Image processing method

Abstract

To provide an image processing method that can reduce a calculation load in processing a plurality of pieces of point data included in an image.SOLUTION: An image processing method specifies the size of the diameter of each of a plurality of pieces of point data included in an image, creates circle regions obtained by enlarging the diameters of the plurality of pieces of point data in a radial direction, brings the plurality of pieces of point data included in the circle regions together to generate first assembly point data, and from the generated first assembly point data, brings the pieces of first assembly point data including the same point data together to generate second assembly point data.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present disclosure relates to an image processing method.

Background Art

[0002] In Patent Document 1, regarding the detection technology of casting cavities, a technique is disclosed in which all of the "large casting cavities" and "small casting cavities" are arranged on the screen, and those that are closer to each other than a certain specified distance are regarded as originating from the same casting cavity.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technology disclosed in Patent Document 1, for example, when the total number of casting cavities is n, it is necessary to perform nC2 combination calculations, and the calculation load increases as the number of casting cavities increases.

[0005] The present disclosure has been made in view of the above, and an object thereof is to provide an image processing method capable of reducing the calculation load when processing a plurality of point data included in an image.

Means for Solving the Problems

[0006] The image processing method according to the present disclosure specifies the size of the diameter of each of a plurality of point data included in an image, creates a circular region in which the diameters of the plurality of point data are enlarged in the radial direction, groups the plurality of point data included in the circular region, creates first set point data, and groups the first set point data including the same point data among the created first set point data to create second set point data.

Effects of the Invention

[0007] According to this disclosure, the computational load when processing multiple point data contained in an image can be reduced. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a block diagram showing a schematic configuration of an image processing apparatus according to an embodiment. [Figure 2] Figure 2 is a diagram illustrating the outline of the first step of the image processing method performed by the image processing apparatus according to the embodiment. [Figure 3] Figure 3 is a diagram illustrating the overview of the second step of the image processing method performed by the image processing apparatus according to the embodiment. [Figure 4] Figure 4 is a diagram illustrating the outline of the third step of the image processing method performed by the image processing apparatus according to the embodiment. [Figure 5] Figure 5 is a diagram illustrating the outline of the fourth step of the image processing method performed by the image processing apparatus according to the embodiment. [Figure 6] Figure 6 is a flowchart showing the flow of the image processing method executed by the image processing apparatus according to the embodiment. [Modes for carrying out the invention]

[0009] The image processing method according to the embodiments of this disclosure will be described with reference to the drawings. Note that the components in the following embodiments include those that are easily substituted or substantially identical to those that are easily substituted by those skilled in the art.

[0010] (Image processing device) The configuration of the image processing apparatus according to this embodiment will be described with reference to Figure 1. The image processing apparatus according to this embodiment is for processing point data in an image. In this embodiment, the point data to be processed is a casting defect contained inside a casting. This casting defect has a predetermined size (area) in the image, but in this embodiment, one casting defect is treated as one point data.

[0011] The image processing apparatus according to this embodiment can be implemented using, for example, a general-purpose computer such as a workstation or a personal computer. Furthermore, as shown in Figure 1, the image processing apparatus 1 includes at least an arithmetic unit 11 and a storage unit 12.

[0012] Specifically, the arithmetic unit 11 includes a processor consisting of a CPU (Central Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), and memory (main memory) consisting of RAM (Random Access Memory), ROM (Read Only Memory), and the like.

[0013] The arithmetic unit 11 loads, for example, a program stored in the storage unit 12 into the working area of ​​the main memory and executes it, thereby controlling each component through the execution of the program and realizing a function that matches a predetermined purpose. Specifically, the arithmetic unit 11 performs the first, second, third, and fourth steps as an image processing method according to the embodiment. The details of each step will be described below with reference to Figures 2 to 5.

[0014] <First Step> In the first step, the diameter of each of the multiple point data points contained in the image is identified. In this first step, as shown in Figure 2 for example, the diameter of the casting defects contained in the image (see the solid circle) is identified, and an individual ID is assigned to the identified casting defects. For example, in the same figure, the four casting defects contained in the image are each assigned the individual IDs "ID:1", "ID:2", "ID:3", and "ID:4".

[0015] <Second Step> In the second step, a circular region is created by radially expanding the diameters of a plurality of point data. In this second step, for example, as shown in FIG. 3, one casting defect is selected, and a circular region (see the dashed circle) is created by expanding the diameter of the selected casting defect three times. For example, in the same figure, a circular region is created by expanding the diameter of the casting defect with "ID: 1" three times.

[0016] Here, the creation of the circular region in the second step is performed for each point data (each casting defect) included in the image. And for each point data (each casting defect) included in the image, a circular region is created.

