ARTIFICIAL INTELLIGENCE-BASED LEATHER INSPECTION METHOD AND LEATHER PRODUCT PRODUCTION METHOD

Abstract

An artificial intelligence-based leather inspection method and leather product production method includes the step of using sensor means to obtain a leather data of a leather raw material, then the step of inputting the leather data to an artificial intelligence module to determine a defective area and a non-defective area of the leather raw material, the step of establishing an area data after judgment of the defective area and the non-defective area and then using the area data to define the non-defective area into one or multiple reserved areas so that the leather raw material can be cut into leather components corresponding to the respective reserved areas.

Claims

1. An artificial intelligence-based leather inspection method comprising the steps of: (a): using sensor means to obtain a leather data of a leather raw material; and (b): inputting said leather data to an artificial intelligence module to determine a defective area and a non-defective area of said leather raw material.

2. The artificial intelligence-based leather inspection method as claimed in claim 1, wherein the step (a) is to obtain local leather data of said leather raw material at different locations, and then to integrate all the local leather data into said leather data of said leather raw material.

3. The artificial intelligence-based leather inspection method as claimed in claim 1, further comprising a sub step of establishing an area data after judgment of said defective area and said non-defective area, and then using said area data to define said non-defective area into at least one reserved area.

4. The artificial intelligence-based leather inspection method as claimed in claim 1, wherein said artificial intelligence module comprises a deep learning model.

5. The artificial intelligence-based leather inspection method as claimed in claim 1, wherein sensor means used in the step (a) is an image sensor for capturing an image of said leather raw material to obtain said leather data.

6. The artificial intelligence-based leather inspection method as claimed in claim 5, wherein said sensor means is used in the step (a) to obtain local leather data of said leather raw material at different locations, and then to integrate all the local leather data into said leather data of said leather raw material.

7. The artificial intelligence-based leather inspection method as claimed in claim 5, wherein said sensor means is used in the step (a) to obtain local leather data of said leather raw material by means of projecting a light source onto said leather raw material, the lighting characteristics of said light source being adjustable according to the material characteristics of said leather raw material.

8. A leather product production method, comprising the steps of: (a): employing the artificial intelligence-based leather inspection method as claimed in claim 1 to inspect a leather raw material; and (b): cutting said leather raw material to obtain leather components corresponding to the defective area and the non-defective area of said leather raw material.

9. The leather product production method as claimed in claim 8, wherein the step (b) of cutting said leather raw material to obtain leather components is performed according to claim 3 to obtain leather components corresponding to said at least one reserved area.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] FIG. 1 is a system architecture block diagram of the present invention.

[0013] FIG. 2 is a schematic drawing of the present invention, illustrating one implementation example of the leather data collection device.

[0014] FIG. 3 is a schematic drawing of the present invention, illustrating another implementation example of the leather data collection device.

[0015] FIG. 4 is a schematic drawing illustrating the configuration of the leather inspection platform.

[0016] FIG. 5 corresponds to FIG. 4, illustrating a leather raw material placed on the leather inspection platform.

[0017] FIG. 6 is a schematic drawing illustrating detective areas of the leather raw material.

[0018] FIG. 7 is a schematic drawing illustrating the non-detective areas of the leather raw material after typesetting.

[0019] FIG. 8 is a schematic drawing illustrating the leather raw material cut into leather components.

DETAILED DESCRIPTION OF THE INVENTION

[0020] Prior to viewing the following specification in conjunction with the accompanying drawings, it is to be understood that the artificial intelligence-based leather inspection method and leather product production method of the present invention can be widely used to inspect various types or surface treatments of natural leather or synthetic leather. Those skilled in the art should be able to understand that the artificial intelligence, the operating instructions, and the operating steps in the present preferred embodiment are all superordinated descriptions that do not limit the specific calculus model, the technical field, or the operation sequence. And for the quantitative term a is meant to include one and more than a plurality of components

[0021] Referring to FIGS. 1-4, an artificial intelligence-based leather inspection method comprises the steps of (A) data collection, (B) data processing, and (C) generation of process data.

