Cloth classification method

Abstract

The invention discloses a cloth classification method. The cloth classification method comprises the following steps: shooting first cloth to generate a first original cloth image; generating a first cloth logic value image according to the first original cloth image; searching a first hole image part in the first original cloth image according to the first cloth logic value image; coloring the first hole image part according to a first cloth image part in the first original cloth image to generate a first colored cloth image; and classifying the first cloth according to the first colored cloth image. Therefore, the classification result is more accurate.

Description

Technical Field

[0001] The present disclosure relates to a fabric classification technology, and more particularly to a fabric classification method. Background Art

[0002] Generally speaking, when conveying cloth, the cloth has elasticity and will be stretched and deformed under tension to produce holes. The holes will cause the cloth image to have color differences, making the classification result inaccurate when the cloth image is classified. Therefore, developing a technology that can overcome the above problems is an important issue in the field. Summary of the invention

[0003] The disclosed embodiment includes a fabric classification method. The fabric classification method includes: photographing a first fabric to generate a first original fabric image; generating a first fabric logic value image according to the first original fabric image; searching for a first hole image portion in the first original fabric image according to the first fabric logic value image; coloring the first hole image portion according to the first fabric image portion in the first original fabric image to generate a first colored fabric image; and classifying the first fabric according to the first colored fabric image.

[0004] In some embodiments, the first fabric image portion is adjacent to the first hole image portion.

[0005] In some embodiments, coloring the first hole image portion includes: generating a first hole color parameter of a first hole image pixel in the first hole image portion according to a first cloth color parameter of a first cloth image pixel in the first cloth image portion, a second cloth color parameter of a second cloth image pixel in the first cloth image portion, and a third cloth color parameter of a third cloth image pixel in the first cloth image portion; and coloring the first hole image pixel according to the first hole color parameter.

[0006] In some embodiments, the first fabric image pixel is adjacent to the first hole image pixel in a first direction and adjacent to the second fabric image pixel in a second direction, the third fabric image pixel is adjacent to the first hole image pixel in the second direction and adjacent to the second fabric image pixel in the first direction, and the first direction is different from the second direction.

[0007] In some embodiments, coloring the first hole image portion further includes: after coloring the first hole image pixel according to the first hole color parameter of the first hole image pixel, generating a second hole color parameter of a second hole image pixel in the first hole image portion according to the first hole color parameter, the third fabric color parameter, and a fourth fabric color parameter of a fourth fabric image pixel in the first fabric image portion; and coloring the second hole image pixel according to the second hole color parameter.

[0008] In some embodiments, the first hole image pixel is adjacent to the second hole image pixel in a first direction, and the fourth cloth image pixel is adjacent to the third cloth image pixel in the first direction.

[0009] In some embodiments, the fourth cloth image pixel is adjacent to the second hole image pixel in a second direction, and the first direction is different from the second direction.

[0010] In some embodiments, coloring the first hole image portion further includes: coloring a third hole image pixel in the first hole image portion according to a third hole color parameter; generating a fourth hole color parameter according to the third hole color parameter, a fifth cloth color parameter of a fifth cloth image pixel in the first cloth image portion, and a sixth cloth color parameter of a sixth cloth image pixel in the first cloth image portion; and coloring a fourth hole image pixel in the first hole image portion according to the fourth hole color parameter; generating a fifth hole color parameter at least according to the fourth hole color parameter; and coloring a fifth hole image pixel in the first hole image portion according to the fifth hole color parameter, wherein the fourth hole image pixel is located between the fifth hole image pixel and the sixth cloth image pixel.

[0011] In some embodiments, generating a fifth hole color parameter based on at least the fourth hole color parameter includes generating the fifth hole color parameter based on the fourth hole color parameter, a seventh cloth color parameter of a seventh cloth image pixel in the first cloth image portion, and an eighth cloth color parameter of an eighth cloth image pixel in the first cloth image portion, wherein the fourth hole image pixel and the fifth hole image pixel are adjacent to the seventh cloth image pixel and the eighth cloth image pixel, respectively.

