CN114921943A - Cloth cutting method and device based on image recognition and storage medium - Google Patents
Cloth cutting method and device based on image recognition and storage medium Download PDFInfo
- Publication number
- CN114921943A CN114921943A CN202210290567.1A CN202210290567A CN114921943A CN 114921943 A CN114921943 A CN 114921943A CN 202210290567 A CN202210290567 A CN 202210290567A CN 114921943 A CN114921943 A CN 114921943A
- Authority
- CN
- China
- Prior art keywords
- cloth
- image
- gray level
- pixel points
- level difference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06H—MARKING, INSPECTING, SEAMING OR SEVERING TEXTILE MATERIALS
- D06H7/00—Apparatus or processes for cutting, or otherwise severing, specially adapted for the cutting, or otherwise severing, of textile materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Textile Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image recognition, and discloses a cloth cutting method, a cloth cutting device and a storage medium based on image recognition, wherein the cloth cutting method comprises the following steps: the controller collects images of the cloth to be distributed shot by the camera device in real time; performing cloth feature recognition on the cloth image, and outputting a feature recognition result; if the characteristic identification result is the sewing head, triggering a counter to calculate the moving distance of the sewing head according to the pulse signal output by the encoder; and when the moving distance reaches a preset distance threshold value, controlling the cloth cutting mechanism to execute cloth cutting operation. The cloth cutting mechanism comprises a cloth cutting mechanism, a cloth image acquisition unit, a cloth image recognition unit, a cloth cutting unit and a cloth cutting unit, wherein the cloth cutting mechanism is used for acquiring the cloth image, then carrying out feature recognition on the cloth image, judging whether a feature recognition result is a seam head, if so, calculating the moving distance of the seam head, and when the moving distance of the seam head reaches a preset threshold value, the cloth cutting mechanism carries out cutting operation. The method realizes the operation of automatically identifying and cutting the cloth, realizes automatic operation, and has the advantages of high cutting accuracy and high cutting speed.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a cloth cutting method and device based on image recognition and a storage medium.
Background
The setting machine is widely applied in the textile industry, but when each piece of cloth is distinguished after the cloth is produced and set, the cloth needs to be cut off by taking a seam as a boundary.
In the prior art, judgment is usually carried out through human eyes, however, the human eyes recognize that wrong cutting exists, and in the production process of the setting machine, a person cannot be too close to cloth, so that defects such as creases and the like can be used as sewing heads when the person looks at the sewing heads, and the human eyes can miss the sewing heads to cause missed cutting when the person looks at the sewing heads. In addition, the setting machine is continuously produced, so that the distance of the sewing head can only be roughly judged when the cloth is manually cut, the sewing head cannot be accurately cut, and certain distance errors exist.
Disclosure of Invention
The invention mainly aims to solve the problem of cloth cutting accuracy in setting machine equipment.
The invention provides a cloth cutting method based on image recognition, which is applied to cloth cutting equipment, wherein the cloth cutting equipment comprises a controller, a camera device, a counter, an encoder and a cloth cutting mechanism, and the cloth cutting method comprises the following steps:
the controller collects the image of the piece goods to be distributed shot by the camera device in real time;
performing cloth feature recognition on the cloth image, and outputting a feature recognition result;
if the characteristic identification result is a seam head, triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder;
and when the moving distance reaches a preset distance threshold value, controlling the cloth cutting mechanism to execute cloth cutting operation.
Optionally, the performing of the piece goods feature recognition on the piece goods image, and outputting a feature recognition result includes:
the controller converts the cloth image into a plurality of gray level images with brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range, and correspondingly obtaining a plurality of gray level differences;
and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the feature recognition result based on the first number.
Optionally, the performing of the piece goods feature recognition on the piece goods image, and outputting a feature recognition result includes:
the controller converts the cloth image into a plurality of gray level images with brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences;
comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference;
classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale;
displaying pixel points of the cloth images higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth images lower than the preset gray scale as black pixel points;
removing rough parts in the cloth images;
expanding the black pixel points in the cloth image into a line;
and determining and outputting the feature recognition result based on the second quantity and the parameters of the black pixel points.
