Visual sign language translation training device and method

1. An apparatus for training a machine learning system, comprising:

a processor, and

a memory including processor executable code, wherein the processor executable code upon execution by the processor causes the processor to:

generate a three-dimensional (3D) scene that includes a 3D model representing a target object, wherein the 3D model is positioned in the 3D scene to simulate a gesture;

determine a plurality of variations of the 3D scene for generating a number of training images;

apply each of the plurality of variations to the 3D scene to produce a plurality of modified 3D scenes;

capture an image of each of the plurality of modified 3D scenes to form the training images for a neural network of the machine learning system; and

automatically generate, for each of the training images, a label that corresponds to a feature of interest associated with the gesture, the label comprising one or more bounding lines that delineates a precise boundary of the feature of interest, wherein the precise boundary of the feature of interest is generated based on a group of polygons that form the feature of interest in the 3D model.

2. The apparatus of claim 1 , wherein the number of training images to be generated is predetermined.

3. The apparatus of claim 1 , wherein the number of training images is less than or equal to 50.

4. The apparatus of claim 1 , wherein the feature of interest has an irregularly shaped boundary.

5. The apparatus of claim 1 , wherein the processor executable code upon execution by the processor configures the processor to determine the plurality of variations of the 3D scene based on a set of parameters that specifies at least one of: a position of the 3D model, an angle of the 3D model, a position of a camera, an orientation of a camera, a lighting attribute, a texture of a subsection of the 3D model, or a background of the 3D scene.

6. The apparatus of claim 1 , wherein the processor executable code upon execution by the processor configures the processor to apply each of the plurality of variations to the 3D scene by changing the 3D scene in a temporal sequence.

7. The apparatus of claim 1 , wherein the processor executable code upon execution by the processor configures the processor to:

evaluate the machine learning system after the machine learning system performs a training operation based on the training images; and

re-generate another set of training images upon a determination that the machine learning system fails to meet one or more predetermined criteria.

8. The apparatus of claim 7 , wherein the one or more predetermined criteria includes at least one of: a performance of the neural network, an accuracy of the neural network, or a number of characteristics that the neural network is capable of recognizing.

9. The apparatus of claim 1 , wherein the processor executable code upon execution by the processor causes the processor to:

evaluate the machine learning system for each of the training images one at a time; and

for at least one of the training images, upon a determination that the machine learning system performance in identifying a feature of interest using the at least one of the training images has failed to improve from its performance based on a previous training image, discard the at least one of the training images.

10. A method for providing training images for training a neural network of a machine learning system, comprising:

generating a three-dimensional (3D) scene that includes a 3D model representing a target object, wherein the 3D model is positioned in the 3D scene to simulate a gesture;

determine a plurality of variations of the 3D scene for generating a number of training images;

applying each of the plurality of variations to the 3D scene to produce a plurality of modified 3D scenes;

capturing an image of each of the plurality of modified 3D scenes to form the training images for the neural network of the machine learning system; and

automatically generating, for each of the training images, a label that corresponds to a feature of interest associated with the gesture, the label comprising one or more bounding lines that delineates a precise boundary of the feature of interest, wherein the precise boundary of the feature of interest is generated based on a group of polygons that form the feature of interest in the 3D model.

11. The method of claim 10 , wherein the number of training images to be generated is predetermined.

12. The method of claim 10 , wherein the number of training images is less than or equal to 50.

13. The method of claim 10 , wherein the feature of interest has an irregularly shaped boundary.

14. The method of claim 10 , wherein determining the plurality of variations of the 3D scene is based on a set of parameters that specifies at least one of: a position of the 3D model, an angle of the 3D model, a position of a camera, an orientation of a camera, a lighting attribute, a texture of a subsection of the 3D model, or a background of the 3D scene.

15. The method of claim 10 , wherein applying each of the plurality of variations to the 3D scene comprises changing the 3D scene in a temporal sequence.

16. The method of claim 10 , further comprising:

evaluating the machine learning system after the machine learning system performs training; and

re-generating another set of training images upon a determination that the machine learning system fails to meet one or more predetermined criteria.

17. The method of claim 16 , wherein the one or more predetermined criteria includes at least one of: a performance of the neural network, an accuracy of the neural network, or a number of characteristics that the neural network is capable of recognizing.

18. The method of claim 10 , further comprising:

evaluating the machine learning system for each of the training images one at a time; and

for at least one of the training images, upon a determination that the machine learning system performance in identifying a feature interest using the at least one of the training images has failed to improve from its performance based on a previous training image, discarding the at least one training image.

19. A non-transitory computer readable medium having code stored thereon, the code upon execution by a processor, causing the processor to implement a method that comprises:

generating a three-dimensional (3D) scene that includes a 3D model representing a target object, wherein the 3D model is positioned in the 3D scene to simulate a gesture;

determining a plurality of variations of the 3D scene for generating a number of training images;

applying each of the plurality of variations to the 3D scene to produce a plurality of modified 3D scenes;

capturing an image of each of the plurality of modified 3D scenes to form the training images for a neural network of the machine learning system; and

automatically generating, for each of the training images, a label that corresponds to a feature of interest associated with the gesture, the label comprising one or more bounding lines that delineates a precise boundary of the feature of interest, wherein the precise boundary of the feature of interest is generated based on a group of polygons that form the feature of interest in the 3D model.

20. The non-transitory computer readable medium of claim 19 , wherein the number of training images to be generated is predetermined.

21. The non-transitory computer readable medium of claim 19 , wherein the number of training images is less than or equal to 50.

22. The non-transitory computer readable medium of claim 19 , wherein the feature of interest has an irregularly shaped boundary.

23. The non-transitory computer readable medium of claim 19 , wherein determining the plurality of variations of the 3D scene is based on a set of parameters that specifies at least one of: a position of the 3D model, an angle of the 3D model, a position of a camera, an orientation of a camera, a lighting attribute, a texture of a subsection of the 3D model, or a background of the 3D scene.

24. The non-transitory computer readable medium of claim 23 , wherein applying each of the plurality of variations to the 3D scene includes changing the 3D scene in a temporal sequence in accordance with the set of parameters.

25. The non-transitory computer readable medium of claim 19 , wherein the method further comprises:

obtaining an evaluation of the machine learning system after the machine learning system performs training; and

re-generating another set of training images upon a determination that the machine learning system fails to meet one or more predetermined criteria.

26. The non-transitory computer readable medium of claim 25 , wherein the one or more predetermined criteria includes at least one of: a performance of the neural network, an accuracy of the neural network, or a number of characteristics that the neural network is capable of recognizing.

27. The non-transitory computer readable medium of claim 19 , wherein the method further comprises:

obtaining an evaluation of the machine learning system for each of the training images one at a time; and

for at least one of the training images, upon a determination that the machine learning system performance in identifying a feature interest using the at least one of the training images has failed to improve from its performance based on a previous training image, discarding the at least one training image.