Open AccessSewing gesture image detection method based on improved SSD model
Author(s) -
Wang Wenjie,
He Mengling,
Wang Xiaohua,
Yao Weiming
Publication year - 2021
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/ell2.12149
Subject(s) - computer science , pyramid (geometry) , artificial intelligence , gesture , residual , feature (linguistics) , economic shortage , set (abstract data type) , computer vision , detector , data set , feature extraction , pattern recognition (psychology) , algorithm , mathematics , telecommunications , linguistics , philosophy , geometry , government (linguistics) , programming language
In this letter, the authors present a novel sewing gesture image detection method based on an improved single shot MultiBox detector (SSD) model. The deeper Resnet50 residual network replaces the VGG16 basic network of the original SSD model to improve the feature extraction ability. High and low level features are fused based on a feature pyramid network (FPN) for enhanced small‐target detection performance. The model is trained via transfer learning to resolve the small sample shortage problem. The proposed model shows an average precision of 88.69% on a sewing gesture data set constructed by the authors. The proposed model outperforms the Faster R‐CNN, YOLO, and SSD networks in terms of accuracy with acceptable operating speed on the same data set and fully satisfies the real‐time requirements for sewing gesture detection.