A Deep Learning-Based Facial Acne Classification System

被引:5
|
作者
Quattrini, Andrea [1 ]
Boer, Claudio [1 ]
Leidi, Tiziano [1 ]
Paydar, Rick [2 ]
机构
[1] Inst Informat Technol & Networking SUPSI, Dept Innovat Technol, Polo Univ Lugano Campus Est,Via La Santa 1, CH-6962 Lugano, Switzerland
[2] CHOLLEY SA, Pambio Noranco, Switzerland
关键词
semantic segmentation; image classification; acne detection; dermatologists; computer vision;
D O I
10.2147/CCID.S360450
中图分类号
R75 [皮肤病学与性病学];
学科分类号
100206 ;
摘要
Introduction: Acne is one of the most common pathologies and affects people of all ages, genders, and ethnicities. The assessment of the type and severity status of a patient with acne should be done by a dermatologist, but the ever-increasing waiting time for an examination makes the therapy not accessible as quickly and consequently less effective. This work, born from the collaboration with CHOLLEY, a Swiss company with decades of experience in the research and production of skin care products, with the aim of developing a deep learning system that, using images produced with a mobile device, could make assessments and be as effective as a dermatologist. Methods: There are two main challenges within this task. The first is to have enough data to train a neural model. Unlike other works in the literature, it was decided not to collect a proprietary dataset, but rather to exploit the enormity of public data available in the world of face analysis. Part of Flickr-Faces-HQ (FFHQ) was re-annotated by a CHOLLEY dermatologist, producing a dataset that is sufficiently large, but still very extendable. The second challenge was to simultaneously use high-resolution images to provide the neural network with the best data quality, but at the same time to ensure that the network learned the task correctly. To prevent the network from searching for recognition patterns in some uninteresting regions of the image, a semantic segmentation model was trained to distinguish, what is a skin region possibly affected by acne and what is background and can be discarded. Results: Filtering the re-annotated dataset through the semantic segmentation model, the trained classification model achieved a final average f1 score of 60.84% in distinguishing between acne affected and unaffected faces, result that, if compared to other techniques proposed in the literature, can be considered as state-of-the-art.
引用
收藏
页码:851 / 857
页数:7
相关论文
共 50 条
  • [1] Development of Deep Learning-based Facial Expression Recognition System
    Jung, Heechul
    Lee, Sihaeng
    Park, Sunjeong
    Kim, Byungju
    Kim, Junmo
    Lee, Injae
    Ahn, Chunghyun
    [J]. 2015 21ST KOREA-JAPAN JOINT WORKSHOP ON FRONTIERS OF COMPUTER VISION, 2015,
  • [2] An Explainable Deep Learning-Based Classification Method for Facial Image Quality Assessment
    Gurjar, Kuldeep
    Kumar, Surjeet
    Bhavsar, Arnav
    Hamad, Kotiba
    Moon, Yang-Sae
    Yoon, Dae Ho
    [J]. JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2024, 20 (04): : 558 - 573
  • [3] Tiara: deep learning-based classification system for eukaryotic sequences
    Karlicki, Michal
    Antonowicz, Stanislaw
    Karnkowska, Anna
    [J]. BIOINFORMATICS, 2022, 38 (02) : 344 - 350
  • [4] Deep Learning-Based Recommendation System: Systematic Review and Classification
    Li, Caiwen
    Ishak, Iskandar
    Ibrahim, Hamidah
    Zolkepli, Maslina
    Sidi, Fatimah
    Li, Caili
    [J]. IEEE ACCESS, 2023, 11 : 113790 - 113835
  • [5] An IoT deep learning-based home appliances management and classification system
    Solatidehkordi, Zahra
    Ramesh, Jayroop
    Al-Ali, A. R.
    Osman, Ahmed
    Shaaban, Mostafa
    [J]. ENERGY REPORTS, 2023, 9 : 503 - 509
  • [6] An IoT deep learning-based home appliances management and classification system
    Solatidehkordi, Zahra
    Ramesh, Jayroop
    Al-Ali, A. R.
    Osman, Ahmed
    Shaaban, Mostafa
    [J]. ENERGY REPORTS, 2023, 9 : 503 - 509
  • [7] An Enhanced Deep Learning-Based DeepFake Video Detection and Classification System
    Awotunde, Joseph Bamidele
    Jimoh, Rasheed Gbenga
    Imoize, Agbotiname Lucky
    Abdulrazaq, Akeem Tayo
    Li, Chun-Ta
    Lee, Cheng-Chi
    [J]. ELECTRONICS, 2023, 12 (01)
  • [8] Deep Learning-Based Tomato's Ripe and Unripe Classification System
    Das, Prasenjit
    Yadav, Jay Kant Pratap Singh
    Singh, Laxman
    [J]. INTERNATIONAL JOURNAL OF SOFTWARE INNOVATION, 2022, 10 (01)
  • [9] An IoT deep learning-based home appliances management and classification system
    Solatidehkordi, Zahra
    Ramesh, Jayroop
    Al-Ali, A. R.
    Osman, Ahmed
    Shaaban, Mostafa
    [J]. ENERGY REPORTS, 2023, 9 : 503 - 509
  • [10] Deep Learning-Based Unsupervised Human Facial Retargeting
    Kim, Seonghyeon
    Jung, Sunjin
    Seo, Kwanggyoon
    Blanco i Ribera, Roger
    Noh, Junyong
    [J]. COMPUTER GRAPHICS FORUM, 2021, 40 (07) : 45 - 55