Device and method for detecting material of object

Abstract

The method for detecting a material of an object may include: acquiring image data of a specific region of the object; extracting a plurality of features included in the acquired image data; and determining at least one material based on at least one of the extracted plurality of features.

Description

Technical Field

[0001] The present embodiment relates to a device and method for detecting the material of an object. Background Art

[0002] If a manufacturer produces a product based on an object such as a raw material, the manufacturer wants to know the type and characteristics of the material contained in the raw material, but the raw material supplier does not provide information for reasons such as information security, and the type and characteristics of the material contained in the raw material may not be known.

[0003] When the manufacturer knows the types and characteristics of materials contained in the raw materials, it is possible to determine the causal relationship in which these materials change or are related during the product manufacturing process, and accordingly, it is possible to minimize the defects that may occur in the product production process based on the causal relationship. In addition, when the manufacturer knows the types and characteristics of materials contained in the raw materials, the manufacturer can feed back the changes in material types or adjustments in material characteristics to the raw material supplier to minimize the defects that may occur in the product production process, and accordingly, it is possible to obtain better quality raw materials from the raw material supplier in the future and produce better products.

[0004] Therefore, there is a strong need for a technology that can easily identify the type and characteristics of materials contained in an object. Summary of the invention

[0005] Technical issues

[0006] Embodiments are directed to solving the above-referenced problems and other problems.

[0007] Another object of an embodiment is to provide an apparatus and method for detecting a material of an object, which can easily identify the material contained in the object.

[0008] Furthermore, another object of the embodiment is to provide an apparatus and method for detecting a material of an object, which may have a simple structure and reduce costs because the material is identified based on an image acquired from the object.

[0009] Technical problems of the embodiment are not limited to those described in this item, and include those that can be identified through the description of the present invention.

[0010] Technical Solution

[0011] According to one aspect of the embodiment, to achieve the above or other purposes, a method for detecting the material of an object includes: acquiring image data of a specific area of ​​the object; extracting multiple features included in the acquired image data; and determining at least one material based on at least one of the extracted multiple features.

[0012] Characteristics may include brightness, size, shape, and color.

[0013] The determining of the at least one material may include determining the at least one material according to brightness.

[0014] The determining of the at least one material may include determining the at least one material according to brightness and size.

[0015] The determining of the at least one material may include determining the at least one material according to brightness, size, and shape.

[0016] The determining of the at least one material may include determining the at least one material according to brightness, size, shape, and color.

[0017] The plurality of features may include sharpness. The determination of at least one material may include determining the void based on the sharpness.

[0018] The at least one material may be at least one of glass fabric, at least one filler, and resin.

[0019] Before extracting the multiple features, the acquired image data may be subjected to denoising.

[0020] According to another aspect of the embodiment, to achieve the above or other purposes, a device for detecting the material of an object includes: an image acquisition unit, which is used to acquire image data of a specific area of ​​the object; a feature extraction unit, which is used to extract multiple features included in the acquired image data; and a material determination unit, which is used to determine at least one material based on at least one feature of the extracted multiple features.

[0021] Characteristics may include brightness, size, shape, and color.

[0022] The material determination unit may determine at least one material according to brightness.

[0023] The material determination unit may determine at least one material according to brightness and size.

[0024] The material determination unit may determine at least one material according to brightness, size, and shape.

[0025] The material determination unit may determine at least one material according to brightness, size, shape, and color.

[0026] The plurality of features may include sharpness, and the material determination unit may determine the gap according to the sharpness.

[0027] The at least one material may be at least one of glass fabric, at least one filler, and resin.

[0028] The apparatus for detecting a material of an object may include a denoising unit for denoising acquired image data.

[0029] Beneficial Effects

[0030] Next, effects of the apparatus and method for detecting a material of an object according to the embodiment will be described.

[0031] According to at least one embodiment, there is an advantage in that various materials included in an object can be easily recognized through image data acquired from the object.

[0032] According to at least one embodiment, there are advantages in that since a material is identified based on an image acquired from an object, the structure is simple and the cost can be reduced.

[0033] Other applicable scopes of the present embodiment will become apparent from the following detailed description. However, since those skilled in the art can clearly understand various changes and modifications within the spirit and scope of the present invention, it should be understood that the detailed description and specific embodiments (such as preferred embodiments) are given only as examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a cross-sectional view showing a circuit board according to an embodiment.

