SW-YOLO: improved YOLOv5s algorithm for blood cell detection

Yonglin Wu; Yinfeng Fang; Dongxu Gao; Hongwei Gao; Zhaojie Ju

doi:10.1007/978-981-99-6489-5_13

SW-YOLO: improved YOLOv5s algorithm for blood cell detection

Yonglin Wu, Yinfeng Fang, Dongxu Gao, Hongwei Gao, Zhaojie Ju

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Downloads (Pure)

Abstract

This paper proposes an improved target detection algorithm SW-YOLO based on the YOLOv5s framework to solve the problems of low detection accuracy, wrong detection and missed detection in blood cell detection tasks. To begin with, the end of the backbone network is fused with Swin Transformer to improve network feature extraction. Next, since blood cells are mostly small and medium-sized targets, resulting in poor detection of large cells, the network layer that identifies large cells is removed. In addition, the normal convolution in the PANet network is replaced with depth-separable convolution during the feature fusion process to ensure the accuracy and real-time detection while having better detection results for small targets. At last, the loss function of the prediction layer uses EIOU to solve the positive and negative sample imbalance problem of CIOU. Compared with existing target detection algorithms such as Faster-RCNN, YOLOv4 and YOLOv5s, SW-YOLO improves to 99.5%, 95.3% and 93.3% mAP on the blood cell dataset BCCD for white blood cells, red blood cells and platelets respectively. The experimental results are eximious and the algorithm is highly practical for blood cell detection.

Original language	English
Title of host publication	Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III
Editors	Huayong Yang, Honghai Liu, Jun Zou, Zhouping Yin, Lianqing Liu, Geng Yang, Xiaoping Ouyang, Zhiyong Wang
Publisher	Springer
Pages	161-172
Number of pages	12
ISBN (Electronic)	9789819964895
ISBN (Print)	9789819964888
DOIs	https://doi.org/10.1007/978-981-99-6489-5_13
Publication status	Published - 11 Oct 2023
Event	International Conference on Intelligent Robotics and Applications - Hangzhou, China Duration: 5 Jul 2023 → 7 Jul 2023

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	14269
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name	Lecture Notes in Artificial Intelligence
Publisher	Springer
ISSN (Print)	2945-9133
ISSN (Electronic)	2945-9141

Conference

Conference	International Conference on Intelligent Robotics and Applications
Country/Territory	China
City	Hangzhou
Period	5/07/23 → 7/07/23

Keywords

blood cells testing
Swin Transformer
PAN
EIOU

Access to Document

10.1007/978-981-99-6489-5_13

Final_paper_343_Yonglin_Wu_1_
This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/978-981-99-6489-5_13.
Accepted author manuscript (Post-print), 1.92 MB

Cite this

Wu, Y., Fang, Y., Gao, D., Gao, H., & Ju, Z. (2023). SW-YOLO: improved YOLOv5s algorithm for blood cell detection. In H. Yang, H. Liu, J. Zou, Z. Yin, L. Liu, G. Yang, X. Ouyang, & Z. Wang (Eds.), Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III (pp. 161-172). (Lecture Notes in Computer Science; Vol. 14269), (Lecture Notes in Artificial Intelligence). Springer. https://doi.org/10.1007/978-981-99-6489-5_13

Wu, Yonglin ; Fang, Yinfeng ; Gao, Dongxu et al. / SW-YOLO: improved YOLOv5s algorithm for blood cell detection. Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III. editor / Huayong Yang ; Honghai Liu ; Jun Zou ; Zhouping Yin ; Lianqing Liu ; Geng Yang ; Xiaoping Ouyang ; Zhiyong Wang. Springer, 2023. pp. 161-172 (Lecture Notes in Computer Science). (Lecture Notes in Artificial Intelligence).

@inproceedings{486b155a2f92427cb020338bc790e8bb,

title = "SW-YOLO: improved YOLOv5s algorithm for blood cell detection",

abstract = "This paper proposes an improved target detection algorithm SW-YOLO based on the YOLOv5s framework to solve the problems of low detection accuracy, wrong detection and missed detection in blood cell detection tasks. To begin with, the end of the backbone network is fused with Swin Transformer to improve network feature extraction. Next, since blood cells are mostly small and medium-sized targets, resulting in poor detection of large cells, the network layer that identifies large cells is removed. In addition, the normal convolution in the PANet network is replaced with depth-separable convolution during the feature fusion process to ensure the accuracy and real-time detection while having better detection results for small targets. At last, the loss function of the prediction layer uses EIOU to solve the positive and negative sample imbalance problem of CIOU. Compared with existing target detection algorithms such as Faster-RCNN, YOLOv4 and YOLOv5s, SW-YOLO improves to 99.5%, 95.3% and 93.3% mAP on the blood cell dataset BCCD for white blood cells, red blood cells and platelets respectively. The experimental results are eximious and the algorithm is highly practical for blood cell detection.",

keywords = "blood cells testing, Swin Transformer, PAN, EIOU",

author = "Yonglin Wu and Yinfeng Fang and Dongxu Gao and Hongwei Gao and Zhaojie Ju",

year = "2023",

month = oct,

day = "11",

doi = "10.1007/978-981-99-6489-5_13",

language = "English",

isbn = "9789819964888",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "161--172",

editor = "Huayong Yang and Honghai Liu and Jun Zou and Zhouping Yin and Lianqing Liu and Geng Yang and Xiaoping Ouyang and Zhiyong Wang",

booktitle = "Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III",

note = "International Conference on Intelligent Robotics and Applications ; Conference date: 05-07-2023 Through 07-07-2023",

