Research on Crab Grading Detection and Recognition Method Based on YOLOv11.

Saved in:

Bibliographic Details
Title:	Research on Crab Grading Detection and Recognition Method Based on YOLOv11.
Authors:	Kang, Jie¹ kang_jie@sju.edu.cn, Chen, Xiaoying¹ 77788489@qq.com
Source:	Engineering Letters. Jul2026, Vol. 34 Issue 7, p2617-2623. 7p.
Subjects:	Convolutional neural networks, Object recognition (Computer vision)
Abstract:	An improved detection method based on YOLOv11 is proposed for the gender identification and size detection of crabs. The Convolutional Block Attention Module (CBAM) and its variants are integrated into the constructed detection model. By adaptively assigning weights to feature maps in both the channel and spatial dimensions, the feature representation capability of the underlying convolutional neural network (CNN) is dynamically enhanced via the CBAM module. On this basis, an improved YOLOv11 model tailored for crab gender identification and size detection is established. Experimental results validate that the key performance indicators of the improved model are significantly enhanced. Specifically, the precision of bounding box detection is increased by 0.23% points. The results demonstrate that both the detection accuracy and inference speed of the proposed model are simultaneously improved for crab size measurement. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	An improved detection method based on YOLOv11 is proposed for the gender identification and size detection of crabs. The Convolutional Block Attention Module (CBAM) and its variants are integrated into the constructed detection model. By adaptively assigning weights to feature maps in both the channel and spatial dimensions, the feature representation capability of the underlying convolutional neural network (CNN) is dynamically enhanced via the CBAM module. On this basis, an improved YOLOv11 model tailored for crab gender identification and size detection is established. Experimental results validate that the key performance indicators of the improved model are significantly enhanced. Specifically, the precision of bounding box detection is increased by 0.23% points. The results demonstrate that both the detection accuracy and inference speed of the proposed model are simultaneously improved for crab size measurement. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X