[0035] Figure 2 is a block diagram showing an apparatus for detecting a material of an object according to a first embodiment.

[0036] Figure 3 is a flowchart describing a method for detecting a material of an object according to an embodiment.

[0037] 5A and 5B illustrate the state of detecting a material according to size.

[0038] Figures 6a to 6f Indicates the status of the test resin.

[0039] Figure 7a and Figure 7b Indicates the status of the detection filler.

[0040] Figure 8a and Figure 8b The diagram shows a state where the glass fabric is detected.

[0041] Figure 9a and Figure 9b The diagram shows a state where a gap is detected.

[0042] Fig.10 The diagram shows the state of detecting materials based on color.

[0043] Fig.11is a block diagram showing an apparatus for detecting a material of an object according to a second embodiment.

[0044] Fig.12a and Figure 12b Images before and after denoising are shown. DETAILED DESCRIPTION

[0045] The embodiments disclosed in this specification will be described in detail below with reference to the accompanying drawings. Regardless of the figure symbols, the same or similar components will be assigned the same reference numerals, and redundant descriptions will be omitted. The suffixes "module" and "unit" used for components in the following description are given or used interchangeably in consideration of the convenience of writing the specification, and do not have clear meanings or functions in themselves. In addition, the accompanying drawings are for the convenience of understanding the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the accompanying drawings. In addition, when it is mentioned that an element such as a layer, a region or a substrate is present "on" another element, this includes that it may be directly present on another element, or other intermediate elements may be present therebetween.

[0046] Embodiments may provide a method and apparatus that can easily identify the type of material included in an object such as a raw material.

[0047] In the following description, a circuit board is presented as a representative raw material, but the present embodiment may include a raw material including at least one material. In addition, the present embodiment may also include a member including at least one material other than the raw material.

[0048] Figure 1 is a cross-sectional view showing a circuit board according to an embodiment.

[0049] refer to Figure 1 The circuit board according to the present embodiment may include a plurality of prepregs 110 , a resin layer 120 between the prepregs 110 , and a plurality of through holes 151 , 152 .

[0050] The prepreg 110 may be formed by impregnating a fiber layer in the form of a fabric sheet (such as a glass fabric 112 woven using glass fiber yarn) with an epoxy resin 111, and then hot pressing the fiber layer. However, the present embodiment is not limited thereto. That is, the prepreg 110 may also include a fiber layer in the form of a fabric sheet woven using carbon fiber yarn.

[0051] After the resin layer 120 is positioned between the prepregs 110, the substrate can be completed by pressurization using a hot pressing method using pressure. Afterwards, a through hole is formed by drilling the prepreg 110, and the through hole is filled with a conductive material or plated with a conductive material, thereby forming through holes 151, 152. The conductive material can be any one selected from Cu, Ag, Sn, Au, Ni, and Pd. The through hole can be formed by any one of mechanical, laser, and chemical processing methods.

[0052] The through holes 151 , 152 may be electrically connected with the circuit patterns 141 to 143 provided on the upper side and / or the lower side of the prepreg 110 .

[0053] Meanwhile, the uninterpreted symbol 113 may be a void, that is, an empty space where no material exists. In addition, the uninterpreted symbol 130 is a filler. The filler 130 may include various types of fillers that are different from each other.

[0054] Figure 2 is a block diagram showing an apparatus for detecting a material of an object according to a first embodiment.

[0055] In the following description, for ease of explanation, Figure 1 The substrate shown in the figure is limited to the object, but this embodiment can be equally applied to other Figure 1 Components other than the substrate shown in FIG.

[0056] refer to Figure 1 and Figure 2 , the apparatus 200 for detecting a material of an object according to the first embodiment may include an image acquiring unit 210 , a feature extracting unit 220 , and a material determining unit 230 .

[0057] The image acquisition unit 210 may acquire image data of a specific area of ​​an object.

[0058] The image data may be acquired by a destructive inspection method. For example, the object is cut so that a specific cross section of the object is exposed, and image data is acquired for the specific cross section of the cut. For example, the image data may be acquired by a microscope, SEM, or TEM, etc., but is not limited thereto.

[0059] At the same time, this embodiment can also acquire image data for the specific area to be photographed by a non-destructive testing method.

[0060] The feature extraction unit 220 may extract a plurality of features included in the image data. The plurality of features may include brightness, size, shape, color, sharpness, and the like.

