Lijuan Zhang

Prof. Lijuan Zhang

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 July 2023 in Agronomy
Verified
Journal Article
Open access
PDF file
Lijuan ZhangLijuan Zhang
Lijuan Zhang
GDGongcheng Ding
Gongcheng Ding
CLChaoran Li
Chaoran Li
DLDongming Li
Dongming Li
The invasion of agricultural diseases and insect pests is a huge difficulty for the growth of crops. The detection of diseases and pests is a very challenging task. The diversity of diseases and pests in terms of shapes, colors, and sizes, as well as changes in the lighting environment, have a massive impact on the accuracy of the detection results. We improved the C2F module based on DenseBlock and proposed DCF to extract low-level features such as the edge texture of pests and diseases. Through the sensitivity of low-level features to the diversity of pests and diseases, the DCF module can better cope with complex detection tasks and improve the accuracy and robustness of the detection. The complex background environment of pests and diseases and different lighting conditions make the IP102 data set have strong nonlinear characteristics. The Mish activation function is selected to replace the CBS module with the CBM, which can better learn the nonlinear characteristics of the data and effectively solve the problems of gradient disappearance in the algorithm training process. Experiments show that the advanced Yolov8 algorithm has improved. Comparing with Yolov8, our algorithm improves the MAP50 index, Precision index, and Recall index by 2%, 1.3%, and 3.7%. The model in this paper has higher accuracy and versatility.

9 April 2019 in IEEE Access
Verified
Journal Article
Open access
DLDongming Li
Dongming Li
Lijuan ZhangLijuan Zhang
Lijuan Zhang
CSChangming Sun
Changming Sun
TYTingting Yin
Tingting Yin
CLChen Liu
Chen Liu
JYJinhua Yang
Jinhua Yang
Retinal image processing is very important in the field of clinical medicine. As the first step in retinal image processing, image enhancement is essential. Because the details of a retinal image are complex and difficult to enhance, we present a robust retinal image enhancement algorithm via a dual-tree complex wavelet transform (DTCWT) and morphology-based method in this paper. To begin with, we utilize the pre-processing method to the captured retinal images. Then, the DTCWT is applied to decompose the gray retinal image to obtain high-pass subbands and low-pass subbands. Then, a Contourlet-based enhancement method is applied to the high-pass subbands. For the low-pass subbands, we improve the morphology top-hat transform by adding dynamic multi-scale parameters to achieve an equivalent percentage enhancement and at the same time achieve multi-scale transforms in multiple directions. Finally, we develop the inverse DTCWT method to obtain the enhanced retinal image after processing the low-frequency subimages and high-frequency subimages. We compare this approach with enhancement based on the adaptive unsharp masking, histogram equalization, and multi-scale retinex. We present the test results of our algorithm on 440 retinal images from the DRIVE and the STARE databases. The experimental results show that the proposed approach can achieve better results, and might be helpful for vessel segmentation.

12 June 2023 in Agronomy
Verified
Journal Article
Open access
PDF file
Lijuan ZhangLijuan Zhang
Lijuan Zhang
CZCuixing Zhao
Cuixing Zhao
YFYuncong Feng
Yuncong Feng
DLDongming Li
Dongming Li
The development of the agricultural economy is hindered by various pest-related problems. Most pest detection studies only focus on a single pest category, which is not suitable for practical application scenarios. This paper presents a deep learning algorithm based on YOLOv5, which aims to assist agricultural workers in efficiently diagnosing information related to 102 types of pests. To achieve this, we propose a new lightweight convolutional module called C3M, which is inspired by the MobileNetV3 network. Compared to the original convolution module C3, C3M occupies less computing memory and results in a faster inference speed, with the detection precision improved by 4.6%. In addition, the GAM (Global Attention Mechanism) is introduced into the neck of YOLO5, which further improves the detection capability of the model. The experimental results indicate that the C3M-YOLO algorithm performs better than YOLOv5 on IP102, a public dataset consisting of 102 pests. Specifically, the detection precision P is 2.4% higher than that of the original model, and mAP0.75 increased by 1.7%, while the F1-score improved by 1.8%. Furthermore, the mAP0.5 and mAP0.75 of the C3M-YOLO algorithm are higher than those of the YOLOX detection model by 5.1% and 6.2%, respectively.