Optionally, the removing the rough part in the cloth image includes: and displaying the high-frequency domain of the cloth image, binarizing the cloth image, and removing the rough part.
Optionally, the parameter includes one or more of an arrangement angle of the black pixel, a length of the black pixel, a width of the black pixel, and a number of the black pixels.
Optionally, the increasing the contrast of the grayscale image includes: and multiplying the gray value of the pixel point of the cloth image by a preset coefficient to enhance the contrast of the gray image.
Correspondingly, still provide a fabric cutting equipment based on image recognition, fabric cutting equipment includes controller, camera device, counter, encoder and fabric cutting mechanism, the controller includes:
the acquisition module is used for acquiring the image of the piece goods to be distributed, which is shot by the camera device, in real time;
the identification module is used for carrying out cloth feature identification on the cloth image and outputting a feature identification result;
the calculating module is used for triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder if the characteristic identification result is the seam head;
and the control module is used for controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance reaches a preset distance threshold value.
Optionally, the identification module is specifically configured to:
converting the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences;
and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the characteristic identification result based on the first number.
Optionally, the identification module is specifically configured to:
converting the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range, and correspondingly obtaining a plurality of gray level differences;
comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference;
classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale;
displaying pixel points of the cloth image higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth image lower than the preset gray scale as black pixel points;
removing rough parts in the cloth image;
expanding the black pixel points in the cloth image into a line;
and determining and outputting the feature recognition result based on the second quantity and the parameters of the black pixel points.
Accordingly, a computer-readable storage medium is also provided, which has instructions stored thereon, and when executed by a processor, implements the image recognition-based cropping method described above.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the cloth image is obtained, then the feature recognition is carried out on the cloth image, whether the feature recognition result is a seam head or not is judged, if yes, the moving distance of the seam head is calculated, and when the moving distance of the seam head reaches a preset threshold value, the cloth cutting mechanism executes the cutting operation. The method realizes the operation of automatically identifying and cutting the cloth, realizes automatic operation, and has the advantages of high cutting accuracy and high cutting speed.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a cloth cutting method based on image recognition in the embodiment of the invention;
FIG. 2 is a schematic diagram of a second embodiment of a cloth cutting method based on image recognition in the embodiment of the present invention;
FIG. 3 is a diagram of a third embodiment of a cloth cutting method based on image recognition according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a fourth embodiment of a cloth cutting method based on image recognition in the embodiment of the invention;
FIG. 5 is a schematic diagram of an embodiment of a cloth cutting device based on image recognition in the embodiment of the present invention;
fig. 6 is a schematic diagram of a cutting line controller based on image recognition in the embodiment of the present invention.
Reference numerals:
100-a controller; 110-an acquisition module; 120-an identification module; 130-a calculation module; 140-a control module; 200-a camera device; 210-a first camera; 211-a first light source; 220-a second camera; 221-a second light source; 300-an encoder; 400-a cloth cutting mechanism; 500-a frame; 600-piece goods.
Detailed Description
The embodiment of the invention provides a cloth cutting method and device based on image recognition and a storage medium. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the cloth cutting method based on image recognition is shown in fig. 1, and is applied to a cloth cutting device, wherein the cloth cutting device comprises a controller, an image pickup device, a counter, an encoder and a cloth cutting mechanism, and the cloth cutting method comprises the following steps:
s10, the controller collects the image of the cloth to be distributed shot by the camera device in real time
Specifically, the camera device collects images of the front side and the back side of the cloth in real time, and the sewing head of the cloth can be arranged on the front side of the cloth or on the back side of the cloth, so that the missing of the sewing head caused by the wrong judgment can be avoided by obtaining the images of the front side and the back side of the cloth.
