Facial Pore Segmentation Algorithm using Shallow CNN

Seo, Sunyong; Yoo, Sangwook; Kim, Semin; Yoon, Da-Eun; Lee, Jong-Ha

doi:10.1109/cbms55023.2022.00062

Cited by 1 publication

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in the introduction, skin attribute segmentation using deep learning techniques has attracted considerable research attention [4][5][6][7][8][9]. Although considerable advancements have been achieved in the application of state-of-the-art networks and their integration with a generative model to expand the scope of application, the unique characteristics of skin are yet to be incorporated into the network itself.…”

Section: Discussionmentioning

confidence: 99%

“…Research using deep learning has begun to emerge in the facial skin analysis field as well [4][5][6][7][8][9]. In [4], a deep learning model was used for segmenting acne, pigmentation, and wrinkles.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning is also being used in skin pore segmentation. For instance, in [8], U-Net with L1 loss was used for pore segmentation, and [9] suggested a shallow CNN focusing on pores with a simple shape.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep-Learning-Based Morphological Feature Segmentation for Facial Skin Image Analysis

Yoon¹,

Kim²,

Lee³

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

Facial skin analysis has attracted considerable attention in the skin health domain. The results of facial skin analysis can be used to provide skin care and cosmetic recommendations in aesthetic dermatology. Because of the existence of several skin features, grouping similar features and processing them together can improve skin analysis. In this study, a deep-learning-based method of simultaneous segmentation of wrinkles and pores is proposed. Unlike color-based skin analysis, this method is based on the analysis of the morphological structures of the skin. Although multiclass segmentation is widely used in computer vision, this segmentation was first used in facial skin analysis. The architecture of the model is U-Net, which has an encoder–decoder structure. We added two types of attention schemes to the network to focus on important areas. Attention in deep learning refers to the process by which a neural network focuses on specific parts of its input to improve its performance. Second, a method to enhance the learning capability of positional information is added to the network based on the fact that the locations of wrinkles and pores are fixed. Finally, a novel ground truth generation scheme suitable for the resolution of each skin feature (wrinkle and pore) was proposed. The experimental results revealed that the proposed unified method achieved excellent localization of wrinkles and pores and outperformed both conventional image-processing-based approaches and one of the recent successful deep-learning-based approaches. The proposed method should be expanded to applications such as age estimation and the prediction of potential diseases.

show abstract