[0061] The image data may include various materials, which may be distinguished from each other by brightness, boundaries, colors, sharpness, etc. That is, the materials may be distinguished from each other by brightness, boundaries, colors, sharpness, etc. Figure 1 The substrate shown in can be a variety of different materials. In other words, the substrate can be composed of various materials. These materials can be resins, glass fabrics, filters, etc. Voids can also be included in the substrate and can also be classified as a material.

[0062] The material determination unit 230 may determine at least one material according to at least one of the plurality of features extracted by the feature extraction unit 220. That is, at least one material may be determined according to at least one of brightness, size, shape, and color.

[0063] because Figure 1 The substrate shown in includes resin, at least one filler, glass fabric, and voids as materials, and thus at least one of the resin, at least one filler, glass fabric, and voids may be determined according to at least one of brightness, size, shape, and color.

[0064] For example, the material determination unit 230 may determine at least one material according to brightness.

[0065] For example, the material determination unit 230 may determine at least one material according to brightness and size.

[0066] For example, the material determination unit 230 may determine at least one material according to brightness, size, and shape.

[0067] For example, the material determination unit 230 may determine at least one material according to brightness, size, shape, and color.

[0068] Meanwhile, the material determination unit 230 may determine the gap according to the sharpness. Figure 9a As shown, when viewing color image data, since both the resin and the void appear black, they may not be distinguished from each other, and errors may occur in determining the void and the resin. Therefore, considering sharpness as a feature, the resin and the void can be distinguished by the size of the sharpness. The sharpness can be increased so that the boundary of the void is clearly visible. In this case, considering that the void is relatively very small compared to the resin, the sharpness can be increased so that a material with a very small outline compared to the resin can be determined as a void.

[0069] Meanwhile, the apparatus 200 for detecting the material of an object according to the first embodiment may include a storage unit (not shown) that stores image data, various information of each material, such as brightness information, size information, shape information, color information, size information, etc. The storage unit may store various data or information generated in the present embodiment.

[0070] The apparatus 200 for detecting the material of an object according to the first embodiment may include a label unit (not shown) that labels each of the detected or determined materials to distinguish them. The label may be processed with color, letters, pictures, numbers, highlights, etc.

[0071] The apparatus 200 for detecting a material of an object according to the first embodiment may include a calculation unit (or an operation unit, not shown) that calculates a size or an area.

[0072] Figure 3 is a flow chart describing a method of detecting a material of an object according to an embodiment.

[0073] like Figure 2 and Figure 3 As shown, the image acquisition unit 210 (S310) acquires image data, the feature extraction unit 220 (S320) extracts a plurality of features, and the material determination unit 230 (S330) may determine at least one material.

[0074] The following will refer to Figures 4 to 10 A method for determining at least one material using a plurality of characteristics is described.

[0075] Figure 4 A method of detecting a material based on brightness is shown.

[0076] like Figure 4 As shown, brightness can be used as one of the multiple features to determine voids, resin, and filler.

[0077] Image data may include various materials that are distinguished from each other by size, shape, color, etc. The materials may also differ in brightness. Figure 4 As shown in , the amount of material included in the corresponding image data according to brightness can be described. The brightness unit can be grayscale, but is not limited thereto.

[0078] The material corresponding to grayscale 0 and grayscale A may be a gap, the material corresponding to grayscale A and grayscale B may be a resin, and the material corresponding to grayscale B or higher may be a filler.

[0079] Therefore, among the materials extracted from the image data, the material distributed between grayscale 0 and grayscale A can be determined as a void, the material distributed between grayscale A and grayscale B can be determined as a resin, and the material distributed at grayscale B or higher can be determined as a filler.

[0080] and Figure 4 Different from what is shown, other materials may be determined to replace the voids, resins and fillers.

[0081] 5A and 5B illustrate a state of detecting a material according to a size.

[0082] As shown in FIGS. 5A and 5B , different materials can be detected based on size.

[0083] The material equal to or larger than size a may be determined as glass fabric 315 (FIG. 5A), and the material smaller than size b may be determined as filler 312 (FIG. 5B). Size a may be several to several dozen times larger than size b, but is not limited thereto.

[0084] When the filler 312 is divided into several types, the dimension b may be set as a reference dimension, such as dimension b-1, dimension b-2, or dimension b-3. Dimension b-2 may be smaller than dimension b-1, and dimension b-3 may be smaller than dimension b-2.