S20, performing cloth feature recognition on the cloth image, and outputting a feature recognition result
Specifically, the controller performs cloth feature recognition on the acquired cloth image, judges whether the cloth image is a seam head, and outputs a corresponding feature recognition result. In addition, when the characteristic identification is carried out on the cloth image, the image is preprocessed, so that the pixelation processing is carried out on the cloth image, the definition of the cloth image is improved, or the interference information of the cloth image is reduced.
S30, if the characteristic recognition result is the seam head, triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder
Specifically, if the controller identifies the acquired cloth image as a seam head and outputs a seam head result to the counter, the counter is triggered to calculate the moving distance of the seam head according to the pulse signal output by the encoder. For example, when the counter counts 1, the seam head is passed, and the controller sets the first seam head to cut off, therefore when the counter counts 1, the counter calculates the moving distance of the seam head according to the pulse signal sent by the encoder.
And S40, controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance reaches a preset distance threshold value.
Specifically, the distance from the sewing head to the cloth cutting mechanism is reduced as the moving distance of the sewing head is increased, and when the moving distance of the sewing head meets a preset distance threshold value, namely the distance close to the cloth cutting mechanism meets a certain condition, the controller controls the cloth cutting mechanism to execute cloth cutting operation.
In this embodiment, the performing the cloth feature recognition on the cloth image, and outputting the feature recognition result includes: the controller converts the cloth image into gray level images with a plurality of brightness levels; increasing the contrast of the grayscale image; dividing the gray level image into a plurality of detection ranges vertically; calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences; and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the feature recognition result based on the first number.
Specifically, the controller may convert the cloth image into an 8-bit gray image with 256 brightness levels, vertically divide the image into 4 detection ranges, extract the highest and lowest gray levels in the 4 detection ranges, and subtract the extracted gray levels to obtain 4 gray level differences. A standard gray difference (i.e., a predetermined gray difference) is set as a conditional judgment, for example, when 3 gray differences out of 4 gray differences are higher than the standard gray difference, it is indicated that a seam head passes through, and the seam head is output as a feature recognition result.
In this embodiment, the performing the cloth feature recognition on the cloth image, and outputting a feature recognition result includes: the controller converts the cloth image into a plurality of gray level images with brightness levels; increasing the contrast of the grayscale image; dividing the gray level image into a plurality of detection ranges vertically; calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences; comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference; classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale; displaying pixel points of the cloth image higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth image lower than the preset gray scale as black pixel points; removing rough parts in the cloth image; expanding the black pixel points in the cloth image into a line; and determining the feature recognition result based on the second quantity and the parameters of the black pixel points and outputting the feature recognition result.
Specifically, all pixel points of the cloth image are classified according to 256 gray scales, each pixel point represents one gray scale, then pixel points higher than a certain gray scale are displayed as white pixel points, pixel points lower than a certain gray scale display black pixel points, parameters of the black pixel points are judged, namely the arrangement angles, the lengths and the widths of the black pixel points and the number of the black pixel points are judged to identify seams and output as characteristic identification results. The Fourier transform algorithm is adopted to display the high-frequency domain of the cloth picture, and then binaryzation is used for filtering the interference of rough cloth, so that the misjudgment can be reduced. And (3) by adopting morphological image processing, the black pixels after binarization are expanded and then connected into a line, so that the missing judgment of the cloth image caused by crease breakage at the seam head is reduced. The embodiment combines two judging modes, and the seam head can be judged more accurately.
In this embodiment, the parameter includes one or more of an arrangement angle of the black pixels, a length of the black pixels, a width of the black pixels, or a number of the black pixels.
In this embodiment, the controller enhances the contrast of the cloth image by multiplying the gray value of each pixel point in the cloth image by a coefficient. The coefficients can be selected according to actual needs.
Correspondingly, the embodiment of the cloth cutting device based on image recognition is provided.
This embodiment includes controller, camera device, counter, encoder and fabric cutting mechanism, the controller includes: the acquisition module is used for acquiring an image of the cloth to be distributed, which is shot by the camera device, in real time; the identification module is used for carrying out cloth feature identification on the cloth image and outputting a feature identification result; the calculating module is used for triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder if the characteristic identification result is the seam head; and the control module is used for controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance reaches a preset distance threshold value.