[0012] In some embodiments, the cloth classification method further includes: coloring a sixth hole image pixel in the first hole image portion according to a sixth hole color parameter; coloring a seventh hole image pixel in the first hole image portion according to a seventh hole color parameter; coloring an eighth hole image pixel in the first hole image portion according to an eighth hole color parameter; coloring a ninth hole image pixel in the first hole image portion according to a ninth hole color parameter; coloring a tenth hole image pixel in the first hole image portion according to a tenth hole color parameter; and after coloring the tenth hole image pixel, stopping coloring the first hole image portion and outputting the first colored cloth image, wherein the sixth hole image pixel is adjacent to a first side of the tenth hole image pixel, the seventh hole image pixel is adjacent to a second side of the tenth hole image pixel, the eighth hole image pixel is adjacent to a third side of the tenth hole image pixel, the ninth hole image pixel is adjacent to a fourth side of the tenth hole image pixel, the first side and the second side are opposite to each other in the first direction, and the third side and the fourth side are opposite to each other in the second direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of a cloth classification system according to some embodiments of the present disclosure;

[0014] Figure 2 is a schematic diagram of a first original fabric image and a first fabric logical value image according to some embodiments of the present disclosure;

[0015] Figure 3 is a schematic diagram showing further details of a first original cloth image according to some embodiments of the present disclosure;

[0016] Figure 4 is a flow chart of a method for classifying fabrics according to some embodiments of the present disclosure;

[0017] Figure 5 According to some embodiments of the present disclosure, Figure 4 a flow chart showing further details of the operations shown;

[0018] Figure 6 According to some embodiments of the present disclosure, Figure 4 a flow chart showing further details of the operations shown;

[0019] Figure 7 According to some embodiments of the present disclosure, Figure 4 Flow chart of other operations of the cloth classification method shown.

[0020]

Explanation of symbols

[0021] 100: Fabric classification system

[0022] 110:Photographic Installation

[0023] 120: Processing device

[0024] 130: Transport device

[0025] FB1: First Fabric

[0026] M1: First original cloth image

[0027] ML1: First cloth logical value image

[0028] BP1: First black part

[0029] HP1: The first hole image

[0030] MP1: First fabric image part

[0031] HX1: First hole image pixel

[0032] HX2: Second hole image pixel

[0033] HX3: The third hole image pixel

[0034] HX4: Fourth hole image pixel

[0035] HX5: Fifth hole image pixel

[0036] HX6: Sixth hole image pixel

[0037] HX7: Seventh hole image pixels

[0038] HX8: Eighth hole image pixels

[0039] HX9: Image pixels of the ninth hole

[0040] HX10: The tenth hole image pixel

[0041] MX1: The first fabric imaging pixel

[0042] MX2: Second fabric image pixel

[0043] MX3: Third Fabric Image Pixel

[0044] MX4: The fourth fabric image pixel

[0045] MX5: The fifth fabric imaging pixel

[0046] MX6: The sixth fabric imaging pixel

[0047] MX7: The seventh fabric imaging pixel

[0048] MX8: The eighth fabric imaging pixel

[0049] 400: Fabric classification method

[0050] OP41~OP45、OP51~OP54、OP61~OP65、OP71~OP76: Operation DETAILED DESCRIPTION

[0051] In this document, although the terms "first", "second", etc. are used to describe different components, the terms are only used to distinguish components or operations described with the same technical terms. Unless the context clearly indicates otherwise, the terms do not specifically refer to or imply an order or sequence, nor are they used to limit the present disclosure.

[0052] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and the present disclosure, and will not be interpreted as an idealized or overly formal meaning unless explicitly defined as such herein.

