scholarly journals Improved Extreme Learning Machine and Its Application in Image Quality Assessment

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Li Mao ◽  
Lidong Zhang ◽  
Xingyang Liu ◽  
Chaofeng Li ◽  
Hong Yang
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Extreme Learning Machine ◽  
Image Quality Assessment ◽  
Risk Minimization ◽  
Minimization Principle ◽  
Empirical Risk ◽  
Weighted Extreme Learning Machine ◽  
Learning Machine ◽  
Hidden Layer

Extreme learning machine (ELM) is a new class of single-hidden layer feedforward neural network (SLFN), which is simple in theory and fast in implementation. Zong et al. propose a weighted extreme learning machine for learning data with imbalanced class distribution, which maintains the advantages from original ELM. However, the current reported ELM and its improved version are only based on the empirical risk minimization principle, which may suffer from overfitting. To solve the overfitting troubles, in this paper, we incorporate the structural risk minimization principle into the (weighted) ELM, and propose a modified (weighted) extreme learning machine (M-ELM and M-WELM). Experimental results show that our proposed M-WELM outperforms the current reported extreme learning machine algorithm in image quality assessment.

NMF-Based Image Quality Assessment Using Extreme Learning Machine

2017 ◽  
Vol 47 (1) ◽  
pp. 232-243 ◽  
Author(s):  
Shuigen Wang ◽  
Chenwei Deng ◽  
Weisi Lin ◽  
Guang-Bin Huang ◽  
Baojun Zhao
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Extreme Learning Machine ◽  
Image Quality Assessment ◽  
Learning Machine

scholarly journals Saturation-based quality assessment for colorful multi-exposure image fusion

2017 ◽  
Vol 14 (2) ◽  
pp. 172988141769462 ◽  
Author(s):  
Chenwei Deng ◽  
Zhen Li ◽  
Shuigen Wang ◽  
Xun Liu ◽  
Jiahui Dai
Keyword(s):  
Image Quality ◽  
Image Fusion ◽  
Quality Assessment ◽  
Visual Information ◽  
Image Quality Assessment ◽  
Human Perception ◽  
Image Features ◽  
Consumer Electronics ◽  
Structure Information ◽  
Learning Machine

Multi-exposure image fusion is becoming increasingly influential in enhancing the quality of experience of consumer electronics. However, until now few works have been conducted on the performance evaluation of multi-exposure image fusion, especially colorful multi-exposure image fusion. Conventional quality assessment methods for multi-exposure image fusion mainly focus on grayscale information, while ignoring the color components, which also convey vital visual information. We propose an objective method for the quality assessment of colored multi-exposure image fusion based on image saturation, together with texture and structure similarities, which are able to measure the perceived color, texture, and structure information of fused images. The final image quality is predicted using an extreme learning machine with texture, structure, and saturation similarities as image features. Experimental results for a public multi-exposure image fusion database show that the proposed model can accurately predict colored multi-exposure image fusion image quality and correlates well with human perception. Compared with state-of-the-art image quality assessment models for image fusion, the proposed metric has better evaluation performance.

Prediction Research of Transformer Fault Based on Regular Extreme Learning Machine

2014 ◽  
Vol 1049-1050 ◽  
pp. 1205-1209
Author(s):  
Xue Zhen Chen ◽  
Yong Li Zhu ◽  
Fei Pei
Keyword(s):  
Prediction Model ◽  
Extreme Learning Machine ◽  
Fault Prediction ◽  
Transformer Oil ◽  
Risk Minimization ◽  
Prediction Ability ◽  
Generalization Performance ◽  
Minimization Principle ◽  
Learning Machine ◽  
Transformer Fault

To predict the concentration of dissolved gas in transformer oil, and then realize the transformer latent fault prediction, can effectively prevent unnecessary loss caused by the transformer faults .In order to improve the transformer fault prediction ability,this paper proposes a new transformer fault prediction model--Regular Extreme Learning Machine (RELM) prediction model。RELM algorithm introduce structure risk minimization principle on the basis of traditional ELM, using the balance factor to weigh the empirical risk and the risk of structure size, further enhance the generalization performance of ELM. Verified by examples, the proposed prediction model based on the RELM in this paper achieve better generalization performance and prediction accuracy in the forecast of gases concentration dissolved in transformer oil.

Research of Single well Production Prediction Based on Improved Extreme Learning Machine

2013 ◽  
Vol 333-335 ◽  
pp. 1296-1300 ◽  
Author(s):  
Wen Bo Na ◽  
Zhi Wei Su ◽  
Yun Feng Ji
Keyword(s):  
Extreme Learning Machine ◽  
Predictive Accuracy ◽  
Oil Well ◽  
Risk Minimization ◽  
Bp Network ◽  
Minimization Principle ◽  
Well Production ◽  
Single Well ◽  
Learning Machine ◽  
Production Prediction

In order to improve the precision of oilfield single well production prediction, a single well production prediction model based on improved extreme learning machine (RWELM) is proposed. Substituting wavelet function for common activation function, structural risk minimization principle is integrated into the model in order to avoid the local minimum and over-fitting problem commonly faced by traditional extreme learning machine (ELM) in single well production forecasting. Dynamic data of an oil well production is simulated of Lun Nan oilfield. Experimental results show that the forecasting model is better than ELM, LM-BP neural networks, BP network with delay time sequence in both generalization performance and predictive accuracy.

A Novel Hybrid Image Quality Assessment Algorithm

2011 ◽  
Vol 4 (4) ◽  
pp. 107-108
Author(s):  
Deepa Maria Thomas ◽  
◽  
S. John Livingston
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment

Document Image Quality Assessment with Relaying Reference to Determine Minimum Readable Resolution for Compression

2020 ◽  
Vol 2020 (9) ◽  
pp. 323-1-323-8
Author(s):  
Litao Hu ◽  
Zhenhua Hu ◽  
Peter Bauer ◽  
Todd J. Harris ◽  
Jan P. Allebach
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Research Area ◽  
Input Image ◽  
Quality Score ◽  
Document Image ◽  
Digital Cameras ◽  
Active Research ◽  
Traditional Approaches

Image quality assessment has been a very active research area in the field of image processing, and there have been numerous methods proposed. However, most of the existing methods focus on digital images that only or mainly contain pictures or photos taken by digital cameras. Traditional approaches evaluate an input image as a whole and try to estimate a quality score for the image, in order to give viewers an idea of how “good” the image looks. In this paper, we mainly focus on the quality evaluation of contents of symbols like texts, bar-codes, QR-codes, lines, and hand-writings in target images. Estimating a quality score for this kind of information can be based on whether or not it is readable by a human, or recognizable by a decoder. Moreover, we mainly study the viewing quality of the scanned document of a printed image. For this purpose, we propose a novel image quality assessment algorithm that is able to determine the readability of a scanned document or regions in a scanned document. Experimental results on some testing images demonstrate the effectiveness of our method.

Sign in / Sign up

Export Citation Format

Share Document