Specifically, the identification module is specifically configured to: converting the cloth image into gray level images with a plurality of brightness levels; increasing the contrast of the grayscale image; dividing the gray level image into a plurality of detection ranges vertically; calculating the gray level difference of each detection range, and correspondingly obtaining a plurality of gray level differences; and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the characteristic identification result based on the first number.
Specifically, the identification module is specifically configured to: converting the cloth image into gray level images with a plurality of brightness levels; increasing the contrast of the grayscale image; dividing the gray level image into a plurality of detection ranges vertically; calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences; comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference; classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale; displaying pixel points of the cloth images higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth images lower than the preset gray scale as black pixel points; removing rough parts in the cloth image; expanding the black pixel points in the cloth image into a line; and determining and outputting the feature recognition result based on the second quantity and the parameters of the black pixel points.
For the sake of understanding, the following describes a specific flow of an embodiment of the present invention, and referring to fig. 2, a second embodiment of the fabric cutting method in an embodiment of the present invention includes:
s101, a controller collects an image of the cloth to be distributed, which is shot by a camera device in real time;
s102, multiplying the gray value of each pixel point in the cloth image by a coefficient to enhance the contrast of the cloth image;
s103, converting the cloth image into an 8-bit gray image with 256 brightness levels, vertically dividing the image into 4 detection ranges, extracting the highest gray and the lowest gray in the 4 detection ranges, and subtracting to obtain 4 gray differences;
s104, comparing the 4 gray level differences with the standard gray level difference, counting the number of the gray level differences larger than the standard gray level difference, and when 3 gray level differences in the 4 gray level differences are higher than the standard gray level difference, indicating that a seam head passes through;
s105, if the seam head passes through the detection device, triggering a counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder;
and S106, controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance of the sewing head reaches a preset distance threshold value.
Referring to fig. 3, a third embodiment of the fabric cutting method according to the embodiment of the present invention includes:
s201, a controller collects an image of the cloth to be distributed, which is shot by a camera device in real time;
s202, multiplying the gray value of each pixel point in the cloth image by a coefficient to enhance the contrast of the cloth image;
s203, classifying all pixel points of the cloth image according to 256 gray scales, wherein each pixel point represents one gray scale, displaying the pixel points higher than a certain gray scale as white pixel points, and displaying the pixel points lower than the certain gray scale as black pixel points;
s204, displaying a high-frequency domain of the cloth picture by adopting a Fourier transform algorithm, and filtering the interference of rough cloth by using binarization so as to reduce erroneous judgment;
s205, adopting morphological image processing to enable the black pixels after binarization to be expanded and then connected into a line, thereby reducing the missing judgment of the cloth image caused by crease fracture at the seam head;
s206, judging parameters of the black pixels, namely judging the arrangement angle, the length and the width of the black pixels and the number of the black pixels to identify the seam head;
s207, if the seam head passes through, triggering a counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder;
and S208, when the moving distance of the sewing head reaches a preset distance threshold value, controlling the cloth cutting mechanism to execute cloth cutting operation.