[0053] The terms used herein are only for the purpose of describing specific embodiments and are not restrictive. As used herein, unless the content clearly indicates, the singular forms "one", "an" and "the" are intended to include plural forms, including "at least one". "Or" means "and / or". As used herein, the term "and / or" includes any and all combinations of one or more related listed items. It should also be understood that when used in this specification, the terms "include" and / or "comprise" specify the presence and / or parts of the features, regions, entireties, steps, operations, elements, but do not exclude the presence or addition of one or more other features, regions, entireties, steps, operations, elements, parts and / or their combinations.

[0054] The following will disclose multiple embodiments of the present disclosure with the accompanying drawings. For the purpose of clear description, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present disclosure. In other words, in some embodiments of the present disclosure, these practical details are not necessary. In addition, in order to simplify the drawings, some conventional structures and elements will be depicted in a simple schematic manner in the drawings.

[0055] Figure 1Schematic diagram of a cloth classification system 100 according to some embodiments of the present disclosure. In some embodiments, the cloth classification system 100 includes a photographic device 110, a processing device 120, and a transporting device 130. In some embodiments, the photographic device 110 is coupled to the processing device 120 and the processing device 120 is coupled to the transporting device 130. In some embodiments, the photographic device 110 can be implemented by a charge coupled device (CCD).

[0056] In some embodiments, the photographing device 110 is used to photograph the first fabric FB1 to generate a first original fabric image M1. The processing device 120 is used to process the first original fabric image M1 to classify the first fabric FB1. In some embodiments, the first fabric FB1 may be a garter.

[0057] In some embodiments, the transport device 130 may transport the first fabric FB1 to a corresponding location according to the classification result of the first fabric FB1. Figures 2 to 7 The implementation method is further described in the following.

[0058] Figure 2 FIG. 1 is a schematic diagram of a first original fabric image M1 and a first fabric logical value image ML1 according to some embodiments of the present disclosure. In some embodiments, the processing device 120 may perform a binarization process on the first original fabric image M1 to generate the first fabric logical value image ML1.

[0059] Specifically, during the binarization process, the processing device 120 may convert the darker portion of the first original fabric image M1 into the black portion of the first fabric logic value image ML1, and convert the lighter portion of the first original fabric image M1 into the white portion of the first fabric logic value image ML1.

[0060] In other words, the darker portion of the first original fabric image M1 has the same position and size as the black portion of the first fabric logical value image ML1, and the lighter portion of the first original fabric image M1 has the same position and size as the white portion of the first fabric logical value image ML1.

[0061] In some embodiments, the black portion in the first fabric logical value image ML1 has a first logical value, such as a logical value of 0, and the white portion in the first fabric logical value image ML1 has a second logical value, such as a logical value of 1.

[0062] In some embodiments, the processing device 120 is further configured to search for a hole image portion in the first original fabric image M1 according to a black portion in the first fabric logical value image ML1. For example, the processing device 120 may search for a first hole image portion HP1 in the first original fabric image M1 according to a first black portion BP1 in the first fabric logical value image ML1. However, the embodiments of the present invention are not limited thereto. In various embodiments, the processing device 120 may also search for other hole image portions in the first original fabric image M1 according to other black portions in the first fabric logical value image ML1.

[0063] In some embodiments, the processing device 120 determines the portion of the first original cloth image M1 other than the hole image portion as the cloth image portion, such as the first cloth image portion MP1 surrounding the first hole image portion HP1.

[0064] In some embodiments, the processing device 120 colors the hole image portion according to the cloth image portion, for example, colors the first hole image portion HP1 according to the first cloth image portion MP1 to generate a first colored cloth image.

[0065] In some embodiments, the processing device 120 further classifies the first fabric FB1 according to the first colored fabric image, for example, determining whether the first fabric FB1 belongs to a dark color category or a light color category. However, the embodiments of the present invention are not limited thereto. In various embodiments, the processing device 120 may also classify the first fabric FB1 into various numbers of categories.

