2019
DOI: 10.3390/app9050841
|View full text |Cite
|
Sign up to set email alerts
|

Color Inverse Halftoning Method with the Correlation of Multi-Color Components Based on Extreme Learning Machine

Abstract: Look-up table (LUT) based method is a popular and effective way for inverse halftoning. However, it still has very large development space to improve the reconstructed color image quality for color halftone images, because most of the existing color inverse halftoning methods are the simple extension of LUT methods to each color components separately. To this end, this paper presents a novel color inverse halftoning method by exploiting the correlation of multi-color components. Through considering all existen… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
16
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
10

Relationship

5
5

Authors

Journals

citations
Cited by 17 publications
(16 citation statements)
references
References 23 publications
0
16
0
Order By: Relevance
“…Plain and twill fabric detection methods can be classified into five aspects: Spectral [9,10], learning [11,12], statistical [13][14][15], model-based [16,17], and structural methods [18,19]. The spectral method based on the Wavelet transform [20] achieved 97.5% detection accuracy with five known defect types and a 93.3% detection accuracy (a slight drop) with three unknown defect types in an evaluation.…”
Section: Related Workmentioning
confidence: 99%
“…Plain and twill fabric detection methods can be classified into five aspects: Spectral [9,10], learning [11,12], statistical [13][14][15], model-based [16,17], and structural methods [18,19]. The spectral method based on the Wavelet transform [20] achieved 97.5% detection accuracy with five known defect types and a 93.3% detection accuracy (a slight drop) with three unknown defect types in an evaluation.…”
Section: Related Workmentioning
confidence: 99%
“…The three features consist of multi-scale completed local binary patterns (MS-CLBP), Bag of visual words (BOVW), and spatial pyramid matching (SPM). Methods based on CNN mainly refer to select the features of a certain layer in the convolutional neural network, and then use the support vector machine (SVM), extreme learning machine (ELM) or logistic regression classifier [12][13][14][15][16][17][18]. The literature [5] has used the 15th layer feature extracted from the pre-trained model vgg-16 based on the ImageNet dataset.…”
Section: Introductionmentioning
confidence: 99%
“…Surface defect detection and classification are important tasks in many fields, such as the manufacturing industry [1,2], textile industry [3], and printing industry [4,5]. For the printing industry, with the increasing speed of modern printing machines and the increasing requirements of printing enterprises in terms of product quality, traditional detection and classification methods based on human visual inspection are impossible.…”
Section: Introductionmentioning
confidence: 99%