Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement
We propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state-of-the-art approaches for body measurement from point clouds...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/1885 |
| _version_ | 1797473718211969024 |
|---|---|
| author | Kristijan Bartol David Bojanić Tomislav Petković Stanislav Peharec Tomislav Pribanić |
| author_facet | Kristijan Bartol David Bojanić Tomislav Petković Stanislav Peharec Tomislav Pribanić |
| author_sort | Kristijan Bartol |
| collection | DOAJ |
| description | We propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state-of-the-art approaches for body measurement from point clouds and images, demonstrate the comparable performance with the best methods, and even outperform several deep learning models on public datasets. The simplicity of the proposed regression model makes it perfectly suitable as a baseline in addition to the convenience for applications such as the virtual try-on. To improve the repeatability of the results of our baseline and the competing methods, we provide guidelines toward standardized body measurement estimation. |
| first_indexed | 2024-03-09T20:21:24Z |
| format | Article |
| id | doaj.art-721bd8fc235c42c8aefd73f61f0612f8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T20:21:24Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-721bd8fc235c42c8aefd73f61f0612f82023-11-23T23:47:45ZengMDPI AGSensors1424-82202022-02-01225188510.3390/s22051885Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body MeasurementKristijan Bartol0David Bojanić1Tomislav Petković2Stanislav Peharec3Tomislav Pribanić4Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, CroatiaPeharec Polyclinic for Physical Medicine and Rehabilitation, 52100 Pula, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, CroatiaWe propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state-of-the-art approaches for body measurement from point clouds and images, demonstrate the comparable performance with the best methods, and even outperform several deep learning models on public datasets. The simplicity of the proposed regression model makes it perfectly suitable as a baseline in addition to the convenience for applications such as the virtual try-on. To improve the repeatability of the results of our baseline and the competing methods, we provide guidelines toward standardized body measurement estimation.https://www.mdpi.com/1424-8220/22/5/1885body measurementlinear regressionstatistical modelsanthropometrySMPLshape estimation |
| spellingShingle | Kristijan Bartol David Bojanić Tomislav Petković Stanislav Peharec Tomislav Pribanić Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement Sensors body measurement linear regression statistical models anthropometry SMPL shape estimation |
| title | Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement |
| title_full | Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement |
| title_fullStr | Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement |
| title_full_unstemmed | Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement |
| title_short | Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement |
| title_sort | linear regression vs deep learning a simple yet effective baseline for human body measurement |
| topic | body measurement linear regression statistical models anthropometry SMPL shape estimation |
| url | https://www.mdpi.com/1424-8220/22/5/1885 |
| work_keys_str_mv | AT kristijanbartol linearregressionvsdeeplearningasimpleyeteffectivebaselineforhumanbodymeasurement AT davidbojanic linearregressionvsdeeplearningasimpleyeteffectivebaselineforhumanbodymeasurement AT tomislavpetkovic linearregressionvsdeeplearningasimpleyeteffectivebaselineforhumanbodymeasurement AT stanislavpeharec linearregressionvsdeeplearningasimpleyeteffectivebaselineforhumanbodymeasurement AT tomislavpribanic linearregressionvsdeeplearningasimpleyeteffectivebaselineforhumanbodymeasurement |