Tea Sprouts Segmentation via Improved Deep Convolutional Encoder-Decoder Network
Summary :
Tea sprouts segmentation via machine vision is the core technology of tea automatic picking. A novel method for Tea Sprouts Segmentation based on improved deep convolutional encoder-decoder Network (TS-SegNet) is proposed in this paper. In order to increase the segmentation accuracy and stability, the improvement is carried out by a contrastive-center loss function and skip connections. Therefore, the intra-class compactness and inter-class separability are comprehensively utilized, and the TS-SegNet can obtain more discriminative tea sprouts features. The experimental results indicate that the proposed method leads to good segmentation results, and the segmented tea sprouts are almost coincident with the ground truth.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.2 pp.476-479
- Publication Date
- 2020/02/01
- Publicized
- 2019/11/06
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019EDL8147
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Chunhua QIAN
Nanjing Forestry University,Suzhou Polytechnic Institute of Agriculture, Suzhou
Mingyang LI
Nanjing Forestry University
Yi REN
Suzhou Polytechnic Institute of Agriculture, Suzhou
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chunhua QIAN, Mingyang LI, Yi REN, "Tea Sprouts Segmentation via Improved Deep Convolutional Encoder-Decoder Network" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 2, pp. 476-479, February 2020, doi: 10.1587/transinf.2019EDL8147.
Abstract: Tea sprouts segmentation via machine vision is the core technology of tea automatic picking. A novel method for Tea Sprouts Segmentation based on improved deep convolutional encoder-decoder Network (TS-SegNet) is proposed in this paper. In order to increase the segmentation accuracy and stability, the improvement is carried out by a contrastive-center loss function and skip connections. Therefore, the intra-class compactness and inter-class separability are comprehensively utilized, and the TS-SegNet can obtain more discriminative tea sprouts features. The experimental results indicate that the proposed method leads to good segmentation results, and the segmented tea sprouts are almost coincident with the ground truth.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8147/_p
Copy
@ARTICLE{e103-d_2_476,
author={Chunhua QIAN, Mingyang LI, Yi REN, },
journal={IEICE TRANSACTIONS on Information},
title={Tea Sprouts Segmentation via Improved Deep Convolutional Encoder-Decoder Network},
year={2020},
volume={E103-D},
number={2},
pages={476-479},
abstract={Tea sprouts segmentation via machine vision is the core technology of tea automatic picking. A novel method for Tea Sprouts Segmentation based on improved deep convolutional encoder-decoder Network (TS-SegNet) is proposed in this paper. In order to increase the segmentation accuracy and stability, the improvement is carried out by a contrastive-center loss function and skip connections. Therefore, the intra-class compactness and inter-class separability are comprehensively utilized, and the TS-SegNet can obtain more discriminative tea sprouts features. The experimental results indicate that the proposed method leads to good segmentation results, and the segmented tea sprouts are almost coincident with the ground truth.},
keywords={},
doi={10.1587/transinf.2019EDL8147},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Tea Sprouts Segmentation via Improved Deep Convolutional Encoder-Decoder Network
T2 - IEICE TRANSACTIONS on Information
SP - 476
EP - 479
AU - Chunhua QIAN
AU - Mingyang LI
AU - Yi REN
PY - 2020
DO - 10.1587/transinf.2019EDL8147
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2020
AB - Tea sprouts segmentation via machine vision is the core technology of tea automatic picking. A novel method for Tea Sprouts Segmentation based on improved deep convolutional encoder-decoder Network (TS-SegNet) is proposed in this paper. In order to increase the segmentation accuracy and stability, the improvement is carried out by a contrastive-center loss function and skip connections. Therefore, the intra-class compactness and inter-class separability are comprehensively utilized, and the TS-SegNet can obtain more discriminative tea sprouts features. The experimental results indicate that the proposed method leads to good segmentation results, and the segmented tea sprouts are almost coincident with the ground truth.
ER -
English
