Redirigiendo al acceso original de articulo en 24 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 18 (2022)  /  Artículo
ARTÍCULO
TITULO

Comparative Study for Patch-Level and Pixel-Level Segmentation of Deep Learning Methods on Transparent Images of Environmental Microorganisms: From Convolutional Neural Networks to Visual Transformers

Hechen Yang    
Xin Zhao    
Tao Jiang    
Jinghua Zhang    
Peng Zhao    
Ao Chen    
Marcin Grzegorzek    
Shouliang Qi    
Yueyang Teng and Chen Li    

Resumen

Currently, the field of transparent image analysis has gradually become a hot topic. However, traditional analysis methods are accompanied by large amounts of carbon emissions, and consumes significant manpower and material resources. The continuous development of computer vision enables the use of computers to analyze images. However, the low contrast between the foreground and background of transparent images makes their segmentation difficult for computers. To address this problem, we first analyzed them with pixel patches, and then classified the patches as foreground and background. Finally, the segmentation of the transparent images was completed through the reconstruction of pixel patches. To understand the performance of different deep learning networks in transparent image segmentation, we conducted a series of comparative experiments using patch-level and pixel-level methods. In two sets of experiments, we compared the segmentation performance of four convolutional neural network (CNN) models and a visual transformer (ViT) model on the transparent environmental microorganism dataset fifth version. The results demonstrated that U-Net++ had the highest accuracy rate of 95.32% in the pixel-level segmentation experiment followed by ViT with an accuracy rate of 95.31%. However, ResNet50 had the highest accuracy rate of 90.00% and ViT had the lowest accuracy of 89.25% in the patch-level segmentation experiments. Hence, we concluded that ViT performed the lowest in patch-level segmentation experiments, but outperformed most CNNs in pixel-level segmentation. Further, we combined patch-level and pixel-level segmentation results to reduce the loss of segmentation details in the EM images. This conclusion was also verified by the environmental microorganism dataset sixth version dataset (EMDS-6).

 Artículos similares

       
 
Camino Eck, Xiaoyu Kröner and Dorte Janussen    
This study investigates taxonomic characteristics of carnivorous sponges from the Southern Ocean. The specimens were collected in 2010 from deep-sea hydrothermal vents of the East Scotia Ridge during the RRS James Cook Cruise JC42. All the investigated s... ver más

 
Yunfei Yang, Zhicheng Zhang, Jiapeng Zhao, Bin Zhang, Lei Zhang, Qi Hu and Jianglong Sun    
Resistance serves as a critical performance metric for ships. Swift and accurate resistance prediction can enhance ship design efficiency. Currently, methods for determining ship resistance encompass model tests, estimation techniques, and computational ... ver más

 
Shizhen Li, Qinfeng Wu, Yufeng Liu, Longfei Qiao, Zimeng Guo and Fei Yan    
To mitigate the interference of waves on an offshore operation ship, heave compensation systems find widespread application. The performance of heave compensation systems significantly influences the efficiency and safety of maritime operations. This stu... ver más

 
Eyad K. Sayhood, Nisreen S. Mohammed, Salam J. Hilo and Salih S. Salih    
This paper presents comprehensive empirical equations to predict the shear strength capacity of reinforced concrete deep beams, with a focus on improving the accuracy of existing codes. Analyzing 198 deep beams imported from 15 existing investigations, t... ver más
Revista: Infrastructures

 
Yifan Wang, Jinglei Xu, Qihao Qin, Ruiqing Guan and Le Cai    
In this study, we propose a novel dynamic mode decomposition (DMD) energy sorting criterion that works in conjunction with the conventional DMD amplitude-frequency sorting criterion on the high-dimensional schlieren dataset of the unsteady flow of a spik... ver más
Revista: Aerospace