[0085] Figures 6a to 6f Indicates the state of resin detection.

[0086] Figure 6a Is Figure 2 The original image data acquired by the image acquisition unit 210 shown in FIG. Figure 6b to Figure 6f It is shown that the area where the resin is detected varies according to reference values ​​different from each other.

[0087] Figure 6b The distribution of the resin 311 detected when the reference value of 5 pixels is exceeded is shown, and only the resin 311 having a total area greater than 5 pixels can be detected. Figure 6c The distribution of the resin 311 detected when the reference value of 15 pixels is exceeded is shown, and only the resin 311 of a total area greater than 15 pixels can be detected. Figure 6d The distribution of the detected resin 311 when the reference value of 25 pixels is exceeded is shown, and only the resin 311 having a total area greater than 25 pixels can be detected. Figure 6e The distribution of the resin 311 detected when the reference value of 35 pixels is exceeded is shown, and only the resin 311 having a total area greater than 35 pixels can be detected. Figure 6f is the distribution of the resin 311 detected when exceeding the reference value of 50 pixels, and only the resin 311 having a total area greater than 50 pixels can be detected.

[0088] like Figure 6b to Figure 6f As shown in , the distribution degree of the detected resin 311 may vary according to the size of the reference value. When the reference value is small or large, the detected resin 311 may be small or large, and the detection accuracy of the resin 311 may be reduced, so it is necessary to set an optimal reference value. For example, the optimal reference value may be 25 pixels, but is not limited thereto.

[0089] Meanwhile, the resin 311 may be detected using at least one feature among a plurality of features extracted from the image data.

[0090] For example, the resin 311 may be detected using brightness. For example, the resin 311 may be detected using brightness and size. For example, the resin 311 may be detected using brightness, size, and shape. For example, the resin 311 may be detected using brightness, size, shape, and color.

[0091] Figure 7a and Figure 7b The diagram shows the state where the filler is detected.

[0092] Multiple features can be extracted from image data ( Figure 7a ), at least one of the extracted features can be used to detect multiple fillers 312 ( Figure 7b ).

[0093] For example, the filler 312 may be detected using brightness. For example, the filler 312 may be detected using brightness and size. For example, the filler 312 may be detected using brightness, size, and shape. For example, the filler 312 may be detected using brightness, size, shape, and color.

[0094] Figure 8a and Figure 8b The diagram shows a state where the glass fabric is detected.

[0095] like Figure 1 , Figure 8a and Figure 8b As shown, the prepreg 110 may be formed by impregnating a fiber layer in the form of a fabric sheet (such as a glass fabric 315 woven using glass fiber yarns) with an epoxy resin 313 and then hot-pressing the fiber layer. Other resins may also be used instead of the epoxy resin 313.

[0096] Figure 8b The state of detecting the epoxy resin 313 is illustrated, and the distribution position and density of the prepreg 110 can be identified by detecting the epoxy resin 313 .

[0097] The epoxy resin 313 is included in the prepreg 110 ( Figure 1 ),and Figures 6a to 6f The resin 311 shown in FIG. 1 may be included in the resin layer 120 ( Figure 1 ).

[0098] Epoxy 313 may be detected using a number of characteristics such as brightness, size, shape, color, and the like.

[0099] In contrast, the epoxy resin 313 forms the prepreg 110 together with the glass fabric 315 , and is located around the glass fabric 315 , and thus can be detected together with the glass fabric 315 .

[0100] Figure 9a and Figure 9b The diagram shows a state where a gap is detected.

[0101] By adjusting the sharpness of the image data ( Figure 9a ), the gap 314 can be detected ( Figure 9b ).

[0102] exist Figure 9a In the image data shown in , both the resin and the void 314 appear black, and thus it is difficult to distinguish them. Therefore, the sharpness can be adjusted to distinguish the void 314 from the resin or other members. Even if both the void 314 and the resin appear black, the void 314 can be distinguished from the resin by increasing the sharpness.

[0103] like Figure 9b As shown, the voids 314 can be detected and distinguished from the resin by adjusting the sharpness.

[0104] Meanwhile, as described above, materials can be detected based on color.

[0105] Fig.10 The diagram shows the state of detecting materials based on color.

[0106] like Fig.10 As shown in , various materials can be distinguished by white and black in image data. Various materials can be detected by color differences including white and black.

[0107] Fig.10 A prepreg is illustrated, which may include epoxy resin 313 and glass fabric 315 .

