METHOD FOR RECOGNIZING HAND GESTURES OF SIGN LANGUAGE

Abstract

ABSTRACT A method (100) for recognizing hand gestures of sign language, the method (100) comprising the steps of pre-processing an input image of hand gestures to improve quality of the input image, extracting one or more features of the input image by passing it through a pre-trained convolutional neural network (CNN) model, applying transfer learning by utilizing the pre-trained CNN model to improve recognition accuracy for the hand gestures, classifying the hand gesture by passing the extracted one or more features through one or more fully connected layers of the pre-trained CNN model and generating an output based at least on the classified hand gestures. <>

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to a field of sign language and in particular relates to a method for recognising hand gestures of sign language.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Traditional methods of communication for individuals who are deaf or hard of hearing often rely heavily on interpreters or written text, which can create barriers in real-time and interactive communication. Sign language, especially American Sign Language (ASL), provides a comprehensive a , Claims:1. A method (100) for recognizing hand gestures of sign language, the method (100) comprising the steps of:
pre-processing an input image of hand gestures to improve quality of the input image;
extracting one or more features of the input image by passing it through a pre-trained convolutional neural network (CNN) model;
applying transfer learning by utilizing the pre-trained CNN model to improve recognition accuracy for the hand gestures;
classifying the hand gesture by passing the extracted one or more features through one or more fully connected layers of the pre-trained CNN model; and
generating an output based at least on the classified hand gestures.

2. The method (100) as claimed in claim 1, further comprising rescaling, normalizing, and applying data augmentation on the input image.

3. The method (100) as claimed in claim 1, wherein the pre-trained convolutional neural network (CNN) model comprises a series of layers including at least one convolutional layer, pooling layer, and activation laye

Documents