改进YOLOv5的白细胞检测算法

doi:10.3778/j.issn.1002-8331.2107-0332

摘要/Abstract

摘要： 针对白细胞数据样本少、类间差别小及目标尺寸小导致的检测精度低、效果不佳等问题，提出一种基于改进YOLOv5的白细胞检测算法YOLOv5-CHE。在主干特征提取网络的卷积层中添加坐标注意力机制，以提升算法的特征提取能力；使用四尺度特征检测，重新获取锚点框，增加浅层检测尺度，来提高小目标的识别精度；改变边框回归损失函数，以提升检验框检测的准确率。实验结果表明，对比标准的YOLOv5算法，YOLOv5-CHE算法的平均精度均值（mean average precision，mAP）、精准率和召回率分别提升了3.8个百分点、1.8个百分点和1.5个百分点，验证了该算法对白细胞检测具有很好的效果。

关键词: 白细胞检测, YOLOv5算法, 坐标注意力机制, 四尺度特征检测, 损失函数

Abstract: Aiming at the problems of low accuracy and poor effect caused by small white blood cell data samples, small difference between classes and small target size, this paper proposes a white blood cell detection algorithm YOLOv5-CHE based on improved YOLOv5. Firstly, coordinate attention mechanism is added to the convolutional layer of the backbone feature extraction network to improve the feature extraction capability of the algorithm. Secondly, the purpose of using four-scale feature detection and reacquiring anchor point frame is to increase the detection scale of shallow layer and improve the recognition accuracy of small targets. Finally, the purpose of changing the bounding box regression loss function is to improve the accuracy of check box detection. Experimental results show that the mean average precision（mAP）, precision and recall of YOLOv5-CHE are improved by 3.8 percentage points, 1.8 percentage points and 1.5 percentage points in comparison with the benchmark YOLOv5 algorithm, respectively, which shows that the proposed algorithm is effective for leukocyte detection.

Key words: leukocyte detection, YOLOv5 algorithm, coordinate attention mechanism, four-scale feature detection, loss function

王静, 孙紫雲, 郭苹, 张龙妹. 改进YOLOv5的白细胞检测算法[J]. 计算机工程与应用, 2022, 58(4): 134-142.

WANG Jing, SUN Ziyun, GUO Ping, ZHANG Longmei. Improved Leukocyte Detection Algorithm of YOLOv5[J]. Computer Engineering and Applications, 2022, 58(4): 134-142.

参考文献

[1] 王卫星，苏培垠.基于颜色、梯度矢量流活动轮廓及向量机实现白细胞的提取与分类[J].光学精密工程，2012，20（12）：2781-2790.
WANG W X，SU P Y.Blood cell image segmentation on color and GVF snake for leukocyte classification on SVM[J].Optics and Precision Engineering，2012，20（12）：2781-2790.
[2] 马力，帅仁俊，刘文佳，等.基于改进的残差神经网络的白细胞分类[J].计算机工程与设计，2020，41（10）：2983-2987.
MA L，SHUAI R J，LIU W J，et al.White blood cell classification based on improved residual neural network[J].Computer Engineering and Design，2020，41（10）：2983-2987.
[3] 王亚品，曹益平，付光凯，等.基于深度卷积神经网络的人体外周血白细胞显微图像分类[J].光电子·激光，2019，30（5）：546-555.
WANG Y P，CAO Y P，FU G K，et al.Human peripheral blood leukocyte microscopic image classification based on deep convolutional neural network[J].Journal of Optoelectronics·Laser，2019，30（5）：546-555.
[4] 耿磊，杨盟盟，肖志涛，等.结合通道空间加权特征金字塔网络的白细胞检测与分割[J].计算机辅助设计与图形学学报，2021，33（9）：1418-1427.
GENG L，YANG M M，XIAO Z T，et al.White blood cell detection and segmentation combined with the channel space weighted feature pyramid network[J].Journal of Computer-Aided Design & Computer Graphics，2021，33（9）：1418-1427.
[5] WANG Q W，BI S S，SUN M L，et al.Deep learning approach to peripheral leukocyte recognition[J].PLoS One，2019，14（6）：e0218808.
[6] SHAHIN A，GUO Y，AMIN K，et al.White blood cells identification system based on convolutional deep neural learning networks[J].Computer Methods and Programs in Biomedicine，2019，168（14）：69-80.
[7] LI J，WU J.Leukocyte detection in blood smear image based on improved YOLOv3[C]//Proceedings of the 10th International Workshop on Computer Science and Engineering，2020：144-149.
[8] 杨雪莹.基于深度学习的白细胞分类识别方法研究[D].西安：西安科技大学，2020：46-56.
YANG X Y.Research on the classification method of white blood cells based on deep learning[D].Xi’an：Xi’an University of Science and Technology，2020：46-56.
[9] LIN T Y，DOLLAR P，GIRSHICK R B，et al.Feature pyramid networks for object dettection[C]//Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition，Los Alamitos，2017：936-944.
[10] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[11] 高照.基于深度学习的遥感图像目标检测方法研究[D].青岛：山东科技大学，2020：23-26.
GAO Z.Research on remote sensing image object detection based on deep learning[D].Qingdao：Shandong University of Science and Technology，2020：23-26.
[12] 舒朗，张智杰，雷波.一种针对红外目标检测的Dense-YOLOv5算法研究[J].光学与光电技术，2021，19（1）：69-75.
SU L，ZHANG Z J，LEI B.Research on Dense-YOLOv5 algorithm for infrared target detection[J].Optics & Optoelectronic Technology，2021，19（1）：69-75.
[13] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[J].arXiv：2103.02907v1，2021.
[14] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO：common objects in context[C]//13th European Conference on Computer Vision.Cham：Springer，2014.
[15] ZHENG Z H，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[J].arXiv：1911.08287，2019.
[16] ZHANG Y F，REN W，ZHANG Z，et al.Focal and efficient IOU loss for accurate bounding box regression[J].arXiv：2101.08158v1，2021.
[17] REZATOFIGHI S H，SOLTANIAN-ZADEH H.Automatic recognition of five types of white blood cells in peripheral blood[J].Computerized Medical Imaging & Graphics，2011，35（4）：333-343.
[18] VATATHANAVARO S，TUNGJITNOBAND S，PASUPA K.White blood cell classification：a comparison between VGG-16 and ResNet-50 models[C]//6th Joint Symposium on Computational Intelligence，2018.
[19] 孙凯，姚旭峰，黄钢.基于机器学习的白细胞六分类研究[J].软件，2020，41（10）：98-101.
SUN K，YAO X F，HUANG G.Research on six classification of white blood cells based on machine learning[J].Computer Engineering & Software，2020，41（10）：98-101.