TY - GEN
T1 - CNN-LSTM Proposal for Colombian Sign Language Greetings Classification
T2 - 3rd International Congress of Biomedical Engineering and Bioengineering, CIIBBI 2024
AU - Rojas, Ivette
AU - Sierra, Katherin
AU - Tocora, Angelica Maria Rojas
AU - Calderon, Luis
AU - Buitrago, Natalia
AU - Orjuela-Canon, Alvaro D.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Colombian sign language (CSL) have shown different advances to automatize the translation and communication between deaf or disabling hearing people and speakers. However, these current efforts are oriented on classification of static signs, mainly. The present proposal implements the use a convolutional neural network (CNN) that also involves the use an architecture of the long short-term memory (LSTM) one. This allowed to include the time dependent information for dynamic signs like a sequence data. For this, a dataset was created with greetings for the CSL through the recording videos of signs. The methodology used the MediaPipe tool for feature extraction, which was used to represent relevant points from fingers articulation for frames of the videos. CNN-LSTM was applied with the joint points information for the classification. Results show that 71.50 % (+/-4.33%) for five greetings classification, employing a crossvalidation and early stopping criteria for the training of models.
AB - Colombian sign language (CSL) have shown different advances to automatize the translation and communication between deaf or disabling hearing people and speakers. However, these current efforts are oriented on classification of static signs, mainly. The present proposal implements the use a convolutional neural network (CNN) that also involves the use an architecture of the long short-term memory (LSTM) one. This allowed to include the time dependent information for dynamic signs like a sequence data. For this, a dataset was created with greetings for the CSL through the recording videos of signs. The methodology used the MediaPipe tool for feature extraction, which was used to represent relevant points from fingers articulation for frames of the videos. CNN-LSTM was applied with the joint points information for the classification. Results show that 71.50 % (+/-4.33%) for five greetings classification, employing a crossvalidation and early stopping criteria for the training of models.
UR - http://www.scopus.com/inward/record.url?scp=85215289615&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85215289615&partnerID=8YFLogxK
U2 - 10.1109/CIIBBI63846.2024.10785211
DO - 10.1109/CIIBBI63846.2024.10785211
M3 - Conference contribution
AN - SCOPUS:85215289615
T3 - 2024 3rd International Congress of Biomedical Engineering and Bioengineering, CIIBBI 2024
BT - 2024 3rd International Congress of Biomedical Engineering and Bioengineering, CIIBBI 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 November 2024 through 8 November 2024
ER -