Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/82546
Título: | Eye-LRCN: A long-term recurrent convolutional network for eye blink completeness detection |
Autor(es): | Cruz, Gonzalo de la Lira, Madalena Luaces, Oscar Remeseiro, Beatriz |
Palavras-chave: | Blink completeness detection Computer vision syndrome (CVS) Eye state detection Long-term recurrent convolutional networks (LRCNs) Siamese neural networks Task analysis Feature extraction Computer architecture Face recognition Support vector machines Eyelids Convolutional neural networks |
Data: | Abr-2024 |
Editora: | IEEE |
Revista: | IEEE Transactions on Neural Networks and Learning Systems |
Citação: | G. de la Cruz, M. Lira, O. Luaces and B. Remeseiro, "Eye-LRCN: A Long-Term Recurrent Convolutional Network for Eye Blink Completeness Detection," in IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 5130-5140, April 2024, doi: 10.1109/TNNLS.2022.3202643. |
Resumo(s): | Computer vision syndrome causes vision problems and discomfort mainly due to dry eye. Several studies show that dry eye in computer users is caused by a reduction in the blink rate and an increase in the prevalence of incomplete blinks. In this context, this article introduces Eye-LRCN, a new eye blink detection method that also evaluates the completeness of the blink. The method is based on a long-term recurrent convolutional network (LRCN), which combines a convolutional neural network (CNN) for feature extraction with a bidirectional recurrent neural network that performs sequence learning and classifies the blinks. A Siamese architecture is used during CNN training to overcome the high-class imbalance present in blink detection and the limited amount of data available to train blink detection models. The method was evaluated on three different tasks: blink detection, blink completeness detection, and eye state detection. We report superior performance to the state-of-the-art methods in blink detection and blink completeness detection, and remarkable results in eye state detection. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/82546 |
DOI: | 10.1109/TNNLS.2022.3202643 |
ISSN: | 2162-237X |
Versão da editora: | https://ieeexplore.ieee.org/document/9885029 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CDF - OCV - Artigos/Papers (with refereeing) |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Eye-LRCN_A_Long-Term_Recurrent_Convolutional_Network_for_Eye_Blink_Completeness_Detection.pdf | 1,55 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons