Damien Lefloch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Damien Lefloch has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Aichun Wang
Tiangong University , Tianjin , China
1 shared publication- Heng Zhao
Shenzhen Technology University
1 shared publication Jianming Wang
School of Computer Science and Technology, Tiangong University, China
1 shared publication- Jianming Wang
Tiangong University
1 shared publication Jun Xu
School of Textile Science and Engineering, Tiangong University, China
1 shared publication- Jun Xu
School of Textile Science and Engineering, Tiangong University, Tianjin, China
1 shared publication
Latest Publications
- Open Access
- 1 October 2022
- Published by Walter de Gruyter GmbH in Fibres & Textiles in Eastern Europe
- Vol. 30 (5) , 66-78
Analysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models
Clothing image in the e-commerce industry plays an important role in providing customers with information. This paper divides clothing images into two groups: pure clothing images and dressed clothing images. Targeting small and medium-sized clothing companies or merchants, it compares traditional machine learning and deep learning models to determine suitable models for each group. For pure clothing images, the HOG+SVM algorithm with the Gaussian kernel function obtains the highest classification accuracy of 91.32% as compared to the Small VGG network. For dressed clothing images, the CNN model obtains a higher accuracy than the HOG+SVM algorithm, with the highest accuracy rate of 69.78% for the Small VGG network. Therefore, for end-users with only ordinary computing processors, it is recommended to apply the traditional machine learning algorithm HOG+SVM to classify pure clothing images. The classification of dressed clothing images is performed using a more efficient and less computationally intensive lightweight model, such as the Small VGG network.
- 1 October 2022
- Published by Walter de Gruyter GmbH in Fibres & Textiles in Eastern Europe
- Vol. 30 (5) , 66-78
Open AccessAnalysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models
Clothing image in the e-commerce industry plays an important role in providing customers with information. This paper divides clothing images into two groups: pure clothing images and dressed clothing images. Targeting small and medium-sized clothing companies or merchants, it compares traditional machine learning and deep learning models to determine suitable models for each group. For pure clothing images, the HOG+SVM algorithm with the Gaussian kernel function obtains the highest classification accuracy of 91.32% as compared to the Small VGG network. For dressed clothing images, the CNN model obtains a higher accuracy than the HOG+SVM algorithm, with the highest accuracy rate of 69.78% for the Small VGG network. Therefore, for end-users with only ordinary computing processors, it is recommended to apply the traditional machine learning algorithm HOG+SVM to classify pure clothing images. The classification of dressed clothing images is performed using a more efficient and less computationally intensive lightweight model, such as the Small VGG network.
- 8 July 2021
- Published by River Publishers in Journal of Web Engineering
- Vol. 20 (4) , 1177-1188
A Deep Convolutional Neural Network to Limit Virus Spread Using Facial Mask Segmentation
Due to the recent COVID-19 outbreak the world has experienced many challenges. Limit and control the virus spread rate is one of them. This letter focuses on limiting the speed of virus spreading by monitoring the use of facial mask in crowded public environments such as tourism places, commercial centres, etc. The proposed method first accurately localizes faces using a state-of-the-art approach and, segments facial mask in a second step. The facial mask segmentation allows to distinguish whether the current subject is wearing a facial mask or not but also if it is properly covering the human face. Indeed, most recent face detection algorithms provide as output a set of facial features such as nose tip and mouth corners. By combining these facial features with facial mask segmentation, the proposed method detects real-time subjects that indirectly encourage virus spread in crowded environments. The proposed facial mask segmentation model is trained with pairs of RGB images and its corresponding alpha image created by extending the publicly available real-world masked face dataset. Further, the proposed model is pruned and optimized using the TensorRt library to be usable for real-world applications.
- 8 July 2021
- Published by River Publishers in Journal of Web Engineering
- Vol. 20 (4) , 1177-1188
A Deep Convolutional Neural Network to Limit Virus Spread Using Facial Mask Segmentation
Due to the recent COVID-19 outbreak the world has experienced many challenges. Limit and control the virus spread rate is one of them. This letter focuses on limiting the speed of virus spreading by monitoring the use of facial mask in crowded public environments such as tourism places, commercial centres, etc. The proposed method first accurately localizes faces using a state-of-the-art approach and, segments facial mask in a second step. The facial mask segmentation allows to distinguish whether the current subject is wearing a facial mask or not but also if it is properly covering the human face. Indeed, most recent face detection algorithms provide as output a set of facial features such as nose tip and mouth corners. By combining these facial features with facial mask segmentation, the proposed method detects real-time subjects that indirectly encourage virus spread in crowded environments. The proposed facial mask segmentation model is trained with pairs of RGB images and its corresponding alpha image created by extending the publicly available real-world masked face dataset. Further, the proposed model is pruned and optimized using the TensorRt library to be usable for real-world applications.
- 20 June 2021
- Published by SAGE Publications in Textile Research Journal
- Vol. 91 (23-24) , 2980-2994
Sportswear retailing forecast model based on the combination of multi-layer perceptron and convolutional neural network
Apparel sales forecasting plays an important role in production planning, distribution decision, and inventory management of enterprises. Especially, the sportswear market has been shown rapid growth characterized by long-term sales. This paper proposes a sales forecasting model for sportswear sales based on the multi-layer perceptron (MLP) and the convolutional neural network (CNN). A novel loss function is also proposed to improve the prediction accuracy. The proposed model is trained and validated on the time-series retailing data collected from three offline local sports stores in China. The influencing factors of retailing forecasting, such as time-series sales data, product features, distribution strategy, shop size, and other parameters, were also defined. Experimental results show that the proposed forecasting model outperforms the compared statistical methods by a large margin. Specifically, the proposed model provided 65% prediction accuracy, while the compared methods provided 16% prediction accuracy. The results show that the proposed model could be potentially used in sportswear sales forecasting, especially offline clothing and other long lifecycle clothing fields.
- 20 June 2021
- Published by SAGE Publications in Textile Research Journal
- Vol. 91 (23-24) , 2980-2994
Sportswear retailing forecast model based on the combination of multi-layer perceptron and convolutional neural network
Apparel sales forecasting plays an important role in production planning, distribution decision, and inventory management of enterprises. Especially, the sportswear market has been shown rapid growth characterized by long-term sales. This paper proposes a sales forecasting model for sportswear sales based on the multi-layer perceptron (MLP) and the convolutional neural network (CNN). A novel loss function is also proposed to improve the prediction accuracy. The proposed model is trained and validated on the time-series retailing data collected from three offline local sports stores in China. The influencing factors of retailing forecasting, such as time-series sales data, product features, distribution strategy, shop size, and other parameters, were also defined. Experimental results show that the proposed forecasting model outperforms the compared statistical methods by a large margin. Specifically, the proposed model provided 65% prediction accuracy, while the compared methods provided 16% prediction accuracy. The results show that the proposed model could be potentially used in sportswear sales forecasting, especially offline clothing and other long lifecycle clothing fields.