Integration of U-Net, ResU-Net and DeepLab Architectures with Intersection Over Union metric for Cells Nuclei Image Segmentation

Goyzueta, Christian Augusto Romero; Cruz, Jose Emmanuel Cruz De la; Machaca, Wilson Antony Mamani

doi:10.1109/eircon52903.2021.9613150

Cited by 6 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IoU is a stan extremely powerful and very simple metric. IoU equals the overlap between the predicted segmentation and the terrain truth, divided by the joining area between the predicted segmentation and the terrain truth [16].…”

Section: Segmentation Evaluation Matricsmentioning

confidence: 99%

Semantic Segmentation of Venous on Deep Vein Thrombosis (DVT) Case using UNet-ResNet

Hernanda

Purnama

Yuniarno

et al. 2022

2022 10th International Conference on Information and Communication Technology (ICoICT)

View full text Add to dashboard Cite

show abstract

Section: Segmentation Evaluation Matricsmentioning

confidence: 99%

Semantic Segmentation of Venous on Deep Vein Thrombosis (DVT) Case using UNet-ResNet

Hernanda

Purnama

Yuniarno

et al. 2022

2022 10th International Conference on Information and Communication Technology (ICoICT)

View full text Add to dashboard Cite

show abstract

“…For this, the encoder and decoder network is a better construct [17,18,22,23]. Goyzueta [19] combined U-Net, ResU-Net, and DeepLab architectures for image segmentation based on the same structure. Diverse feature extraction using dynamic effects was improved with DeepLab [21].…”

Section: Introductionmentioning

confidence: 99%

Melanoma Classification via Hybrid Saliency and Conditional Random Field with Bottleneck to Optimize DeepLab

Tuyet,

Binh

2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Neural networks overcome drawbacks of vision tasks by becoming convolutional in a wide range of layers. The salient map is affected by multilevels of strong pixels (superpixels) in global images and that is dependent on the hard threshold for their dividing. Deep neural networks have been established for saliency prediction of segmentation because the feature extraction must be suited to the input data. The convolutional neural network (CNN) also endures conflict between spatial pattern and a likeness of salient objects. Semantic segmentation is one of the approaches to continue classification based on these features. Therefore, upgrading the extraction process can be of use in saliency. In this work, we optimize DeepLab based on an atrous convolutional and a conditional random field (CRF) with a bottleneck in the semantic segmentation method, which serves for classification. The backbone of deep feature extraction is atrous convolution and the bottleneck based on CRF for hybrid saliency in the encoder-decoder system. The classification results are compared with some approaches for saliency prediction of recent deeper methods in an ISIC 2017 dataset. The results give better values not only for saliency prediction for segmentation but also for training and testing for classification.

show abstract

Image Segmentation of Neuronal Cell with Ensemble Unet Architecture

Kanani

Gupta

Nikum

et al. 2023

Mathematics and Computer Science Volume 2

View full text Add to dashboard Cite

Integration of U-Net, ResU-Net and DeepLab Architectures with Intersection Over Union metric for Cells Nuclei Image Segmentation

Cited by 6 publications

References 3 publications

Semantic Segmentation of Venous on Deep Vein Thrombosis (DVT) Case using UNet-ResNet

Semantic Segmentation of Venous on Deep Vein Thrombosis (DVT) Case using UNet-ResNet

Melanoma Classification via Hybrid Saliency and Conditional Random Field with Bottleneck to Optimize DeepLab

Image Segmentation of Neuronal Cell with Ensemble Unet Architecture

Contact Info

Product

Resources

About