Referring to fig. 4, a fourth embodiment of the fabric cutting method according to the embodiment of the present invention includes:
s301, a controller collects an image of the cloth to be distributed, which is shot by a camera device in real time;
s302, multiplying the gray value of each pixel point in the cloth image by a coefficient to enhance the contrast of the cloth image;
s303, converting the cloth image into an 8-bit gray image with 256 brightness levels, vertically dividing the image into 4 detection ranges, extracting the highest and lowest gray in the 4 detection ranges, and subtracting to obtain 4 gray differences;
s304, comparing the 4 gray level differences with the standard gray level difference, counting the number of the gray level differences larger than the standard gray level difference, and preliminarily judging that a seam passes through when 3 gray level differences in the 4 gray level differences are higher than the standard gray level difference;
s305, when the seam is judged to pass through preliminarily, classifying all pixel points of the cloth image according to 256 gray scales, wherein each pixel point represents one gray scale, displaying the pixel points higher than the certain gray scale as white pixel points, and displaying the pixel points lower than the certain gray scale as black pixel points;
s306, displaying a high-frequency domain of the cloth picture by adopting a Fourier transform algorithm, and filtering the interference of rough cloth by using binarization so as to reduce erroneous judgment;
s307, adopting morphological image processing to enable the black pixels after binarization to be expanded and then connected into a line, thereby reducing the missing judgment of the cloth image caused by crease fracture of the seam head;
s308, judging parameters of the black pixels, namely judging the arrangement angle, the length and the width of the black pixels and the number of the black pixels to assist in identifying the seam head;
s309, if the sewing head passes through is finally judged, the counter is triggered to calculate the moving distance of the sewing head according to the pulse signal output by the encoder;
and S310, controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance of the sewing head reaches a preset distance threshold.
Compared with the embodiment, the embodiment can more accurately identify the seam head and avoid misjudgment.
With reference to fig. 5, the cloth cutting method in the embodiment of the present invention is described above, and the cloth cutting apparatus in the embodiment of the present invention is described below, where an embodiment of the cloth cutting apparatus in the embodiment of the present invention includes: a controller 100, a camera 200, a counter (not shown), an encoder 300, a cloth cutting mechanism 400, and a frame 500.
Specifically, the camera device 200 is an industrial camera having an industrial lens, the camera device 200 specifically includes a first camera 210 and a second camera 220, the first camera 210 and the second camera 220 are respectively located above and below the cloth 600 and are used for acquiring cloth images and transmitting the cloth images to the controller 100, the two cameras have two sets of upward and downward vision systems, and the seam head can be effectively detected upward or downward, so that missing judgment is avoided.
Correspondingly, the camera further comprises a first light source 211 and a second light source 221 which are respectively arranged corresponding to the first camera 210 and the second camera 220, and are used for providing illumination of the cameras and improving the image pickup quality.
The encoder 300 is disposed in a rotating shaft of the cloth conveying mechanism and used for sending out a pulse signal, and when the rotating shaft rotates by a preset angle, the encoder 300 correspondingly sends out the pulse signal. When the controller 100 judges that the stitch is detected, the counter starts to count the number of pulses given to the counter by the encoder 300, and when the number reaches a specified distance, the software gives a 24V voltage switch signal to the cloth cutting device through the analog-digital I/0 box.
The controller 100 is configured to process the cloth image and other related data, and send a control instruction, and the controller 100 may be a computer. The cloth cutting mechanism 400 performs a cloth cutting operation according to the control command.
Further, as shown in fig. 6, the controller 100 includes an acquisition module 110, a recognition module 120, a calculation module 130, and a control module 140. The acquisition module 110 is in communication with the camera device 200, and the acquisition module 110 is used for acquiring an image of the piece to be distributed, which is shot by the camera device 200 in real time; the recognition module 120 is respectively connected with the acquisition module 110 and the calculation module 130, and the recognition module 120 is used for performing cloth feature recognition on the cloth image and outputting a feature recognition result; the calculation module 130 is further connected to the control module 140, and the calculation module 130 is configured to trigger the counter to calculate a moving distance of the seam head according to the pulse signal output by the encoder 100 if the feature recognition result is the seam head; the control module 140 is further connected to the cloth cutting mechanism 400, and the control module 140 is configured to control the cloth cutting mechanism 400 to perform a cloth cutting operation when the moving distance of the sewing head reaches a preset distance threshold.
This embodiment sets up in the front end of putting the cloth structure in forming machine exit, and a plurality of cameras cooperation industrial lens under the shining of low angle light source, the seam head of monitoring cloth of shooing has two sets of visual system up and down with two cameras, and the seam head can both effectively detect down and obtain up. When the camera shoots the seam head of the cloth, the software of the computer can analyze the picture and then trigger the counter to start counting, and the counter can calculate the distance from the seam head to the cloth cutting device through the pulse given by the encoder on the rolling shaft. When the distance of the counter reaches the designated number, software gives a trigger signal to the cloth cutting device through a digital analog I/O signal, and the cloth cutting device can accurately reach the position of the sewing head.