[0066] In some embodiments, the photographing device 110 may photograph a plurality of fabrics to generate a plurality of original fabric images. The processing device 120 may process the plurality of original fabric images to generate a plurality of corresponding colored fabric images, and convert the image data (e.g., color representation feature values) of the plurality of colored fabric images from the RGB color space to the XYZ color space, and then convert from the XYZ color space to the La*b* color space.

[0067] In some embodiments, the processing device 120 can group the image data in the La*b* color space, for example, by performing group evaluation through the AI ​​model K-means grouping principle to define corresponding categories, such as a light color category, a middle color category, and a dark color category. However, the embodiments of the present invention are not limited thereto. In various embodiments, the processing device 120 can define various numbers of categories through the AI ​​model K-means grouping principle.

[0068] Figure 3 FIG. 4 is a schematic diagram showing further details of the first original cloth image M1 according to some embodiments of the present disclosure. Figure 3As shown, the first original cloth image M1 includes a first hole image portion HP1 and a first cloth image portion MP1.

[0069] like Figure 3 As shown, the first hole image portion HP1 includes multiple hole image pixels, such as a first hole image pixel HX1, a second hole image pixel HX2, a third hole image pixel HX3, a fourth hole image pixel HX4, a fifth hole image pixel HX5, a sixth hole image pixel HX6, a seventh hole image pixel HX7, an eighth hole image pixel HX8, a ninth hole image pixel HX9 and a tenth hole image pixel HX10.

[0070] like Figure 3 As shown, the first cloth image portion MP1 includes a plurality of cloth image pixels, such as a first cloth image pixel MX1, a second cloth image pixel MX2, a third cloth image pixel MX3, a fourth cloth image pixel MX4, a fifth cloth image pixel MX5, a sixth cloth image pixel MX6, a seventh cloth image pixel MX7 and an eighth cloth image pixel MX8.

[0071] In some embodiments, the processing device 120 uses a spiral interpolation method along Figure 3 The arrows shown in FIG. 1 sequentially colorize the plurality of hole image pixels of the first hole image portion HP1. The details of colorizing the first hole image portion HP1 are described in detail below with respect to Figures 4 to 7 The embodiments are further described in the examples.

[0072] Figure 4 FIG. 4 is a flow chart of a fabric classification method 400 according to some embodiments of the present disclosure. Figure 4 As shown, the cloth classification method 400 includes operations OP41 to OP45. In some embodiments, the cloth classification method 400 may be performed by Figure 1 The cloth classification system 100 is shown to be implemented, but the disclosure is not limited thereto.

[0073] In operation OP41 , the photographing device 110 photographs the first fabric FB1 to generate a first original fabric image M1 .

[0074] In operation OP42 , the processing device 120 generates a first cloth logic value image ML1 according to the first original cloth image M1 .

[0075] In operation OP43 , the processing device 120 searches for the first hole image portion HP1 in the first original cloth image M1 according to the first cloth logical value image ML1 .

[0076] In operation OP44 , the processing device 120 colors the first hole image portion HP1 according to the first cloth image portion MP1 in the first original cloth image M1 to generate a first colored cloth image.

[0077] In operation OP45 , the processing device 120 classifies the first fabric FB1 according to the first colored fabric image.

[0078] In some embodiments, the first cloth image portion MP1 is adjacent to the first hole image portion HP1. For example, the first cloth image portion MP1 surrounds the first hole image portion HP1 and is adjacent to the first hole image portion HP1 in both the first direction and the second direction. In some embodiments, the first direction and the second direction are perpendicular to each other.

[0079] In some methods, when the cloth is conveyed, the cloth is elastic and will be stretched and deformed under tension to produce holes. The holes will cause the cloth image to have color differences, making the classification result inaccurate when the cloth image is classified.

