Systems and method for textile fabric definition
Disclosed herein are systems and methods that allow an image of a fabric sample to be captured. The image may be analyzed to extract features, sometimes referred to as a stitch parameter, of the fabric's construction, such the use of one or more stitch types. Using the stitch parameters, a build specification can be selected from a plurality of build specification. Each of the plurality of build specifications may be associated with at least one of a plurality of known fabric constructions. The build specification may be exported and then used to construct a fabric similar to the fabric sample captured in the received image.
1. A method for analyzing a fabric to determine a construction thereof. the method comprising:
receiving a digital image of at least a portion of a fabric sample;
using a computer-based process, performing an image analysis using digital image processing technology to identify stitch parameters from the digital image, wherein the stitch parameters include determining of: a stitch type, a courses per inch parameter a wales per inch parameter and/or a yarn thickness for at least one strand of yarn;
comparing identified stitch parameters to parameters stored in a database of a plurality of digital build specifications, each of the plurality of digital build specifications associated with at least one of a plurality of known fabric constructions; associating one or more fabrics with the digital image based on the comparing; and
generating a digital build specification that is based at least partly on a loop map that is a sequence of stitch types, wherein the digital build specification objectively identifies the construction of the portion of the fabric sample for further use including for: search by fabric designers, digital export as a file for use in setting up a fabric knitting machine, and construction of the fabric at another location.
2. The method of claim 1 , wherein the stitch type includes at least one of a knit stitch, a tuck stitch, and a miss stitch.
3. The method of claim 1 , wherein the comparing is performed by a machine learning model by mapping the stitch parameters to a variable of the machine learning model.
4. The method of claim 3 , wherein the machine learning model is trained using at least a first subset of training images with a known fabric construction.
5. The method of claim 1 , wherein performing the image analysis includes image subtracting utilizing the digital image of the fabric sample and an image of a known fabric sample.
6. The method of claim 1 , wherein performing the image analysis includes extracting a vertical and horizontal dimension from the digital image of the fabric sample.
7. The method of claim 1 , further comprising exporting the digital build specification for use in setting up the fabric knitting machine.
8. The method of claim 1 , further comprising constructing the fabric based on the digital build specification.
9. A system for digitizing a construction of a fabric, the system comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform actions comprising:
receive a digital image of the fabric,
perform an image analysis using digital image processing technology to identify stitch parameters from the digital image, wherein the stitch parameters include determining of: a stitch type, a courses per inch parameter, a wales per inch parameter and/or a yarn thickness for at least one strand of yarn,
compare identified stitch parameters to parameters stored in a database of a plurality of digital build specifications, each of the plurality of digital build specifications associated with at least one of a plurality of known fabric constructions,
associate one or more fabrics with the digital image based on the identified stitch parameters, and
generate a digital build specification or select the digital build specification from the plurality of digital build specifications using the stitch parameters, wherein digital build specification is based at least partly on a loop map that is a sequence of stitch types, wherein the digital build specification objectively identifies the construction of the fabric for further use including for: search by fabric designers, digital export as a file for use in setting up a fabric knitting machine, and construction of the fabric at another location.
10. The system of claim 9 , wherein the the digital build specification includes using a machine learning model to map the stitch parameters.
11. A method for analyzing a fabric to determine a construction thereof, the method comprising:
receiving a digital image of at least a portion of a fabric sample;
using a computer-based process, performing an image analysis using digital image processing technology to identify stitch parameters from the digital image, wherein the stitch parameters include determining of: a stitch type, a courses per inch parameter, a wales per inch parameter and a yarn thickness for at least one strand of yarn;
comparing identified stitch parameters to parameters stored in a database of a plurality of digital build specifications, each of the plurality of digital build specifications associated with at least one of a plurality of known fabric constructions;
associating one or more fabrics with the digital image based on the comparing; and
generating a digital build specification that is based at least partly on a loop map that is a sequence of stitch types, wherein the digital build specification objectively identifies the construction of the portion of the fabric sample for further use including for: search by fabric designers, digital export as a file for use in setting up a fabric knitting machine, and/or construction of the fabric at another location.
12. The method of claim 11 , wherein the stitch type includes at least one of a knit stitch, a tuck stitch, and a miss stitch.
13. The method of claim 11 , wherein the comparing is performed by a machine learning model by mapping the stitch parameters to a variable of the machine learning model.
14. The method of claim 13 , wherein the machine learning model is trained using at least a first subset of training images with a known fabric construction.
15. The method of claim 1 , further comprising exporting the digital build specification for use in setting up the fabric knitting machine.
16. The method of claim 1 , further comprising constructing the fabric based on the digital build specification.