Method for nipple replication
A method includes scanning a user's nipple via a user computing device to generate a scan image and applying a machine learning engine to the scan image to identify the user's nipple. The method also includes generating an output scan image via the machine learning engine, where the output scan image includes features identifying the user's nipple within the output scan image. The method also includes applying a genetic algorithm to the output scan image to generate a 3D image of the user's nipple, where the genetic algorithm employs at least one genetic process and where the 3D image of the user's nipple is a baby bottle nipple profile. The method also includes transmitting the 3D image of the user's nipple to a second user computing device for 3D printing of a custom baby bottle nipple, where the custom baby bottle nipple is a 3D replication of the user's nipple.
1. A method comprising:
obtaining, by at least one processor, a 3D scanned visual output comprising an exposed nipple of a user, wherein the obtaining comprises:
instructing, by the at least one processor, a mobile device, comprising a camera, to scan an area to acquire a 3D scanned visual input;
wherein the area comprises the exposed nipple;
wherein the 3D scanned visual input comprises a plurality of visual digital representations of the area that comprises the exposed nipple;
receiving, by the at least one processor, the 3D scanned visual input;
determining, by the at least one processor, when at least one visual digital representation of the exposed nipple in the plurality of digital representations is complete or incomplete within the 3D scanned visual input;
generating, by the at least one processor, an indication to the user to inform the user when the visual digital representation of the exposed nipple is incomplete so as to direct the user to reposition the mobile device that scans the area to re-acquire or continue to acquire the 3D scanned visual input; and
utilizing, by the at least one processor, when the visual digital representation of the exposed nipple is complete within the 3D scanned visual input, a nipple detection machine learning model to generate at least one bounding box within the 3D scanned visual input that includes the exposed nipple;
wherein the 3D scanned visual output comprises the exposed nipple within the at least one bounding box within the 3D scanned visual input; and
determining, by the at least one processor, based on the 3D scanned visual output, a custom nipple profile associated with the exposed nipple within the at least one bounding box.
2. The method of claim 1 , further comprising training, by the at least one processor, the nipple detection machine learning model to identify the exposed nipple within the 3D scanned visual input based at least in part on a set of images comprising at least a portion of a nipple of a human.
3. The method of claim 1 , wherein the plurality of visual digital representations are videos comprising at least two image frames.
4. The method of claim 3 , further comprising gathering and creating a point cloud, by the at least one processor, by stitching each image frame of each of the at least two image frames together.
5. The method of claim 4 , further comprising:
orienting, by the at least one processor, the point cloud with a teat of the exposed nipple in a predetermined direction.
6. The method of claim 5 , wherein the predetermined direction is along a positive z axis.
7. The method of claim 6 , further comprising setting, by the at least one processor, an average normal at a top portion of the point cloud based on the positive z axis.
8. The method of claim 7 , further comprising maximizing, by the at least one processor, a height at which the teat exceeds a predetermined cross-sectional diameter.
9. The method of claim 8 , wherein the predetermined cross-sectional diameter is 30 mm.
10. The method of claim 6 , further comprising filtering out, by the at least one processor, a normal of each point in the point cloud further and further away from the positive z axis until there is a clear separation between the teat and a base of the exposed nipple.
11. The method of claim 1 , wherein the nipple detection machine learning model is trained to identify the exposed nipple within the plurality of visual digital representations.
12. The method of claim 1 , further comprising receiving, by the at least one processor, a plurality of rescanned images if the nipple detection machine learning model does not identify the exposed nipple within the plurality of visual digital representations.
13. The method of claim 1 , further comprising rebuilding, by the at least one processor, the exposed nipple without any gaps or holes by extracting key contours and measurements from the 3D scanned visual input.
14. The method of claim 1 , wherein determining the custom nipple profile comprises:
determining, by the at least one processor, based on the 3D scanned visual output and one or more nipple profiles associated with baby bottles, the custom nipple profile associated with the exposed nipple.