[0080] Compared to the above method, in the embodiment of the present invention, the processing device 120 colors the first hole image portion HP1 according to the first fabric image portion MP1 to eliminate the color difference caused by the hole. In this way, the classification result of the first fabric FB1 according to the first colored fabric image is more accurate.

[0081] Figure 5 According to some embodiments of the present disclosure, Figure 4 44. Figure 5 As shown, operation OP44 may include operations OP51 - OP54 .

[0082] In operation OP51, the processing device 120 generates a first hole color parameter of the first hole image pixel HX1 in the first hole image part HP1 according to the first cloth color parameter of the first cloth image pixel MX1 in the first cloth image part MP1, the second cloth color parameter of the second cloth image pixel MX2 in the first cloth image part MP1, and the third cloth color parameter of the third cloth image pixel MX3 in the first cloth image part MP1.

[0083] In operation OP52 , the processing device 120 colors the first hole image pixel HX1 according to the first hole color parameter.

[0084] In some embodiments, the first fabric image pixel MX1 is adjacent to the first hole image pixel HX1 in the first direction and adjacent to the second fabric image pixel MX2 in the second direction. The third fabric image pixel MX3 is adjacent to the first hole image pixel HX1 in the second direction and adjacent to the second fabric image pixel MX2 in the first direction. The first direction is different from the second direction.

[0085] In operation OP53, after the processing device 120 colors the first hole image pixel HX1 according to the first hole color parameter of the first hole image pixel HX1, it generates the second hole color parameter of the second hole image pixel HX2 in the first hole image part HP1 according to the first hole color parameter, the third fabric color parameter and the fourth fabric color parameter of the fourth fabric image pixel MX4 in the first fabric image part HP1.

[0086] In operation OP54 , the processing device 120 colors the second hole image pixel HX2 according to the second hole color parameter.

[0087] In some embodiments, the first hole image pixel HX1 is adjacent to the second hole image pixel HX2 in the first direction, and the fourth fabric image pixel MX4 is adjacent to the third fabric image pixel MX3 in the first direction. The third fabric image pixel MX3 is located between the fourth fabric image pixel MX4 and the second fabric image pixel MX2. The first hole image pixel HX1 is located between the second hole image pixel HX2 and the first fabric image pixel MX1.

[0088] In some embodiments, the fourth cloth image pixel MX4 is adjacent to the second hole image pixel HX2 in the second direction, and the first direction is different from the second direction.

[0089] Figure 6 According to some embodiments of the present disclosure, Figure 4 44. Figure 6 As shown, operation OP44 may further include operations OP61 - OP65 .

[0090] In operation OP61 , the processing device 120 colors the third hole image pixel HX3 in the first hole image portion HP1 according to the third hole color parameter.

[0091] In operation OP62 , the processing device 120 generates a fourth hole color parameter according to the third hole color parameter, the fifth cloth color parameter of the fifth cloth image pixel MX5 in the first cloth image portion MP1 , and the sixth cloth color parameter of the sixth cloth image pixel MX6 in the first cloth image portion MP1 .

[0092] In operation OP63 , the processing device 120 colors the fourth hole image pixel HX4 in the first hole image portion HP1 according to the fourth hole color parameter.

[0093] In operation OP64 , the processing device 120 generates a fifth hole color parameter according to at least the fourth hole color parameter.

[0094] In operation OP65 , the processing device 120 colors the fifth hole image pixel HX5 in the first hole image portion HP1 according to the fifth hole color parameter.

[0095] In some embodiments, the fourth hole image pixel HX4 is located between the fifth hole image pixel HX5 and the sixth fabric image pixel MX6.

[0096] In some embodiments, generating the fifth hole color parameter based on at least the fourth hole color parameter includes generating the fifth hole color parameter based on the fourth hole color parameter, a seventh cloth color parameter of a seventh cloth image pixel MX7 in the first cloth image portion MP1, and an eighth cloth color parameter of an eighth cloth image pixel MX8 in the first cloth image portion MP1.

