Optimization algorithm of CT image edge segmentation using improved convolution neural network

Wang, Xiaojuan; Wei, Yuntao

doi:10.1371/journal.pone.0265338

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image segmentation is an important research direction in the field of computer vision. Image segmentation is the semi-automatic or automatic extraction and separation of areas of interest in an image, which lays a foundation for high-level image analysis and understanding, such as model representation of objects of interest, parameter extraction, feature extraction and image recognition [1][2][3][4]. Image segmentation is the basis of machine vision, and its accuracy determines the quality of computer vision [5,6].…”

Section: Introductionmentioning

confidence: 99%

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

Hou,

Zhao,

Cui

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The identification research of hydrogenation catalyst information has always been one of the most important businesses in the chemical industry. In order to aid researchers in efficiently screening high-performance catalyst carriers and tackle the pressing challenge at hand, it is imperative to find a solution for the intelligent recognition of hydrogenation catalyst images. To address the issue of low recognition accuracy caused by adhesion and stacking of hydrogenation catalysts, An image recognition algorithm of hydrogenation catalyst based on FPNC Net was proposed in this paper. In the present study, Resnet50 backbone network was used to extract the features, and spatially-separable convolution kernel was used to extract the multi-scale features of catalyst fringe. In addition, to effectively segment the adhesive regions of stripes, FPN (Feature Pyramid Network) is added to the backbone network for deep and shallow feature fusion. Introducing an attention module to adaptively adjust weights can effectively highlight the target features of the catalyst. The experimental results showed that the FPNC Net model achieved an accuracy of 94.2% and an AP value improvement of 19.37% compared to the original CenterNet model. The improved model demonstrates a significant enhancement in detection accuracy, indicating a high capability for detecting hydrogenation catalyst targets

show abstract

Section: Introductionmentioning

confidence: 99%

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

Hou,

Zhao,

Cui

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Hyperparameter optimisation of CNNs is one of the most challenging tasks. Small variations in the hyperparameter values can influence the overall performance of the model [ 21 , 22 ]. The Deep Neuroevolutionary algorithms (DNEs) are practical solutions that optimise both the architecture and hyperparameters of the CNNs model to find out the best architecture design and hyperparameters set [ 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection

Noman,

Shamsul Islam,

Jafar Jalali

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Deep learning, a subset of machine learning that utilizes neural networks, has seen significant advancements in recent years. These advancements have led to breakthroughs in a wide range of fields, from natural language processing to computer vision, and have the potential to revolutionize many industries or organizations. They have also demonstrated exceptional performance in the identification and mapping of seagrass images. However, these deep learning models, particularly the popular Convolutional Neural Networks (CNNs) require architectural engineering and hyperparameter tuning. This paper proposes a Deep Neuroevolutionary (DNE) model that can automate the architectural engineering and hyperparameter tuning of CNNs models by developing and using a novel metaheuristic algorithm, named ‘Boosted Atomic Orbital Search (BAOS)’. The proposed BAOS is an improved version of the recently proposed Atomic Orbital Search (AOS) algorithm which is based on the principle of atomic model and quantum mechanics. The proposed algorithm leverages the power of the Lévy flight technique to boost the performance of the AOS algorithm. The proposed DNE algorithm (BAOS-CNN) is trained, evaluated and compared with six popular optimisation algorithms on a patch-based multi-species seagrass dataset. This proposed BAOS-CNN model achieves the highest overall accuracy (97.48%) among the seven evolutionary-based CNN models. The proposed model also achieves the state-of-the-art overall accuracy of 92.30% and 93.5% on the publicly available four classes and five classes version of the ‘DeepSeagrass’ dataset, respectively. This multi-species seagrass dataset is available at: https://ro.ecu.edu.au/datasets/141/.

show abstract

“…Hyperparameter optimisation of CNNs is one of the most challenging tasks. Small variations in the hyperparameter values can influence the overall performance of the model [21,22]. The Deep Neuroevolutionary algorithms (DNEs) are practical solutions that optimise both the architecture and hyperparameters of the CNNs model to find out the best architecture design and hyperparameters set [23,24].…”

Section: Introductionmentioning

confidence: 99%

Untitled

View full text Add to dashboard Cite

Optimization algorithm of CT image edge segmentation using improved convolution neural network

Cited by 3 publications

References 27 publications

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection

Untitled

Contact Info

Product

Resources

About