The automatic cloth cutting device can realize the automatic cloth identification and automatic cloth cutting operation, realizes automatic operation, and has the advantages of high cutting accuracy and high cutting speed.
The invention also provides a computer readable storage medium embodiment, and the computer readable storage medium stores instructions which, when executed by a processor, implement the cloth cutting method based on image recognition.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The cloth cutting method based on image recognition is applied to cloth cutting equipment, the cloth cutting equipment comprises a controller, a camera device, a counter, an encoder and a cloth cutting mechanism, and the cloth cutting method is characterized by comprising the following steps:
the controller collects images of the cloth to be distributed shot by the camera device in real time;
performing cloth feature recognition on the cloth image, and outputting a feature recognition result;
if the characteristic identification result is a seam head, triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder;
and when the moving distance reaches a preset distance threshold value, controlling the cloth cutting mechanism to execute cloth cutting operation.
2. The image recognition-based cloth cutting method according to claim 1, wherein the performing cloth feature recognition on the cloth image and outputting a feature recognition result comprises:
the controller converts the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences;
and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the feature recognition result based on the first number.
3. The image recognition-based cloth cutting method according to claim 1, wherein the performing cloth feature recognition on the cloth image and outputting a feature recognition result comprises:
the controller converts the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences;
comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference;
classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale;
displaying pixel points of the cloth image higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth image lower than the preset gray scale as black pixel points;
removing rough parts in the cloth image;
expanding the black pixel points in the cloth image into a line;
and determining and outputting the feature recognition result based on the second quantity and the parameters of the black pixel points.
4. The cloth cutting method based on image recognition according to claim 3, wherein the removing of the rough parts in the cloth image comprises revealing a high-frequency domain of the cloth image, binarizing the cloth image, and removing the rough parts.
5. The image recognition-based cloth cutting method according to claim 3, wherein the parameters include one or more of an arrangement angle of the black pixels, a length of the black pixels, a width of the black pixels, and a number of the black pixels.
6. The image-recognition-based cropping method according to any one of claims 2 to 5, wherein the increasing the contrast of the grayscale image comprises: and multiplying the gray value of the pixel point of the cloth image by a preset coefficient to enhance the contrast of the gray image.
7. The utility model provides a fabric cutting equipment based on image recognition, fabric cutting equipment includes controller, camera device, counter, encoder and fabric cutting mechanism, its characterized in that, the controller includes:
the acquisition module is used for acquiring the image of the piece goods to be distributed, which is shot by the camera device, in real time;
the identification module is used for carrying out cloth feature identification on the cloth image and outputting a feature identification result;
the calculating module is used for triggering the counter to calculate the moving distance of the seam head according to the pulse signal output by the encoder if the characteristic identification result is the seam head;
and the control module is used for controlling the cloth cutting mechanism to execute cloth cutting operation when the moving distance reaches a preset distance threshold value.
8. The image recognition-based cloth cutting device according to claim 7, wherein the recognition module is specifically configured to:
converting the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range to correspondingly obtain a plurality of gray level differences;
and comparing the gray level difference with a preset gray level difference, counting a first number of gray level differences larger than the preset gray level difference, and determining and outputting the characteristic identification result based on the first number.