[0017] <Third step> In the third step, a plurality of point data included in the circular region created in the second step are grouped together to create first aggregated point data. In this third step, for example, as shown in FIG. 3, it is checked whether other casting defects are included in the expanded circular region (overlapping). And when other casting defects are included in the expanded circular region, for example, as shown in FIG. 4, they are grouped together as one casting defect (aggregated casting defect), and the individual IDs of the grouped casting defects are stored in the storage unit 12. For example, in the same figure, since the casting defect with "ID: 4" is included in the circular region of the casting defect with "ID: 1", the individual IDs are grouped together as "ID[1,4]". Also, since the casting defect with "ID: 4" is included in the circular region of the casting defect with "ID: 3", the individual IDs are grouped together as "ID[3,4]".

[0018] Here, the duplication check in the third step is performed for each point data (each casting defect) included in the image. And for each point data (each casting defect) included in the image, first aggregated point data are created.

[0019] <Fourth step> The fourth step is performed after performing the second step and the third step for each point data (each casting defect) as described above. In this fourth step, among the first aggregated point data created in the third step, the first aggregated point data including the same point data are grouped together to create second aggregated point data.

[0020] In the fourth step, for example as shown in Figure 4, if the same casting defect is included in multiple first aggregate data points, for example as shown in Figure 5, they are combined into a single aggregate data point (second aggregate data point), and the individual IDs of the combined casting defects are stored in the storage unit 12. For example in the same figure, since the casting defect with "ID:4" is duplicated, the individual IDs are combined as "ID[1,3,4]".

[0021] The calculations described in steps one through four above are repeated until all point data (casting defects) are identified. In other words, the same image processing is repeated by changing arbitrary point data.

[0022] The memory unit 12 is implemented by recording media such as EPROM (Erasable Programmable ROM), Hard Disk Drive (HDD), and removable media. Examples of removable media include USB (Universal Serial Bus) memory, CD (Compact Disc), DVD (Digital Versatile Disc), and BD (Blu-ray® Disc).

[0023] The memory unit 12 stores, for example, image and casting data processed by the arithmetic unit 11, and the results of image processing performed by the arithmetic unit 11.

[0024] (Image processing method) The flow of the image processing method executed by the image processing apparatus according to the embodiment will be explained with reference to Figure 6.

[0025] First, the calculation unit 11 identifies the diameter of the casting defects included in the image and assigns an individual ID to the identified casting defects (step S1). Next, the calculation unit 11 selects one casting defect (step S2) and creates a circular region with the diameter of the selected casting defect tripled (step S3).

[0026] Next, the calculation unit 11 determines whether there are other casting defects overlapping the enlarged circular area in step S3 (step S4). If it is determined in step S4 that there are other casting defects overlapping the enlarged circular area (Yes in step S4), the calculation unit 11 combines the overlapping casting defects into one and stores the individual ID of the combined casting defect in the storage unit 12 (step S5).

[0027] Next, the calculation unit 11 determines whether the processes in steps S2 to S5 have been performed for all casting defects (step S6). If, in step S6, it is determined that the processes in steps S2 to S5 have not been performed for all casting defects (No in step S6), the calculation unit 11 returns to the process in step S2. On the other hand, if, in step S6, it is determined that the processes in steps S2 to S5 have been performed for all casting defects (Yes in step S6), the calculation unit 11 checks for duplicates of the saved individual IDs (step S7).

[0028] Next, the calculation unit 11 determines whether or not there are duplicate individual IDs (step S8). If it is determined in step S8 that there are duplicate individual IDs (Yes in step S8), the calculation unit 11 combines the sets of duplicate individual IDs (step S9), stores the individual IDs of the combined sets in the storage unit 12, and completes this process.

[0029] Here, if it is determined in step S4 that there are no other casting defects overlapping the enlarged circular area (No in step S4), the calculation unit 11 proceeds to the process in step S6. Also, if it is determined in step S8 that there are no duplicate individual IDs (No in step S8), the calculation unit 11 completes this process.

[0030] The image processing method according to the embodiment described above can reduce the computational load when processing multiple point data (casting defects) contained in an image. Specifically, when multiple casting defects are located close together in an image, the multiple casting defects are combined into one based on the distance between them. However, if the distance is calculated one by one, it is necessary to perform nC2 combination calculations for n casting defects. On the other hand, the image processing method according to the embodiment uses region data that combines overlapping casting defects, thereby reducing the number of combination calculations to n and thus reducing the computational load.

[0031] Further effects and modifications can be readily derived by those skilled in the art. Therefore, broader aspects of the present invention are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and their equivalents. [Explanation of Symbols]

[0032] 1 Image processing device 11 Arithmetic section 12 Storage section

Claims

[Claim 1] Identify the diameter of each of the multiple point data points indicating casting defects contained in the image. For each of the aforementioned multiple point data, a circular region is created by expanding its diameter in the radial direction. A first set of point data is created by combining the multiple point data contained within the circular region, which was created for each of the multiple point data mentioned above. From the first set point data created, the first set point data containing identical point data are grouped together to create a second set point data. Image processing methods.

Images