[0108] For example, epoxy 313 may be indicated in black, and glass fabric 315 may be indicated in white.

[0109] The material smaller than the size of the glass fabric 315 may be a filler. Both the glass fabric 315 and the filler may be indicated in white. In this case, when the respective sizes of the glass fabric 315 and the filler are known, the material corresponding to the corresponding size among the materials indicated in white may be detected as the glass fabric 315 or the filler.

[0110] When there are fillers of various sizes, each of the fillers can be detected separately when the size of each of the various fillers is known.

[0111] Fig.11is a block diagram showing an apparatus for detecting a material of an object according to a second embodiment.

[0112] refer to Fig.11 , the apparatus 201 for detecting the material of an object according to the second embodiment may include an image acquiring unit 210 , a denoising unit 240 , a feature extracting unit 220 , and a material determining unit 230 .

[0113] Since the image acquisition unit 210, the feature extraction unit 220, and the material determination unit 230 have been described in the first embodiment Figure 2 Therefore, the detailed description thereof will be omitted.

[0114] The denoising unit 240 may process shadows inside the specific material to be the same while emphasizing the edge of the specific material.

[0115] Fig.12a can be image data without denoising processing, and Figure 12b It may be image data with denoising processing.

[0116] When no denoising is performed ( Fig.12a ), it can be seen that the edge of the glass fabric 315 is blurred and the shadow inside the glass fabric 315 is uneven. However, when the denoising process is performed ( Figure 12b ), it can be seen that the edge of the glass fabric 315 is sharper and the shadow inside the glass fabric 315 is the same.

[0117] The above detailed description should not be interpreted as limiting in all aspects, but should be regarded as illustrative. The scope of the embodiment should be determined by reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present embodiment are included in the scope of the present embodiment.

Claims

1. A method for detecting a material of an object, comprising: Acquiring image data of a specific area of ​​the object; extracting a plurality of features included in the acquired image data; as well as At least one material is determined based on at least one of the extracted plurality of features.

2. The method for detecting the material of an object according to claim 1, wherein: The multiple characteristics include brightness, size, shape and color.

3. The method for detecting the material of an object according to claim 2, wherein: The determining of the at least one material includes determining the at least one material based on the brightness.

4. The method for detecting the material of an object according to claim 2, wherein: The determining of the at least one material includes determining the at least one material based on the brightness and the size.

5. The method for detecting the material of an object according to claim 2, wherein: The determining of the at least one material includes determining the at least one material based on the brightness, the size, and the shape.

6. The method for detecting the material of an object according to claim 2, wherein: The determining of the at least one material includes determining the at least one material based on the brightness, the size, the shape, and the color.

7. The method for detecting the material of an object according to claim 2, wherein: The plurality of features include sharpness, and The determining of the at least one material includes determining a void based on the sharpness.

8. The method for detecting a material of an object according to claim 1, wherein: The at least one material is at least one of glass fabric, at least one filler, and resin.

9. The method for detecting a material of an object according to claim 1, comprising: The acquired image data is denoised before extracting the plurality of features.

10. A device for detecting a material of an object, comprising: an image acquisition unit, the image acquisition unit acquiring image data of a specific area of ​​the object; a feature extraction unit, the feature extraction unit extracting a plurality of features included in the acquired image data; as well as A material determination unit is configured to determine at least one material based on at least one of the extracted plurality of features.

11. The device for detecting the material of an object according to claim 10, wherein: The multiple characteristics include brightness, size, shape and color.

12. The device for detecting the material of an object according to claim 11, wherein: The material determination unit determines the at least one material based on the brightness.

13. The device for detecting the material of an object according to claim 11, wherein: The material determination unit determines the at least one material based on the brightness and the size.

14. The device for detecting the material of an object according to claim 11, wherein: The material determination unit determines the at least one material based on the brightness, the size, and the shape.

15. The device for detecting the material of an object according to claim 11, wherein: The material determination unit determines the at least one material based on the brightness, size, shape, and color.

16. The device for detecting the material of an object according to claim 11, wherein: The plurality of features include sharpness, and The material determination unit determines a gap based on the sharpness.

17. The device for detecting the material of an object according to claim 10, wherein: The at least one material is at least one of glass fabric, at least one filler, and resin.

18. The device for detecting the material of an object according to claim 10, comprising: A denoising unit is used to denoise the acquired image data.

Images