}

Wu, Y, Fang, Y, Gao, D, Gao, H & Ju, Z 2023, SW-YOLO: improved YOLOv5s algorithm for blood cell detection. in H Yang, H Liu, J Zou, Z Yin, L Liu, G Yang, X Ouyang & Z Wang (eds), Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III. Lecture Notes in Computer Science, vol. 14269, Lecture Notes in Artificial Intelligence, Springer, pp. 161-172, International Conference on Intelligent Robotics and Applications, Hangzhou, China, 5/07/23. https://doi.org/10.1007/978-981-99-6489-5_13

SW-YOLO: improved YOLOv5s algorithm for blood cell detection. / Wu, Yonglin; Fang, Yinfeng; Gao, Dongxu et al.
Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III. ed. / Huayong Yang; Honghai Liu; Jun Zou; Zhouping Yin; Lianqing Liu; Geng Yang; Xiaoping Ouyang; Zhiyong Wang. Springer, 2023. p. 161-172 (Lecture Notes in Computer Science; Vol. 14269), (Lecture Notes in Artificial Intelligence).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - SW-YOLO: improved YOLOv5s algorithm for blood cell detection

AU - Wu, Yonglin

AU - Fang, Yinfeng

AU - Gao, Dongxu

AU - Gao, Hongwei

AU - Ju, Zhaojie

PY - 2023/10/11

Y1 - 2023/10/11

N2 - This paper proposes an improved target detection algorithm SW-YOLO based on the YOLOv5s framework to solve the problems of low detection accuracy, wrong detection and missed detection in blood cell detection tasks. To begin with, the end of the backbone network is fused with Swin Transformer to improve network feature extraction. Next, since blood cells are mostly small and medium-sized targets, resulting in poor detection of large cells, the network layer that identifies large cells is removed. In addition, the normal convolution in the PANet network is replaced with depth-separable convolution during the feature fusion process to ensure the accuracy and real-time detection while having better detection results for small targets. At last, the loss function of the prediction layer uses EIOU to solve the positive and negative sample imbalance problem of CIOU. Compared with existing target detection algorithms such as Faster-RCNN, YOLOv4 and YOLOv5s, SW-YOLO improves to 99.5%, 95.3% and 93.3% mAP on the blood cell dataset BCCD for white blood cells, red blood cells and platelets respectively. The experimental results are eximious and the algorithm is highly practical for blood cell detection.

AB - This paper proposes an improved target detection algorithm SW-YOLO based on the YOLOv5s framework to solve the problems of low detection accuracy, wrong detection and missed detection in blood cell detection tasks. To begin with, the end of the backbone network is fused with Swin Transformer to improve network feature extraction. Next, since blood cells are mostly small and medium-sized targets, resulting in poor detection of large cells, the network layer that identifies large cells is removed. In addition, the normal convolution in the PANet network is replaced with depth-separable convolution during the feature fusion process to ensure the accuracy and real-time detection while having better detection results for small targets. At last, the loss function of the prediction layer uses EIOU to solve the positive and negative sample imbalance problem of CIOU. Compared with existing target detection algorithms such as Faster-RCNN, YOLOv4 and YOLOv5s, SW-YOLO improves to 99.5%, 95.3% and 93.3% mAP on the blood cell dataset BCCD for white blood cells, red blood cells and platelets respectively. The experimental results are eximious and the algorithm is highly practical for blood cell detection.

KW - blood cells testing

KW - Swin Transformer

KW - PAN

KW - EIOU

U2 - 10.1007/978-981-99-6489-5_13

DO - 10.1007/978-981-99-6489-5_13

M3 - Conference contribution

SN - 9789819964888

T3 - Lecture Notes in Computer Science

SP - 161

EP - 172

BT - Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III

A2 - Yang, Huayong

A2 - Liu, Honghai

A2 - Zou, Jun

A2 - Yin, Zhouping

A2 - Liu, Lianqing

A2 - Yang, Geng

A2 - Ouyang, Xiaoping

A2 - Wang, Zhiyong

PB - Springer

T2 - International Conference on Intelligent Robotics and Applications

Y2 - 5 July 2023 through 7 July 2023

ER -

Wu Y, Fang Y, Gao D, Gao H, Ju Z. SW-YOLO: improved YOLOv5s algorithm for blood cell detection. In Yang H, Liu H, Zou J, Yin Z, Liu L, Yang G, Ouyang X, Wang Z, editors, Intelligent Robotics and Applications 16th International Conference, ICIRA 2023, Hangzhou, China, July 5–7, 2023, Proceedings, Part III. Springer. 2023. p. 161-172. (Lecture Notes in Computer Science). (Lecture Notes in Artificial Intelligence). doi: 10.1007/978-981-99-6489-5_13

SW-YOLO: improved YOLOv5s algorithm for blood cell detection

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this