Missing body measurements prediction in fashion industry: a comparative approach
Abstract The use of artificial intelligence to predict body dimensions rather than measuring them by stylists or 3D scanners permits to obtain easily all measurements of individual consumers and can consequently reduce costs of population survey campaigns. In this paper, we have compared several mod...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-10-01
|
| Series: | Fashion and Textiles |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40691-023-00357-5 |
| _version_ | 1797578028332613632 |
|---|---|
| author | Philippe Meyer Babiga Birregah Pierre Beauseroy Edith Grall Audrey Lauxerrois |
| author_facet | Philippe Meyer Babiga Birregah Pierre Beauseroy Edith Grall Audrey Lauxerrois |
| author_sort | Philippe Meyer |
| collection | DOAJ |
| description | Abstract The use of artificial intelligence to predict body dimensions rather than measuring them by stylists or 3D scanners permits to obtain easily all measurements of individual consumers and can consequently reduce costs of population survey campaigns. In this paper, we have compared several models of machine learning to predict about 30 measurements used in fashion industry to construct clothes from 6 easy-to-measure body dimensions and demographic information. The four types of models we have studied are linear regressions, random forests, gradient boosting trees and support vector regressions. To construct and train them we have used anthropometric measurements of 9000 adult individuals of the French population collected by the French Institute of Textiles and Clothing (IFTH) during a national measurement campaign collected between 2003 and 2005. We have analyzed the model prediction performance in terms of individual and global predictions as well as the effect of the training dataset size and the importance of the input features. The linear and the support vector regressions have given the best results with respect to evaluation metrics, predicted distributions and have required less training data than tree-based models. It turns out that the weight and height have been the most important input features for the models considered while the hip girth has been the less important among the input measurements. Since the set of body dimensions used in fashion industry and the morphology depend on the gender, we have decided to treat men and women separately and to compare them. |
| first_indexed | 2024-03-10T22:17:09Z |
| format | Article |
| id | doaj.art-839c3acaff034b6cb6912e02729aea4c |
| institution | Directory Open Access Journal |
| issn | 2198-0802 |
| language | English |
| last_indexed | 2024-03-10T22:17:09Z |
| publishDate | 2023-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Fashion and Textiles |
| spelling | doaj.art-839c3acaff034b6cb6912e02729aea4c2023-11-19T12:24:43ZengSpringerOpenFashion and Textiles2198-08022023-10-0110111710.1186/s40691-023-00357-5Missing body measurements prediction in fashion industry: a comparative approachPhilippe Meyer0Babiga Birregah1Pierre Beauseroy2Edith Grall3Audrey Lauxerrois4Computer Science and Digital Society Laboratory (LIST3N), Université de Technologie de TroyesComputer Science and Digital Society Laboratory (LIST3N), Université de Technologie de TroyesComputer Science and Digital Society Laboratory (LIST3N), Université de Technologie de TroyesComputer Science and Digital Society Laboratory (LIST3N), Université de Technologie de TroyesFrench Institute of Textiles and ClothingAbstract The use of artificial intelligence to predict body dimensions rather than measuring them by stylists or 3D scanners permits to obtain easily all measurements of individual consumers and can consequently reduce costs of population survey campaigns. In this paper, we have compared several models of machine learning to predict about 30 measurements used in fashion industry to construct clothes from 6 easy-to-measure body dimensions and demographic information. The four types of models we have studied are linear regressions, random forests, gradient boosting trees and support vector regressions. To construct and train them we have used anthropometric measurements of 9000 adult individuals of the French population collected by the French Institute of Textiles and Clothing (IFTH) during a national measurement campaign collected between 2003 and 2005. We have analyzed the model prediction performance in terms of individual and global predictions as well as the effect of the training dataset size and the importance of the input features. The linear and the support vector regressions have given the best results with respect to evaluation metrics, predicted distributions and have required less training data than tree-based models. It turns out that the weight and height have been the most important input features for the models considered while the hip girth has been the less important among the input measurements. Since the set of body dimensions used in fashion industry and the morphology depend on the gender, we have decided to treat men and women separately and to compare them.https://doi.org/10.1186/s40691-023-00357-5Artificial intelligenceMachine learningFashion and apparel industryAnthropometric measurementSizing system |
| spellingShingle | Philippe Meyer Babiga Birregah Pierre Beauseroy Edith Grall Audrey Lauxerrois Missing body measurements prediction in fashion industry: a comparative approach Fashion and Textiles Artificial intelligence Machine learning Fashion and apparel industry Anthropometric measurement Sizing system |
| title | Missing body measurements prediction in fashion industry: a comparative approach |
| title_full | Missing body measurements prediction in fashion industry: a comparative approach |
| title_fullStr | Missing body measurements prediction in fashion industry: a comparative approach |
| title_full_unstemmed | Missing body measurements prediction in fashion industry: a comparative approach |
| title_short | Missing body measurements prediction in fashion industry: a comparative approach |
| title_sort | missing body measurements prediction in fashion industry a comparative approach |
| topic | Artificial intelligence Machine learning Fashion and apparel industry Anthropometric measurement Sizing system |
| url | https://doi.org/10.1186/s40691-023-00357-5 |
| work_keys_str_mv | AT philippemeyer missingbodymeasurementspredictioninfashionindustryacomparativeapproach AT babigabirregah missingbodymeasurementspredictioninfashionindustryacomparativeapproach AT pierrebeauseroy missingbodymeasurementspredictioninfashionindustryacomparativeapproach AT edithgrall missingbodymeasurementspredictioninfashionindustryacomparativeapproach AT audreylauxerrois missingbodymeasurementspredictioninfashionindustryacomparativeapproach |