Abstract
The non-destructive recognition of coated seeds is crucial for advancing studies in coating theory. Currently, the recognition of coated seeds heavily relies on manual visual inspection and machine vision detection. However, these methods pose challenges such as high misclassification rates, low recognition efficiency, and elevated labor intensity. In response to the aforementioned challenges, this study leveraged deep learning techniques to develop a coated seed recognition model named YOLO-Coated Seeds Recognition (YOLO-CSR), aiming to address the challenges posed by coated seed recognition tasks. The experiment of this study mainly includes the following steps: First, a seed coating machine was set up to coat red clover seeds, resulting in three types of coated red clover seeds. Subsequently, by collecting images of the three types of coated seeds, a coated seed image dataset was further constructed. Then, the YOLOv5s was built, incorporating the Convolutional Block Attention Module (CBAM) into the model’s backbone to enhance its ability to learn features of coated seeds. Finally, the training results of YOLO-CSR were compared with those of other classical recognition models. The experimental results showed that YOLO-CSR achieved the best recognition performance on the self-built coated seed image dataset. The average precision (AP) for recognizing the three types of coated seeds reached 98.43%, 97.91%, and 97.26%, with a mean average precision@0.5 (mAP@0.5) of 97.87%. Compared to YOLOv5, YOLO-CSR showed a 1.18% improvement in mAP@0.5. Additionally, YOLO-CSR has a model size of only 14.9 MB, with an average recognition time (ART) of 10.1 ms and a frame per second (FPS) of 99. Experimental results prove that YOLO-CSR can accurately, efficiently, and rapidly recognize coated red clover seeds. The findings of this study provide technical support for the non-destructive recognition of spherical coated seeds. Keywords: coated seed recognition, red clover seed, YOLO; Attention Module, CNNs DOI: 10.25165/j.ijabe.20231606.7773 Citation: Zhang X W, Xuan C Z, Hou Z F. Recognition model for coated red clover seeds using YOLOv5s optimized with an attention module. Int J Agric & Biol Eng, 2023; 16(6): 207–214.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 9
Claim · model-written summary
YOLO-CSR achieved the best recognition performance on the self-built coated seed image dataset compared with other classical recognition models.
- Taxon
- red clover
Trifolium pratenset0 - Outcome
- recognition performancee2
- Direction
- beste2
- Comparator
- other classical recognition modelse3
- Setting
- self-built coated seed image datasete2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e2“YOLO-CSR achieved the best recognition performance on the self-built coated seed image dataset”
e3“the training results of YOLO-CSR were compared with those of other classical recognition models”
Claim · model-written summary
Average precision for one of the three coated seed types reached 98.43%.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- average precision (AP)e1
- Value
- 98.43%e1
- Qualifier
- three types of coated seedse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e1“The average precision (AP) for recognizing the three types of coated seeds reached 98.43%, 97.91%, and 97.26%”
Claim · model-written summary
Average precision for one of the three coated seed types reached 97.91%.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- average precision (AP)e1
- Value
- 97.91%e1
- Qualifier
- three types of coated seedse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e1“The average precision (AP) for recognizing the three types of coated seeds reached 98.43%, 97.91%, and 97.26%”
Claim · model-written summary
Average precision for one of the three coated seed types reached 97.26%.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- average precision (AP)e1
- Value
- 97.26%e1
- Qualifier
- three types of coated seedse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e1“The average precision (AP) for recognizing the three types of coated seeds reached 98.43%, 97.91%, and 97.26%”
Claim · model-written summary
Mean average precision at 0.5 reached 97.87%.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- mean average precision@0.5 (mAP@0.5)e4
- Value
- 97.87%e4
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e4“a mean average precision@0.5 (mAP@0.5) of 97.87%”
Claim · model-written summary
YOLO-CSR improved mAP@0.5 by 1.18% compared with YOLOv5.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- mAP@0.5e5
- Direction
- improvemente5
- Value
- 1.18%e5
- Comparator
- YOLOv5e5
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e5“Compared to YOLOv5, YOLO-CSR showed a 1.18% improvement in mAP@0.5”
Claim · model-written summary
YOLO-CSR has a model size of 14.9 MB.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- model sizee6
- Value
- 14.9 MBe6
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e6“YOLO-CSR has a model size of only 14.9 MB”
Claim · model-written summary
YOLO-CSR has an average recognition time of 10.1 ms.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- average recognition time (ART)e7
- Value
- 10.1 mse7
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e7“with an average recognition time (ART) of 10.1 ms and a frame per second (FPS) of 99”
Claim · model-written summary
YOLO-CSR runs at a frame per second of 99.
- Taxon
- red cloverTrifolium pratenset0
- Outcome
- frame per second (FPS)e7
- Value
- 99e7
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“coated red clover seeds”
e7“with an average recognition time (ART) of 10.1 ms and a frame per second (FPS) of 99”