[0097] In some embodiments, the fourth hole image pixel HX4 and the fifth hole image pixel HX5 are adjacent to the seventh fabric image pixel MX7 and the eighth fabric image pixel MX8, respectively. In the first direction, the fourth hole image pixel HX4 is located between the third hole image pixel HX3 and the seventh fabric image pixel MX7. In the first direction, the fourth hole image pixel HX4 is located between the fifth hole image pixel HX5 and the sixth fabric image pixel MX6.

[0098] Figure 7 According to some embodiments of the present disclosure, Figure 4 Flow chart of other operations of the cloth classification method 400 shown in FIG. Figure 7 As shown, the cloth classification method 400 may further include operations OP71 - OP76 .

[0099] In operation OP71 , the processing device 120 colors the sixth hole image pixel HX6 in the first hole image portion HP1 according to the sixth hole color parameter.

[0100] In operation OP72 , the processing device 120 colors the seventh hole image pixel HX7 in the first hole image portion HP1 according to the seventh hole color parameter.

[0101] In operation OP73 , the processing device 120 colors the eighth hole image pixel HX8 in the first hole image portion HP1 according to the eighth hole color parameter.

[0102] In operation OP74 , the processing device 120 colors the ninth hole image pixel HX9 in the first hole image portion HP1 according to the ninth hole color parameter.

[0103] In operation OP75 , the processing device 120 colors the tenth hole image pixel HX10 in the first hole image portion HP1 according to the tenth hole color parameter.

[0104] In operation OP76 , after coloring the tenth hole image pixel HX10 , the processing device 120 stops coloring the first hole image portion HP1 and outputs a first colored cloth image.

[0105] In some embodiments, the sixth hole image pixel HX6 is adjacent to the first side of the tenth hole image pixel HX10, the seventh hole image pixel HX7 is adjacent to the second side of the tenth hole image pixel HX10, the eighth hole image pixel HX8 is adjacent to the third side of the tenth hole image pixel HX10, and the ninth hole image pixel HX9 is adjacent to the fourth side of the tenth hole image pixel HX10, the first side and the second side are opposite to each other in the first direction, and the third side and the fourth side are opposite to each other in the second direction.

[0106] In some embodiments, when the sixth hole image pixel HX6, the seventh hole image pixel HX7, the eighth hole image pixel HX8, and the ninth hole image pixel HX9 located on the first side, the second side, the third side, and the fourth side of the tenth hole image pixel HX10 are all colored, the processing device 120 can determine that the tenth hole image pixel HX10 is the last hole image pixel in the first hole image portion HP1 that needs to be colored. Correspondingly, after the tenth hole image pixel HX10 is colored, the processing device 120 can determine that the first hole image portion HP1 has been colored, and output the first colored cloth image.

[0107] In summary, the cloth classification method 400 executed by the cloth classification system 100 colors the first hole image portion HP1 according to the first cloth image portion MP1 to eliminate the color difference caused by the hole. Compared with the conventional method, the classification result of the first cloth FB1 in the present disclosure is more accurate.

[0108] Although the present disclosure has been disclosed as above in the form of implementation methods, it is not intended to limit the present disclosure. Anyone with ordinary knowledge in the technical field may make slight changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the scope of protection of the present disclosure shall be determined by the definition of the attached claims.

Claims

1. A method for classifying cloth, characterized in that: Include: photographing a first fabric to generate a first original fabric image; generating a first fabric logic value image according to the first original fabric image; Searching for a first hole image portion in the first original cloth image according to the first cloth logical value image; Coloring the first hole image portion according to a first cloth image portion in the first original cloth image to generate a first colored cloth image; and The first cloth is classified according to the first colored cloth image.

2. The cloth classification method according to claim 1, characterized in that: The first cloth image portion is adjacent to the first hole image portion.