15. The method of claim 1 , wherein determining the custom nipple profile comprises:
utilizing, by the at least one processor, a genetic algorithm to extract a plurality of nipple-related geometric features from the 3D scanned visual output comprising the exposed nipple within the at least one bounding box within the 3D scanned visual input;
wherein the plurality of nipple-related geometric features comprise:
nipple-related height, and
nipple-related width; and
determining, by the at least one processor, based on the plurality of nipple-related geometric features, the custom nipple profile associated with the exposed nipple.
16. The method of claim 1 , wherein determining the custom nipple profile comprises:
utilizing, by the at least one processor, a genetic algorithm to extract a nipple-related color and a plurality of nipple-related geometric features from the 3D scanned visual output comprising the exposed nipple within the at least one bounding box within the 3D scanned visual input;
wherein the plurality of nipple-related geometric features comprise:
nipple-related height, and
nipple-related width; and
determining, by the at least one processor, based on the plurality of nipple-related geometric features and the nipple-related color, the custom nipple profile associated with the exposed nipple.
17. The method of claim 1 , wherein receiving, by the at least one processor, the 3D scanned visual input comprises:
identifying, by the mobile device, the exposed nipple within the 3D scanned visual input;
transmitting, by the mobile device, to the at least one processor, the 3D scanned visual input identifying the exposed nipple; and
receiving, by the at least one processor, the 3D scanned visual input identifying the exposed nipple.
18. A system comprising:
a non-transitory computer readable medium storing instructions; and
at least one processor configured to execute the instructions that cause the at least one processor to:
obtain a 3D scanned visual output comprising an exposed nipple of a user, wherein the obtaining comprises:
instruct a mobile device comprising a camera to scan an area to acquire a 3D scanned visual input;
wherein the area comprises the exposed nipple;
wherein the 3D scanned visual input comprises a plurality of visual digital representations of the area that comprises the exposed nipple;
receive the 3D scanned visual input;
determine when at least one visual digital representation of the exposed nipple in the plurality of digital representations is complete or incomplete within the 3D scanned visual input;
generate an indication to the user to inform the user when the visual digital representation of the exposed nipple is incomplete so as to direct the user to reposition the mobile device that scans the area to acquire or continue to acquire the 3D scanned visual input; and
utilize, when the visual digital representation of the exposed nipple is complete within the 3D scanned visual input, a nipple detection machine learning model to generate at least one bounding box within the 3D scanned visual input that includes the exposed nipple;
wherein the 3D scanned visual output comprises the exposed nipple within the at least one bounding box within the 3D scanned visual input; and
determine, based on the 3D scanned visual output, a custom nipple profile associated with the exposed nipple within the at least one bounding box.
19. The system of claim 18 , wherein determining the custom nipple profile comprises:
determine, based on the 3D scanned visual output and one or more nipple profiles associated with baby bottles, the custom nipple profile associated with the exposed nipple.
20. The system of claim 18 , wherein determining the custom nipple profile comprises:
utilize a genetic algorithm to extract a plurality of nipple-related geometric features from the 3D scanned visual output comprising the exposed nipple within the at least one bounding box within the 3D scanned visual input;
wherein the plurality of nipple-related geometric features comprise:
nipple-related height, and
nipple-related width; and
determine, based on the plurality of nipple-related geometric features, the custom nipple profile associated with the exposed nipple.
21. The system of claim 18 , wherein determining the custom nipple profile comprises:
utilize a genetic algorithm to extract a nipple-related color and a plurality of nipple-related geometric features from the 3D scanned visual output comprising the exposed nipple within the at least one bounding box within the 3D scanned visual input;
wherein the plurality of nipple-related geometric features comprise:
nipple-related height, and
nipple-related width; and
determine, based on the plurality of nipple-related geometric features and the nipple-related color, the custom nipple profile associated with the exposed nipple.