[0022] In Step (A) of data collection, place a leather raw material 10 on a leather inspection platform 12, and then use a leather data collecting device 14 in the leather inspection platform 12 to obtain the leather data of the leather raw material 10. In the present preferred embodiment, the leather raw material 10 is a natural leather, however, this step is also applicable to other kinds of leathers. In the present preferred embodiment, the leather data collecting device 14 is an optical sensor device adapted for photographing the surface of the leather raw material 10 to obtain a digital image of the leather surface so as to further form leather data for judging the edge and surface state of the leather raw material 10.

[0023] As shown in FIG. 2, the leather data collecting device 14 comprises a plurality of sensor components 16 that are arranged in an array and evenly distributed over the leather raw material 10. Each of the sensor components 16 obtains local leather data of the leather raw material 10 at different locations. The leather data collecting device 14 further comprises a light source 17 adapted to emit light onto the leather raw material 10 for enabling the sensor components 16 to obtain complete digital leather data. The light source 17 can be a point light source or an array light source. In order to cooperate with the material types, different material treatments or different leather raw material surface textures, the light source 17 can project different illumination characteristics according to the material characteristics of different leather raw materials 10, that is, the intensity, illuminance, or brightness of the light source can be adjusted with the leather raw material 10 to be inspected.

[0024] In Step (B) of data processing, as shown in FIG. 4 and FIG. 5, after the leather raw material 10 is placed flat on the leather inspection platform 12 and the leather data is obtained from the leather data collecting device 14 above the leather inspection platform 12, input the leather data into a leather data processing device 18 for calculation procedures. In the present preferred embodiment, the leather data processing device 18 comprises at least one image processing module for splicing and integrating the local leather data obtained by the leather data collecting device 14 into complete leather data.

[0025] The leather data processing device 18 further comprises an artificial intelligence module 20. The artificial intelligence module 20 of the present preferred embodiment is an example including a deep learning model for calculating and judging the defective area 22 and the non-defective area 24 of the surface of the leather raw material 10.

[0026] In step (C) of generation of process data, as shown in FIG. 1 and FIGS. 6-8, use a typesetting module 30 to establish the area data of the leather raw material 10 after judgment of the defective area 22 and the non-defective area 24 of the surface of the leather raw material 10 by the artificial intelligence module 20 of the leather data processing device 18, and then use the area data to define the non-defective area 24 into at least one reserved area 32. In the subsequent leather product production method, the leather raw material 10 is cut by a cutting device 40 to produce at least one leather component 50 corresponding to the at least one reserved area 32.

[0027] Based on the aforesaid artificial intelligence-based leather inspection method and leather product production method, the present invention has at least the following technical effects:

[0028] 1. Using the artificial intelligence module with deep learning model, you can judge the defects of leather without manual, greatly reducing leather inspection time.

[0029] 2. The invention can quickly complete the inspection without considering the inspection environment, time or human factors, and establish a consistent and universal leather quality inspection standard.

[0030] 3. The leather inspection method is combined with the subsequent typesetting and cutting process to improve the utilization of the raw material is improved.

[0031] 4. The invention can integrate the leather raw material quality inspection into the subsequent cutting process to realize the automatic production process of the leather product.

[0032] It is worth mentioning that the above-mentioned leather data collecting device can also obtain the internal organization or material state of the leather raw material by using a device to produce a collapse effect on leather raw material by means of transmission or mechanical force. For example, use an X-ray device to irradiate X-rays to the leather raw material, and then analyze the X-ray signal thus obtained to find out the characteristics of the inner organization of the leather raw material.

[0033] As shown in FIG. 3, the leather data collecting device 14 can scan the leather surface of the leather raw material 10 to obtain the desired leather data when the leather raw material 10 is moving along with a conveyor belt 13 over the leather inspection platform 12, thereby improving the overall inspection and production efficiency.

[0034] Further, in addition to the deep learning model, the artificial intelligence module can use other machine learning models such as neural network models, convolutional network models, or cyclic neural network models to enhance the accuracy and precision of artificial intelligence.