Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

A Stacked Multi-Granularity Convolution Denoising Auto-Encoder

Yang, Y, Cao, L, Liu, Q and Yang, P (2019) A Stacked Multi-Granularity Convolution Denoising Auto-Encoder. IEEE Access, 7. pp. 83888-83899. ISSN 2169-3536

[img]
Preview
Text
A Stacked Multi-Granularity Convolution Denoising Auto Encoder.pdf - Published Version

Download (8MB) | Preview
Open Access URL: https://doi.org/10.1109/ACCESS.2019.2918409 (Published version)

Abstract

With the development of big data, artificial intelligence has provided many intelligent solutions to urban life. For instance, an image-based intelligent technology, such as image classification of diseases, is widely used in daily life. However, the image in real life is mostly unlabeled, so the performance of many image-based intelligent models shows limitations. Therefore, how to use a large amount of unlabeled image data to build an efficient and high-quality model for better urban life has been an urgent research topic. In this paper, we propose an unsupervised image feature extraction method that is referred to as a stacked multi-granularity convolution denoising auto-encoder (SMGCDAE). The algorithm is based on a convolutional neural network (CNN), yet it introduces a multi-granularity kernel. This approach resolved issues with image unicity by extracting a diverse category of high-level features. In addition, the denoising auto-encoder ensures stability and improves the classification accuracy by extracting more robust features. The algorithm was assessed using three image benchmark datasets and a series of meningitis images, achieving higher average accuracy than other methods. These results suggest that the algorithm is capable of extracting more discriminative high-level features and thus offers superior performance compared with the existing methodologies.

Item Type: Article
Additional Information: © 2019 IEEE.
Uncontrolled Keywords: Science & Technology; Technology; Computer Science, Information Systems; Engineering, Electrical & Electronic; Telecommunications; Computer Science; Engineering; Unsupervised learning; feature extraction; denoising auto-encoder; convolutional neural network; NEURAL-NETWORK; DEEP NETWORK; CLASSIFICATION; ENSEMBLE; REPRESENTATIONS
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Computer Science
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Related URLs:
Date Deposited: 10 Mar 2020 10:42
Last Modified: 10 Mar 2020 10:45
DOI or Identification number: 10.1109/ACCESS.2019.2918409
URI: http://researchonline.ljmu.ac.uk/id/eprint/12443

Actions (login required)

View Item View Item