Neonatal Face Mosaic: An areas-of-interest segmentation method based on 2D face images

• Pedro Henrique Silva Domingues FEI University Center
• Renan Martins Mendes da Silva FEI University Center
• Ibrahim Jamil Orra FEI University Center
• Matheus Elias Cruz FEI University Center
• Tatiany Marcondes Heiderich FEI University Center
• Carlos Eduardo Thomaz FEI University Center

DOI: https://doi.org/10.5753/wvc.2021.18914

Abstract

The daily life of preterm babies may be involved with long exposure to pain, causing problems in the development of the nervous system. In this context, an on-going area of research is the scientific development of image-based automatic pain detection systems based on several techniques, from anatomical measurements to artificial intelligence, they have generally two main issues: the categorization of the most relevant facial regions for identifying neonatal pain and the practical difficulty related to the presence of artifacts obstructing parts of the face. This paper proposes and implements an areas-of-interest automatic segmentation method that allows the creation of a novel dataset containing crops of neonatal faces relevant for pain classification, labelled by areas-of-interest and pain status. Moreover, we have also investigated the use of similarity matching techniques to compare each area-of-interest to the corresponding one extracted from a prototype face with no occlusion.t

Keywords: preterm infants, face dataset, face segmentation, mosaic, computer vision

References

R. d. C. X. Balda, R. Guinsburg, “Evaluation and treatment of pain in the neonatal period,” Revista Pediátrica-Publicação Oficial da Sociedade Brasileira de Pediatria, v. 9,n. 1, p. 43-52, 2019, doi: 10.25060/residpediatr-2019.v9n1-13.

T. M. Heiderich, A. T. F. S. Leslie, R. Guinsburg, “Neonatal procedural pain canbe assessed by computer software that has good sensitivity and specificity to detect facial movements,” Acta Paediatrica, Wiley Online Library, vol. 104, n. 2, pp. e63-e69, 2015.

S. M. Walker, “Long-term effects of neonatal pain” In: ELSEVIER. Seminars in Fetal and Neonatal Medicine. [S.l.], 2019. v. 24, n. 4, p. 101005.

G. F. Teruel, C. E. Thomaz, “Analise e reconhecimento de dor em imagens 2d frontais de recem-nascidos a termo e saudáveis,”. In: SBC. Anais Estendidos do XIX Simpósio Brasileiro de Computação Aplicada à Saúde. [S.l.], 2019. p. 97-102.

G. Zamzmi, S. Salekin, D. Goldgof, T. Ho, Y. Sun, “Pain assessment from facial expression: Neonatal convolutional neural network (ncnn)”. In: IEEE.2019 International Joint Conference on Neural Networks( IJCNN). [S.l.], 2019. p. 1-7.

L. Buzuti, “Avaliação de dor em expressão facial neonatal por meio de redes neurais profundas”. Centro Universitário FEI, São Bernardo do Campo, 2020.

J. Deng, J. Guo, E. Ververas, I. Kotsia, S. Zafeiriou, “Retinaface: Singleshot multi-level face localisation in the wild”. In: IEEE.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [S.l.], 2020. p. 5202-5211.