9. The image recognition-based cloth cutting device according to claim 7, wherein the recognition module is specifically configured to:
converting the cloth image into gray level images with a plurality of brightness levels;
increasing the contrast of the grayscale image;
dividing the gray level image into a plurality of detection ranges vertically;
calculating the gray level difference of each detection range, and correspondingly obtaining a plurality of gray level differences;
comparing the gray level difference with a preset gray level difference, and counting a second number of gray level differences larger than the preset gray level difference;
classifying the pixel points of the cloth images according to gray scales, wherein the pixel point of each cloth image corresponds to one gray scale;
displaying pixel points of the cloth image higher than a preset gray scale as white pixel points, and displaying pixel points of the cloth image lower than the preset gray scale as black pixel points;
removing rough parts in the cloth images;
expanding the black pixel points in the cloth image into a line;
and determining and outputting the feature recognition result based on the second quantity and the parameters of the black pixel points.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the image recognition-based cropping method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290567.1A CN114921943A (en) | 2022-03-23 | 2022-03-23 | Cloth cutting method and device based on image recognition and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290567.1A CN114921943A (en) | 2022-03-23 | 2022-03-23 | Cloth cutting method and device based on image recognition and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114921943A true CN114921943A (en) | 2022-08-19 |
Family
ID=82805057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210290567.1A Pending CN114921943A (en) | 2022-03-23 | 2022-03-23 | Cloth cutting method and device based on image recognition and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114921943A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202770781U (en) * | 2012-09-05 | 2013-03-06 | 西安工程大学 | Fabric defect online detection device based on machine vision |
| CN106919933A (en) * | 2017-03-13 | 2017-07-04 | 重庆贝奥新视野医疗设备有限公司 | The method and device of Pupil diameter |
| EP3327627A1 (en) * | 2016-11-26 | 2018-05-30 | MEWA Textil-Service AG & Co Management oHG | Method, apparatus and computer program for visual quality control of textiles |
| CN109176668A (en) * | 2018-07-25 | 2019-01-11 | 长沙慧联智能科技有限公司 | A kind of detection segmenting system and method based on machine vision |
-
2022
- 2022-03-23 CN CN202210290567.1A patent/CN114921943A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202770781U (en) * | 2012-09-05 | 2013-03-06 | 西安工程大学 | Fabric defect online detection device based on machine vision |
| EP3327627A1 (en) * | 2016-11-26 | 2018-05-30 | MEWA Textil-Service AG & Co Management oHG | Method, apparatus and computer program for visual quality control of textiles |
| CN106919933A (en) * | 2017-03-13 | 2017-07-04 | 重庆贝奥新视野医疗设备有限公司 | The method and device of Pupil diameter |
| CN109176668A (en) * | 2018-07-25 | 2019-01-11 | 长沙慧联智能科技有限公司 | A kind of detection segmenting system and method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112348773B (en) | Screen defect detection method and device and electronic equipment | |
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| US8243166B2 (en) | Automatic detection of blocked field-of-view in camera systems | |
| JP3123587B2 (en) | Moving object region extraction method using background subtraction | |
| US7936926B2 (en) | Apparatus, method, and program for face feature point detection | |
| JP4307496B2 (en) | Facial part detection device and program | |
| CN110738135A (en) | worker work step specification visual identification judgment and guidance method and system | |
| CN110018172B (en) | Product detection system and method | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| KR102322546B1 (en) | Sewing stitching defect detection method and system | |
| GB2610734A (en) | Barcode readers with 3D camera(s) | |
| EP2618136A1 (en) | Gob inspection system for glass product | |
| CN113808087A (en) | Defect management and control method and device for surface of steel plate and computer readable storage medium | |
| CN106093051A (en) | Paper roll tangent plane burr detection method based on machine vision and device | |
| CN113111903A (en) | Intelligent production line monitoring system and monitoring method | |
| JP6630341B2 (en) | Optical detection of symbols | |
| CN108133479B (en) | Automatic spinning machine drawing-in monitoring method and device | |
| CN113189005B (en) | Portable surface defect integrated detection device and surface defect automatic detection method | |
| CN111028209B (en) | Telephone silk-screen quality detection method and system | |
| CN114921943A (en) | Cloth cutting method and device based on image recognition and storage medium | |
| CN109257594B (en) | Television delivery detection method and device and computer readable storage medium | |
| CN116840240A (en) | Visual detection system of power supply distributor | |
| CN110672209A (en) | Online detection method for warp knitting cloth color difference | |
| JP2005241304A (en) | Appearance inspection method | |
| CN109035236B (en) | Casting burr detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |