Centered convolutional deep Boltzmann machine for 2D shape modeling

Yang, Jiangong; Liu, Shigang; Wang, Xili

doi:10.1007/s00779-020-01487-z

Cited by 2 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate seven shape denoising methods (ASM [6], DBM [8], CDBM [9], EBM [10], U-Net [11], Deeplabv3+ [12], MAE [13]) for denoising shapes corrupted by the six types of noise introduced in Section 2.2. The criterion we use to estimate the quality of the denoising result is the IoU (7).…”

Section: Evaluation Of Shape Denoising Methodsmentioning

confidence: 99%

“…A recent study about 2D shape modeling [9] introduces convolutions into a DBM-based shape model. The goal of their work is to generate realistic shapes that are different from all training shapes.…”

Section: Related Workmentioning

confidence: 99%

“…In our work, the aim is to recover the object shape from different kinds of noisy perturbations, which allows us to use an objective evaluation criterion: the recovered shape must be close to the original (unseen) shape. In [9], all models used for comparison are based on Restricted Boltzmann Machines. Our work expands the scope of comparison by adding more methods that include both classical ones such as the Active Shape Model(ASM) and recent ones such as the Energy-611 978-1-6654-9620-9/22/$31.00 ©2022 IEEE ICIP 2022…”

Section: Related Workmentioning

confidence: 99%

“…In this work, the shape will be represented by a binary image, which is a form of a level set representation. Considering a shape as a binary image allows many generative models to be applied to shape modeling, such as Restricted Boltzmann Machines (RBM) [7], Deep Boltzmann Machines (DBM) [8], Centered Convolutional Deep Boltzmann Machines (CCDBM) [9] and Energy Based Models (EBM) [10]. Moreover, deep learning based methods for semantic segmentation can also be used for shape modeling, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Study of Shape Modeling Against Noise

Long

Barbu

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Shape modeling is a challenging task with many potential applications in computer vision and medical imaging. There are many shape modeling methods in the literature, each with its advantages and applications. However, many shape modeling methods have difficulties handling shapes that have missing pieces or outliers. In this regard, this paper introduces shape denoising, a fundamental problem in shape modeling that lies at the core of many computer vision and medical imaging applications and has not received enough attention in the literature. The paper introduces six types of noise that can be used to perturb shapes as well as an objective measure for the noise level and for comparing methods on their shape denoising capabilities. Finally, the paper evaluates seven methods capable of accomplishing this task, of which six are based on deep learning, including some generative models.

show abstract

Section: Evaluation Of Shape Denoising Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Study of Shape Modeling Against Noise

Long

Barbu

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…This is a significant problem for RBM, which has numerous layers, including DBN and Convolutional Deep Belief Networks. The hidden units' bias values can increase speed, but they are unable to handle the learning process that occurs between the hidden units [31]. To address these concerns, this model employs centered factors to relieve the causes of instability by resolving the gradient and centering the unit activations.…”

Section: _ _mentioning

confidence: 99%

An Optimization-Linked Intelligent Security Algorithm for Smart Healthcare Organizations

et al. 2023

View full text Add to dashboard Cite

IoT-enabled healthcare apps are providing significant value to society by offering cost-effective patient monitoring solutions in IoT-enabled buildings. However, with a large number of users and sensitive personal information readily available in today’s fast-paced, internet, and cloud-based environment, the security of these healthcare systems must be a top priority. The idea of safely storing a patient’s health data in an electronic format raises issues regarding patient data privacy and security. Furthermore, with traditional classifiers, processing large amounts of data is a difficult challenge. Several computational intelligence approaches are useful for effectively categorizing massive quantities of data for this goal. For many of these reasons, a novel healthcare monitoring system that tracks disease processes and forecasts diseases based on the available data obtained from patients in distant communities is proposed in this study. The proposed framework consists of three major stages, namely data collection, secured storage, and disease detection. The data are collected using IoT sensor devices. After that, the homomorphic encryption (HE) model is used for secured data storage. Finally, the disease detection framework is designed with the help of Centered Convolutional Restricted Boltzmann Machines-based whale optimization (CCRBM-WO) algorithm. The experiment is conducted on a Python-based cloud tool. The proposed system outperforms current e-healthcare solutions, according to the findings of the experiments. The accuracy, precision, F1-measure, and recall of our suggested technique are 96.87%, 97.45%, 97.78%, and 98.57%, respectively, according to the proposed method.

show abstract

Centered convolutional deep Boltzmann machine for 2D shape modeling

Cited by 2 publications

References 21 publications

A Study of Shape Modeling Against Noise

A Study of Shape Modeling Against Noise

An Optimization-Linked Intelligent Security Algorithm for Smart Healthcare Organizations

Contact Info

Product

Resources

About