Apparatus and methods for image segmentation using machine learning processes
Methods, systems, and apparatuses for image segmentation are provided. For example, a computing device may obtain an image, and may apply a process to the image to generate input image feature data and input image segmentation data. Further, the computing device may obtain reference image feature data and reference image classification data for a plurality of reference images. The computing device may generate reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data. The computing device may further blend the input image segmentation data and the reference image segmentation data to generate blended image segmentation data. The computing device may store the blended image segmentation data within a data repository. In some examples, the computing device provides the blended image segmentation data for display.
1. An apparatus comprising:
a non-transitory, machine-readable storage medium storing instructions; and
at least one processor coupled to the non-transitory, machine-readable storage medium, the at least one processor being configured to:
apply a process to an input image to generate input image feature data characterizing features of the input image, and input image segmentation data characterizing an initial segmentation of the input image;
obtain, for a plurality of reference images, reference image feature data characterizing features of the plurality of reference images, and reference image classification data characterizing classifications of the plurality of reference images;
generate reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data; and
combine values of the input image segmentation data with values of the reference image segmentation data to generate blended image segmentation data, the blended image segmentation data characterizing a final segmentation of the input image.
2. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to:
generate, for each of the plurality of reference images, first reference image data based on the reference image feature data and the reference image classification data corresponding to each of the plurality of reference images; and
generate the reference image segmentation data based on the first reference image data for each of the plurality of reference images and the input image feature data.
3. The apparatus of claim 2 , wherein the at least one processor is further configured to execute the instructions to:
generate, for each of the plurality of reference images, second reference image data based on the first reference image data and the input image feature data; and
generate the reference image segmentation data based on the second reference image data for each of the plurality of reference images.
4. The apparatus of claim 3 , wherein the at least one processor is further configured to execute the instructions to obtain the plurality of reference images from a data repository.
5. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to obtain the reference image feature data from a data repository.
6. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to apply the process to the plurality of reference images to generate the reference image feature data.
7. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to display the blended image segmentation data.
8. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to store the blended image segmentation data within a data repository.
9. The apparatus of claim 1 , wherein the process is a trained machine learning process, and wherein the at least one processor is further configured to execute the instructions to establish a convolutional neural network to apply the trained machine learning process to the input image.
10. The apparatus of claim 9 , wherein the input image feature data is an output of an encoder of the convolutional neural network, and the input image segmentation data is an output of a decoder of the convolutional neural network.
11. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to:
receive a first input from a user; and
capture the input image in response to the first input from the user.
12. The apparatus of claim 1 , wherein the apparatus is a head mounted device.
13. The apparatus of claim 1 , wherein the at least one processor is further configured to execute the instructions to apply at least one image processing operation to the input image based on the blended image segmentation data.
14. A method for image segmentation comprising:
applying a process to an input image to generate input image feature data characterizing features of the input image, and input image segmentation data characterizing an initial segmentation of the input image;
obtaining, for a plurality of reference images, reference image feature data characterizing features of the plurality of reference images, and reference image classification data characterizing classifications of the plurality of reference images;
generating reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data; and
combining values of the input image segmentation data with values of the reference image segmentation data to generate blended image segmentation data, the blended image segmentation data characterizing a final segmentation of the input image.
15. The method of claim 14 , comprising:
generating, for each of the plurality of reference images, first reference image data based on the reference image feature data and the reference image classification data corresponding to each of the plurality of reference images; and
generating the reference image segmentation data based on the first reference image data for each of the plurality of reference images and the input image feature data.
16. The method of claim 15 , comprising:
generating, for each of the plurality of reference images, second reference image data based on the first reference image data and the input image feature data; and
generating the reference image segmentation data based on the second reference image data for each of the plurality of reference images.
17. The method of claim 14 , comprising applying the process to the plurality of reference images to generate the reference image feature data.
18. The method of claim 14 , wherein the process is a trained machine learning process, the method comprising establishing a convolutional neural network to apply the trained machine learning process to the input image.
19. A non-transitory, machine-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations that include:
applying a process to an input image to generate input image feature data characterizing features of the input image, and input image segmentation data characterizing an initial segmentation of the input image;
obtaining, for a plurality of reference images, reference image feature data characterizing features of the plurality of reference images, and reference image classification data characterizing classifications of the plurality of reference images;
generating reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data; and
combining values of the input image segmentation data with values of the reference image segmentation data to generate blended image segmentation data, the blended image segmentation data characterizing a final segmentation of the input image.
20. The non-transitory, machine-readable storage medium of claim 19 , wherein the instructions, when executed by the at least one processor, cause the at least one processor to perform additional operations that include:
generating, for each of the plurality of reference images, first reference image data based on the reference image feature data and the reference image classification data corresponding to each of the plurality of reference images; and
generating the reference image segmentation data based on the first reference image data for each of the plurality of reference images and the input image feature data.