An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy

Hou, Yue-Jie; Xie, Zai-Xin; Jianhu,; Yao-Shen,; Zhou, Chi-Chun

doi:10.48550/arxiv.2109.05526

Cited by 3 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we introduce the proposed BA-CCAE model. It is based on the CCAE proposed in the previous work [16]. The CCAE is an effective model that can extract key features from a given images and compress the dimension of the raw images by giving the encoded vectors, as shown in Fig.…”

Section: The Main Methodsmentioning

confidence: 99%

“…In the CCAE, an L2 constraint of the latent vector is added to the mean square error function between the decoded and raw images giving the final loss function. More details of the CCAE can be found in the previous work [16].…”

Section: The Main Methodsmentioning

confidence: 99%

“…In this paper, instead of the supervised deep-learning method, we proposed an unsupervised deep-learning method for the bone age assessment. The main method is based on the previous work [16], where a convolutional auto-encoder with constraints (CCAE), an unsupervised deep-learning model, is proposed in the classification of the fingerprint. The propose unsupervised deep-learning model for the classification of the bone age is named BA-CCAE for short.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Unsupervised Deep-Learning Method for Bone Age Assessment

Zhu¹,

Nie²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The bone age, reflecting the degree of development of the bones, can be used to predict the adult height and detect endocrine diseases of children. Both examinations of radiologists and variability of operators have a significant impact on bone age assessment. To decrease human intervention , machine learning algorithms are used to assess the bone age automatically. However, conventional supervised deep-learning methods need pre-labeled data. In this paper, based on the convolutional auto-encoder with constraints (CCAE), an unsupervised deep-learning model proposed in the classification of the fingerprint, we propose this model for the classification of the bone age and baptize it BA-CCAE. In the proposed BA-CCAE model, the key regions of the raw X-ray images of the bone age are encoded, yielding the latent vectors. The K-means clustering algorithm is used to obtain the final classifications by grouping the latent vectors of the bone images. A set of experiments on the Radiological Society of North America pediatric bone age dataset (RSNA) show that the accuracy of classifications at 48-month intervals is 76.15%. Although the accuracy now is lower than most of the existing supervised models, the proposed BA-CCAE model can establish the classification of bone age without any pre-labeled data, and to the best of our knowledge, the proposed BA-CCAE is one of the few trails using the unsupervised deep-learning method for the bone age assessment.

show abstract

Section: The Main Methodsmentioning

confidence: 99%

Section: The Main Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Unsupervised Deep-Learning Method for Bone Age Assessment

Zhu¹,

Nie²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main applications of autoencoders are dimensionality reduction and feature extraction [21][22][23]. In this study, we used a deep learning unsupervised classi cation model that integrated a CNN and an auto-encoding network known as the constraint convolutional auto-encoder (CCAE) to extract cell characteristics, and a hybrid clustering approach was applied to obtain the nal clusters [24]. Certain changes were made to improve the performance of CCAE, such as adding a new loss function to aid model convergence and improve the network fundamental structure.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised deep learning of bright-field images for apoptotic cell classification

Zhuo

Sun

et al. 2023

SIViP

View full text Add to dashboard Cite

The classi cation of apoptotic and living cells is signi cant in drug screening and treating various diseases. Conventional supervised methods require a large amount of prelabelled data, which is often costly and consumes immense human resources in the biological eld. In this study, unsupervised deeplearning algorithms were used to extract cell characteristics and classify cells. A model integrating a convolutional neural network and an auto-encoder network was utilised to extract cell characteristics, and a hybrid clustering approach was employed to obtain cell feature clustering results. Experiments on both public and private datasets revealed that the proposed unsupervised strategy performs well in cell categorisation. For instance, in the public dataset, our method obtained a precision of 96.72% on only 1000 unlabelled cells. To the best of our knowledge, this is the rst time unsupervised deep learning has been applied to distinguish apoptosis and live cells with high accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Learning of Bright Field Images for Apoptotic Cell Classification

Zhuo

Sun

et al. 2022

Preprint

View full text Add to dashboard Cite

The classification of apoptotic and living cells is significant in drug screening and treating various diseases. Conventional supervised methods require a large amount of prelabelled data, which is often costly and consumes immense human resources in the biological field. In this study, unsupervised deep-learning algorithms were used to extract cell characteristics and classify cells. A model integrating a convolutional neural network and an auto-encoder network was utilised to extract cell characteristics, and a hybrid clustering approach was employed to obtain cell feature clustering results. Experiments on both public and private datasets revealed that the proposed unsupervised strategy performs well in cell categorisation. For instance, in the public dataset, our method obtained a precision of 96.72% on only 1000 unlabelled cells. To the best of our knowledge, this is the first time unsupervised deep learning has been applied to distinguish apoptosis and live cells with high accuracy.

show abstract

An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy

Cited by 3 publications

References 53 publications

An Unsupervised Deep-Learning Method for Bone Age Assessment

An Unsupervised Deep-Learning Method for Bone Age Assessment

Unsupervised deep learning of bright-field images for apoptotic cell classification

Unsupervised Deep Learning of Bright Field Images for Apoptotic Cell Classification

Contact Info

Product

Resources

About