Visual sign language translation training device and method
Methods, devices and systems for training a pattern recognition system are described. In one example, a method for training a sign language translation system includes generating a three-dimensional (3D) scene that includes a 3D model simulating a gesture that represents a letter, a word, or a phrase in a sign language. The method includes obtaining a value indicative of a total number of training images to be generated, using the value indicative of the total number of training images to determine a plurality of variations of the 3D scene for generating of the training images, applying each of plurality of variations to the 3D scene to produce a plurality of modified 3D scenes, and capturing an image of each of the plurality of modified 3D scenes to form the training images for a neural network of the sign language translation system.
1 . An apparatus for using a sign language translation 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:
perform, subsequent to using the sign language translation system to perform a training operation, an interpretation operation to identify and interpret input data,
wherein the processor executable code upon execution by the processor configures the processor, as part of performing the training operation, to:
generate a three-dimensional (3D) scene that includes a 3D model representing at least a part of a human body, the 3D model positioned in the 3D scene to simulate a gesture that represents a letter, a word, or a phrase in a sign language;
obtain a value indicative of a total number of training images to be generated;
use the value indicative of the total number of training images to determine a plurality of variations of the 3D scene for generating 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 sign language translation system; and
automatically generate, for each of the training images, a label that corresponds to a feature of interest associated with the gesture, wherein the label comprises one or more bounding lines that delineates a precise boundary of the feature of interest, and wherein the precise boundary of the feature of interest is generated based on a group of polygons that collectively form the feature of interest in the 3D model.
2 . The apparatus of claim 1 , wherein the feature of interest has an irregularly shaped boundary.
3 . The apparatus of claim 1 , wherein the feature of interest is associated with a hand movement.
4 . The apparatus of claim 1 , wherein the feature of interest is associated with a non-manual activity.
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 specify at least one of: a position of the 3D model, an angle of 3D model, a position of a camera, an orientation of the 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 5 , 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 in accordance with the set of parameters.
7 . The apparatus of claim 1 , wherein the processor executable code upon execution by the processor configures the processor to:
obtain an evaluation of the sign language translation system after the sign language translation system uses the training images to perform the training operation; and
re-generate another set of training images upon a determination that the sign language translation 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 value indicative of the total number of training images is less than or equal to 50.
10 . The apparatus of claim 1 , wherein the processor executable code upon execution by the processor causes the processor to:
obtain an evaluation of the sign language translation system for each of the training images one at a time; and
for at least one of the training images, upon a determination that a performance of the sign language translation system 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.
11 . A method for using a neural network of a sign language translation system, comprising:
performing, subsequent to using the sign language translation system to perform a training operation, an interpretation operation to identify and interpret input data, wherein the training operation comprises:
generating a three-dimensional (3D) scene that includes a 3D model representing at least a part of a human body, the 3D model positioned in the 3D scene to simulate a gesture that represents a letter, a word, or a phrase in a sign language;
obtaining a value indicative of a total number of training images to be generated;
using the value indicative of the total number of training images to determine a plurality of variations of the 3D scene for generating 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 sign language translation system; and
automatically generating, for each of the training images, a label that corresponds to a feature of interest associated with the gesture, wherein the label comprises one or more bounding lines that delineates a precise boundary of the feature of interest, and wherein the precise boundary of the feature of interest is generated based on a group of polygons that collectively form the feature of interest in the 3D model.
12 . The method of claim 11 , wherein the feature of interest has an irregularly shaped boundary.
13 . The method of claim 11 , wherein the feature of interest is associated with a hand movement.
14 . The method of claim 11 , wherein the feature of interest is associated with a non-manual activity.
15 . The method of claim 11 , wherein determining the plurality of variations of the 3D scene is based on a set of parameters that specify at least one of: a position of the 3D model, an angle of 3D model, a position of a camera, an orientation of the camera, a lighting attribute, a texture of a subsection of the 3D model, or a background of the 3D scene.
16 . The method of claim 15 , 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.
17 . The method of claim 11 , wherein the training operation further comprises:
obtaining an evaluation of the sign language translation system after the sign language translation system performs training; and
re-generating another set of training images upon a determination that the sign language translation system fails to meet one or more predetermined criteria.