with the pure noise data benchmark system, which saves labor costs, has high processing efficiency, low misjudgment rate, and good inspection quality.

[0038] Combination Figure 2In this embodiment, before establishing a pure noise data baseline based on the carrier material, the environmental factors are first determined. The environmental factors include but are not limited to visual focus information and visual auxiliary light information. Since visual acquisition will be affected by the surrounding lighting environment, camera focus settings, etc., the environmental factors will be different for different carrier materials. After determining a certain carrier material, the environmental factors related to it must be determined accordingly, and the same environmental factors must be maintained when subsequently acquiring the image data to be tested.

[0039] Combination Figure 2 As an implementation method, when establishing a pure noise data benchmark based on a carrier material, under certain environmental factors, M carrier material noise images are collected, and an N1×N2 unit element dot matrix image is established for each carrier material noise image, wherein the values ​​of N1 and N2 may be the same or different; a matrix analysis algorithm is performed on the same divided areas of the M carrier material noise images, and a pure noise data benchmark for the carrier material is established based on the calculation results of the matrix analysis algorithm.

[0040] It should be noted that for each carrier material noise map, a unit element dot matrix of size N1×N2 is first established. Depending on the size of the carrier material, it can be a rectangle or a square. In this unit element dot matrix, the area is divided according to a certain rule. The rule for dividing the area can be divided according to the unit element area of ​​A×B, where the values ​​of A and B can be the same or different; it can also be divided according to artificially set areas; for example, in a 10×20 unit element dot matrix, it is divided into 2×4 in size, and each divided area does not overlap, and a total of 25 divided areas can be divided; under the same division rule, each carrier material noise map can be divided into the same divided area, and the matrix analysis algorithm is used to calculate the same divided area of ​​different carrier material noise maps to obtain the mean of this divided area. Based on the calculation results of the matrix analysis algorithm, a pure noise data benchmark for the carrier material is established, with high calculation accuracy, and the coverage range of the calculation results for the noise is real and accurate.

[0041] In other embodiments, the same divided area is a unit cell area of ​​size A×A, where A≥1, that is, the unit cell area is a square. Of course, it can be divided into 1×1 sizes, that is, each unit cell is the smallest divided area, which has the highest accuracy.

[0042] In contrast, after knowing the approximate layout of the product to be tested, the area where the label has more concentrated actual content can be divided and laid out with emphasis, with a relatively fine grid area, while the corner area has a relatively large grid area, so it can be divided according to the artificially set area.

[0043] In some embodiments, in order to adapt to the scenarios of various carrier materials, pure noise data benchmarks are established for different types of carrier materials, and a carrier material data benchmark database is established. The pure noise data benchmarks corresponding to various carrier materials are organized into a database, which can be retrieved when a specific carrier material is needed.

[0044] Combination Figure 3 More specifically, when receiving the original image data and synthesizing the original image data with the pure noise data benchmark into standard comparison data, the following steps are included:

[0045] Receive a quality inspection task data packet, the quality inspection task data packet at least includes original image data and carrier material information, the original image data is the original design image data, retrieve the corresponding pure noise data benchmark in the carrier material data benchmark database according to the carrier material information, perform data synthesis on the original image data and the retrieved pure noise data benchmark to obtain standard comparison data; utilize data-driven to automatically retrieve a suitable pure noise data benchmark, and then combine it with the original design image data to quickly obtain standard comparison data.

[0046] In this embodiment, when comparing the image data to be tested with the standard comparison data, the following steps are included:

[0047] Establish N1×N2 unit element dot matrix diagrams for the image data to be tested and the standard comparison data respectively, perform matrix value calculations for the same divided areas of the two unit element dot matrix diagrams respectively, and compare the matrix values ​​belonging to the same divided area. Similarly, divide the image data to be tested and the standard comparison data into areas according to the same rule. Each divided area may have different situations in the corresponding two data. The inspection result can be judged according to the matrix value calculation result.

[0048] As an implementation mode, when performing matrix value calculation, the unit element dot matrix of the image data to be tested and the standard comparison data is divided into unit element areas of A×A, that is, the square unit element area is used as the comparison object, and the matrix value calculation is performed on each unit element area.

[0049] In this embodiment, when using vision to collect the image data to be tested, machine vision is first performed on the product to be tested, and the collected image is cropped to a suitable size to obtain the image data to be tested, which is then compared with the standard comparison data, which can improve data processing efficiency and comparison efficiency.

