Automatic Measurement of Comprehensive Skin Types Based on Image Processing and Deep Learning

被引:0
|
作者
Ran, Jianghong [1 ,2 ]
Dong, Guolong [1 ,2 ]
Yi, Fan [1 ,2 ]
Li, Li [1 ,2 ]
Wu, Yue [1 ,2 ]
机构
[1] Beijing Technol & Business Univ, Key Lab Cosmet, China Natl Light Ind, Beijing 100048, Peoples R China
[2] Beijing Technol & Business Univ, Inst Cosmet Regulatory Sci, Beijing 100048, Peoples R China
来源
ELECTRONICS | 2025年 / 14卷 / 01期
关键词
Baumann skin type indicator; Inception-v3; fine-tuning; biophysical properties; non-invasive measurement;
D O I
10.3390/electronics14010049
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The skin serves as a physical and chemical barrier, effectively protecting us against the external environment. The Baumann Skin Type Indicator (BSTI) classifies skin into 16 types based on traits such as dry/oily (DO), sensitive/resistant (SR), pigmented/nonpigmented (PN), and wrinkle-prone/tight (WT). Traditional assessments are time-consuming and challenging as they require the involvement of experts. While deep learning has been widely used in skin disease classification, its application in skin type classification, particularly using multimodal data, remains largely unexplored. To address this, we propose an improved Inception-v3 model incorporating transfer learning, based on the four-dimensional classification of the Baumann Skin Type Index (BSTI), which demonstrates outstanding accuracy. The dataset used in this study includes non-invasive physiological indicators, BSTI questionnaires, and skin images captured under various light sources. By comparing performance across different light sources, regions of interest (ROI), and baseline models, the improved Inception-v3 model achieved the best results, with accuracy reaching 91.11% in DO, 81.13% in SR, 91.72% in PN, and 74.9% in WT, demonstrating its effectiveness in skin type classification. This study surpasses traditional classification methods and previous similar research, offering a new, objective approach to measuring comprehensive skin types using multimodal and multi-light-source data.
引用
收藏
页数:21
相关论文
共 50 条
  • [41] Deep Learning-based Image Text Processing Research
    Xiong, Huixuan
    Jin, Kai
    Liu, Jingnian
    Cai, Jiahong
    Xiao, Lijun
    2023 IEEE 9TH INTL CONFERENCE ON BIG DATA SECURITY ON CLOUD, BIGDATASECURITY, IEEE INTL CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, HPSC AND IEEE INTL CONFERENCE ON INTELLIGENT DATA AND SECURITY, IDS, 2023, : 163 - 168
  • [42] Deep learning-based image processing in optical microscopy
    Sindhoora Kaniyala Melanthota
    Dharshini Gopal
    Shweta Chakrabarti
    Anirudh Ameya Kashyap
    Raghu Radhakrishnan
    Nirmal Mazumder
    Biophysical Reviews, 2022, 14 : 463 - 481
  • [43] An Approach on Image Processing of Deep Learning Based on Improved SSD
    Jin, Liang
    Liu, Guodong
    SYMMETRY-BASEL, 2021, 13 (03):
  • [44] Automatic image processing to identify post-COVID conditions by using deep learning
    Hernandez-Trinidad, A.
    Cordova-Fraga, T.
    Padierna-Garcia, L. C.
    Lopez-Hernandez, J. L.
    Murillo-Ortiz, B. O.
    Guzman-Cabrera, R.
    REVISTA MEXICANA DE FISICA, 2023, 69 (06)
  • [45] Measurement of Fish Morphological Features through Image Processing and Deep Learning Techniques
    Petrellis, Nikos
    APPLIED SCIENCES-BASEL, 2021, 11 (10):
  • [46] An automatic progressive chromosome segmentation approach using deep learning with traditional image processing
    Chang, Ling
    Wu, Kaijie
    Cheng, Hao
    Gu, Chaocheng
    Zhao, Yudi
    Chen, Cailian
    MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2024, 62 (01) : 207 - 223
  • [47] An automatic progressive chromosome segmentation approach using deep learning with traditional image processing
    Ling Chang
    Kaijie Wu
    Hao Cheng
    Chaocheng Gu
    Yudi Zhao
    Cailian Chen
    Medical & Biological Engineering & Computing, 2024, 62 (1) : 207 - 223
  • [48] Automatic Measurement and Comparison of Normal Eyelid Contour by Age and Gender Using Image-Based Deep Learning
    Shao, Ji
    Cao, Jing
    Wang, Changjun
    Xu, Peifang
    Lou, Lixia
    Ye, Juan
    OPHTHALMOLOGY SCIENCE, 2024, 4 (05):
  • [49] A comprehensive evaluation method for dust pollution: Digital image processing and deep learning approach
    Wang, Shaofeng
    Yin, Jiangjiang
    Zhou, Zilong
    JOURNAL OF HAZARDOUS MATERIALS, 2024, 475
  • [50] AniLength: GUI-based automatic worm length measurement software using image processing and deep neural network
    Jung, Sang-Kyu
    SOFTWAREX, 2021, 15