3. The cloth classification method according to claim 1, characterized in that: The coloring of the first hole image portion includes: generating a first hole color parameter of a first hole image pixel in the first hole image portion according to a first cloth color parameter of a first cloth image pixel in the first cloth image portion, a second cloth color parameter of a second cloth image pixel in the first cloth image portion, and a third cloth color parameter of a third cloth image pixel in the first cloth image portion; as well as The first hole image pixel is colored according to the first hole color parameter.

4. The cloth classification method according to claim 3, characterized in that: in The first fabric image pixel is adjacent to the first hole image pixel in a first direction, and is adjacent to the second fabric image pixel in a second direction, The third fabric image pixel is adjacent to the first hole image pixel in the second direction and adjacent to the second fabric image pixel in the first direction, and The first direction is different from the second direction.

5. The cloth classification method according to claim 3, characterized in that: The coloring of the first hole image portion further comprises: After coloring the first hole image pixel according to the first hole color parameter of the first hole image pixel, generating a second hole color parameter of a second hole image pixel in the first hole image portion according to the first hole color parameter, the third fabric color parameter, and a fourth fabric color parameter of a fourth fabric image pixel in the first fabric image portion; and The second hole image pixel is colored according to the second hole color parameter.

6. The cloth classification method according to claim 5, characterized in that: in The first hole image pixel is adjacent to the second hole image pixel in a first direction, and The fourth cloth image pixel is adjacent to the third cloth image pixel in the first direction.

7. The cloth classification method according to claim 6, characterized in that: in The fourth fabric image pixel is adjacent to the second hole image pixel in a second direction, and The first direction is different from the second direction.

8. The cloth classification method according to claim 5, characterized in that: The coloring of the first hole image portion further comprises: Coloring a third hole image pixel in the first hole image portion according to a third hole color parameter; generating a fourth hole color parameter according to the third hole color parameter, a fifth cloth color parameter of a fifth cloth image pixel in the first cloth image portion, and a sixth cloth color parameter of a sixth cloth image pixel in the first cloth image portion; and Coloring a fourth hole image pixel in the first hole image portion according to the fourth hole color parameter; generating a fifth hole color parameter at least according to the fourth hole color parameter; and Coloring a fifth hole image pixel in the first hole image portion according to the fifth hole color parameter, The fourth hole image pixel is located between the fifth hole image pixel and the sixth fabric image pixel.

9. The cloth classification method according to claim 8, characterized in that: The fifth hole color parameter is generated at least according to the fourth hole color parameter, comprising: generating the fifth hole color parameter according to the fourth hole color parameter, a seventh cloth color parameter of a seventh cloth image pixel in the first cloth image portion, and an eighth cloth color parameter of an eighth cloth image pixel in the first cloth image portion, The fourth hole image pixel and the fifth hole image pixel are adjacent to the seventh cloth image pixel and the eighth cloth image pixel respectively.

10. The cloth classification method according to claim 9, characterized in that: Also includes: Coloring a sixth hole image pixel in the first hole image portion according to a sixth hole color parameter; Coloring a seventh hole image pixel in the first hole image portion according to a seventh hole color parameter; Coloring an eighth hole image pixel in the first hole image portion according to an eighth hole color parameter; Coloring a ninth hole image pixel in the first hole image portion according to a ninth hole color parameter; Coloring a tenth hole image pixel in the first hole image portion according to a tenth hole color parameter; as well as After coloring the tenth hole image pixel, stop coloring the first hole image portion and output the first colored cloth image, wherein the sixth hole image pixel is adjacent to a first side of the tenth hole image pixel, The seventh hole image pixel is adjacent to a second side of the tenth hole image pixel, The eighth hole image pixel is adjacent to a third side of the tenth hole image pixel, The ninth hole image pixel is adjacent to a fourth side of the tenth hole image pixel, The first side and the second side are opposite to each other in a first direction, and The third side and the fourth side are opposite to each other in the second direction.

Images