[0050] Combination Figure 4 In a second aspect, the present invention further provides a visual image quality inspection system for the above-mentioned image acquisition, comprising:

[0051] A data benchmark database, including a plurality of pure noise data benchmarks based on carrier materials, and correspondingly, a pure noise data establishment unit is also provided to establish corresponding pure noise data benchmarks for different carrier materials;

[0052] A preprocessing unit, configured to receive original image data, and synthesize the original image data and the pure noise data benchmark into standard comparison data;

[0053] An acquisition unit, used for visually acquiring image data to be tested;

[0054] The comparison unit is used to compare the image data to be tested with the standard comparison data to obtain a product inspection result.

[0055] Compared with the prior art, the present invention provides a visual acquisition image inspection method and system, which first establishes a pure noise data benchmark for the carrier material. The pure noise data benchmark includes optical noise in the visual acquisition process, while the original image data contains correct information, with neither environmental noise nor product defects. Therefore, after the original image data and the pure noise data benchmark are synthesized into standard comparison data, the standard comparison data contains the correct information of the original image data and the unavoidable optical noise. After comparing the standard comparison data with the image data to be tested, the product defects in the image data to be tested can be clearly identified to avoid misjudgment. The establishment of the standard comparison data only requires the synthesis of the original image data with the pure noise data benchmark system, which saves labor costs, has high processing efficiency, low misjudgment rate, and good inspection quality.

[0056] Finally, it should be emphasized that the present invention is not limited to the above-mentioned implementation mode. The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0057] The above description is the main process steps of the invention, which may be interspersed with other functional steps and may disrupt the above logical order and process steps. If the data is processed in the form of this process step or the core idea of ​​data processing is similar or identical, it should be protected.

Claims

1. A visual image quality inspection method, applied to the field of printed product quality inspection, characterized in that: The following steps are involved: Establishing a pure noise data benchmark based on a carrier material, wherein the pure noise data benchmark includes optical noise in a visual acquisition process; wherein, before establishing the pure noise data benchmark based on a carrier material, first determining environmental factors, wherein the environmental factors include but are not limited to visual focus information and visual auxiliary light information; establishing pure noise data benchmarks for different types of carrier materials respectively, and establishing a carrier material data benchmark database; Receiving original image data, and synthesizing the original image data and the pure noise data benchmark into standard comparison data, wherein the standard comparison data contains correct information of the original image data and unavoidable optical noise; Collect the image data to be tested by vision, compare the image data to be tested with the standard comparison data, and obtain the inspection result; Wherein, when receiving the original image data and synthesizing the original image data and the pure noise data benchmark into standard comparison data, the following steps are included: receiving a quality inspection task data packet, the quality inspection task data packet at least including original image data and carrier material information, the original image data being original design image data, retrieving corresponding pure noise data benchmarks from a carrier material data benchmark database according to the carrier material information, synthesizing the original image data with the retrieved pure noise data benchmark to obtain standard comparison data; When establishing a pure noise data benchmark based on carrier materials, under certain environmental factors, M carrier material noise images are collected, an N1×N2 unit element dot matrix image is established for each carrier material noise image, matrix analysis algorithm calculations are performed on the same divided areas of the M carrier material noise images, and a pure noise data benchmark for the carrier material is established based on the calculation results of the matrix analysis algorithm.

2. A visual image quality inspection method according to claim 1, characterized in that: The same divided area is a unit cell area of ​​size A×A, where A≥1.

3. A visual image quality inspection method according to claim 2, characterized in that: When comparing the image data to be tested with the standard comparison data, the following steps are included: An N1×N2 unit element dot matrix is ​​established for the image data to be tested and the standard comparison data respectively, matrix values ​​are calculated for the same divided areas of the two unit element dot matrixes respectively, and matrix values ​​belonging to the same divided area are compared.

4. A visual image quality inspection method according to claim 3, characterized in that: When performing matrix value calculation, the unit element dot matrix of the image data to be tested and the standard comparison data is divided into unit element regions of A×A, and matrix value calculation is performed on each unit element region.

5. A visual image quality inspection method according to claim 4, characterized in that: When using vision to collect the image data to be tested, the product to be tested is firstly collected by machine vision, and the collected image is cropped to obtain the image data to be tested.

6. A visual image acquisition inspection system according to any one of claims 1 to 5, characterized in that: include: Data benchmark database, including several pure noise data benchmarks based on carrier materials; A preprocessing unit, configured to receive original image data, and synthesize the original image data and the pure noise data benchmark into standard comparison data; An acquisition unit, used for visually acquiring image data to be tested; The comparison unit is used to compare the image data to be tested with the standard comparison data to obtain a product inspection result.

Images