21 August 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
YYYue Yu
Yue Yu
QZQi Zhou
Qi Zhou
WHWang Hao
Wang Hao
KLKe Lv
Ke Lv
Lijuan ZhangLijuan Zhang
Lijuan Zhang
DLDongming Li
Dongming Li
To enhance agricultural productivity through the accurate detection of pests under the constrained resources of mobile devices, we introduce LP-YOLO, a bespoke lightweight object detection framework optimized for mobile-based insect pest identification. Initially, we devise lightweight components, namely LP_Unit and LP_DownSample, to serve as direct substitutes for the majority of modules within YOLOv8. Subsequently, we develop an innovative attention mechanism, denoted as ECSA (Efficient Channel and Spatial Attention), which is integrated into the network to forge LP-YOLO(l). Moreover, assessing the trade-offs between parameter reduction and computational efficiency, considering both the backbone and head components of the network, we use structured pruning methods for the pruning process, culminating in the creation of LP-YOLO(s). Through a comprehensive series of evaluations on the IP102 dataset, the efficacy of LP-YOLO as a lightweight object detection model is validated. By incorporating fine-tuning techniques during training, LP-YOLO(s)n demonstrates a marginal mAP decrease of only 0.8% compared to YOLOv8n. However, it achieves a significant reduction in parameter count by 70.2% and a remarkable 40.7% increase in FPS, underscoring its efficiency and performance.

7 August 2021 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
DLDongming Li
Dongming Li
PTPeng Tang
Peng Tang
RZRun Zhang
Run Zhang
CSChangming Sun
Changming Sun
YLYong Li
Yong Li
Lijuan ZhangLijuan Zhang
Lijuan Zhang
For the analysis of medical images, one of the most basic methods is to diagnose diseases by examining blood smears through a microscope to check the morphology, number, and ratio of red blood cells and white blood cells. Therefore, accurate segmentation of blood cell images is essential for cell counting and identification. The aim of this paper is to perform blood smear image segmentation by combining neural ordinary differential equations (NODEs) with U-Net networks to improve the accuracy of image segmentation. In order to study the effect of ODE-solve on the speed and accuracy of the network, the ODE-block module was added to the nine convolutional layers in the U-Net network. Firstly, blood cell images are preprocessed to enhance the contrast between the regions to be segmented; secondly, the same dataset was used for the training set and testing set to test segmentation results. According to the experimental results, we select the location where the ordinary differential equation block (ODE-block) module is added, select the appropriate error tolerance, and balance the calculation time and the segmentation accuracy, in order to exert the best performance; finally, the error tolerance of the ODE-block is adjusted to increase the network depth, and the training NODEs-UNet network model is used for cell image segmentation. Using our proposed network model to segment blood cell images in the testing set, it can achieve 95.3% pixel accuracy and 90.61% mean intersection over union. By comparing the U-Net and ResNet networks, the pixel accuracy of our network model is increased by 0.88% and 0.46%, respectively, and the mean intersection over union is increased by 2.18% and 1.13%, respectively. Our proposed network model improves the accuracy of blood cell image segmentation and reduces the computational cost of the network.

17 August 2023 in IEEE Access
Verified
Journal Article
Open access
Lijuan ZhangLijuan Zhang
Lijuan Zhang
MWMinhui Wang
Minhui Wang
YJYutong Jiang
Yutong Jiang
DLDongming Li
Dongming Li
YZYue Zhou
Yue Zhou
There are still many technological challenges in recognizing small objects in complex situations, and the performance of current detection algorithms for small objects is still unsatisfactory. Most existing methods mainly use feature pyramid networks to enrich shallow features using contextual features. However, due to the inconsistency of gradients between different layers of the feature pyramid network, the shallow features cannot be fully utilized resulting in the slow improvement of small object detection accuracy. To effectively improve the small object detection algorithm, we propose a new feature pyramid network-based small object detection algorithm, SSRDet. To effectively assign positive and negative sample labels and address the issue of sample scale imbalance, we first present RFLA. Then, to overcome the gradient inconsistency between various layers and enable the full utilization of the shallow features, we extend the feature pyramid network by including a scale enhancement module (SEM) and a scale selection module (SSM). Finally, we introduced the attention module (SPAM) to filter out the background noise in the shallow feature extraction to better extract small object features. We validated our method on VisDrone2019 and AI-TOD, and our method outperformed the state-of-the-art detectors.