[article]
| Titre : |
Artificial Intelligence in hair research : A proof-of-concept study on evaluating hair assembly features |
| Type de document : |
document électronique |
| Auteurs : |
Gabriela Daniels, Auteur ; Slobodanka Tamburic, Auteur ; Sergio Benini, Auteur ; Jane Randall, Auteur ; Tracey Sanderson, Auteur ; Mattia Savardi, Auteur |
| Année de publication : |
2021 |
| Article en page(s) : |
p. 405-418 |
| Note générale : |
Bibliogr. |
| Langues : |
Anglais (eng) |
| Catégories : |
Analyse sensorielle
Apprentissage automatiqueL'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Cheveux -- analyse
Cheveux décolorés
Détection de défauts (Ingénierie)
Intelligence artificielle
|
| Index. décimale : |
668.5 Parfums et cosmétiques |
| Résumé : |
- Objective : The first objective of this study was to apply computer vision and machine learning techniques to quantify the effects of haircare treatments on hair assembly and to identify correctly whether unknown tresses were treated or not. The second objective was to explore and compare the performance of human assessment with that obtained from artificial intelligence (AI) algorithms.
- Methods : Machine learning was applied to a data set of hair tress images (virgin and bleached), both untreated and treated with a shampoo and conditioner set, aimed at increasing hair volume whilst improving alignment and reducing the flyway of the hair. The automatic quantification of the following hair image features was conducted : local and global hair volumes and hair alignment. These features were assessed at three time points: t0 (no treatment), t1 (two treatments) and t2 (three treatments). Classifier tests were applied to test the accuracy of the machine learning. A sensory test (paired comparison of t0 vs t2) and an online front image-based survey (paired comparison of t0 vs t1, t1 vs t2, t0 vs t2) were conducted to compare human assessment with that of the algorithms.
- Results : The automatic image analysis identified changes to hair volume and alignment which enabled the successful application of the classification tests, especially when the hair images were grouped into untreated and treated groups. The human assessment of hair presented in pairs confirmed the automatic image analysis. The image assessment for both virgin hair and bleached only partially agreed with the analysis of the subset of images used in the online survey. One hypothesis is that treatments changed somewhat the shape of the hair tress, with the effect being more pronounced in bleached hair. This made human assessment of flat images more challenging than when viewed directly in 3D. Overall, the bleached hair exhibited effects of higher magnitude than the virgin hair.
- Conclusions : This study illustrated the capacity of artificial intelligence for hair image detection and classification, and for image analysis of hair assembly features following treatments. The human assessment partially confirmed the image analysis and highlighted the challenges imposed by the presentation mode. |
| Note de contenu : |
- Hair assembly volume, alignment and flyaway
- Hair assembly properties and Artificial Intelligence
- MATERIALS AND METHODS : Hair tresses and treatment - Image dataset - Automatic hair segmentation - Automatic quantification of hair assembly features - Timepoint recognition on single hair images with AI - Online paired image-comparison test with naïve assessors (n = 100) - Paired difference test with naïve assessors )n = 50) - Statistical analysis
- RESULTS : Hair volume analysis - Fibre alignment analysis - Machine learning: treatment order test - Machine learning : timepoint recognition - Online paired image-comparison test : image analysis - Online paired image-comparison test : human assessment - Visual paired difference test
- DISCUSSION : Image data analysis and machine learning - Classifiers tests - The online survey and AI - Visual paired difference test
- Table 1 : Global and local hair volumes for the three time points of the training data set
- Table 2 : Fibre alignment indices for three time points of the training data set
- Table 3 : Confusion matrices. Correct results in bold
- Table 4 : Results of the online paired image-comparison test
- Table 5 : Fibre alignment indices for the selected image subset used in the online survey, based on three images for each tress
- Table 6 : Results of the online paired image-comparison test
- Table 7 : Volume and hair straightness comparisons between the different time points reported in the survey (Table 6) and their agreement with AI-generated GHV
- Table 8 : Results of the visual paired difference test (n = 50 responses) |
| DOI : |
https://doi.org/10.1111/ics.12706 |
| En ligne : |
https://drive.google.com/file/d/1RnhXaRtILFJxcQM1zyk09SH7pQcXM1Mh/view?usp=shari [...] |
| Format de la ressource électronique : |
Pdf |
| Permalink : |
https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36675 |
in INTERNATIONAL JOURNAL OF COSMETIC SCIENCE > Vol. 43, N° 4 (08/2021) . - p. 405-418
[article]
|
Aller sur edunet
Accueil
Artificial Intelligence in hair research : A proof-of-concept study on evaluating hair assembly features in INTERNATIONAL JOURNAL OF COSMETIC SCIENCE, Vol. 43, N° 4 (08/2021)
