Eleventh International Conference on Machine Vision (ICMV 2018) 2019
DOI: 10.1117/12.2522849
|View full text |Cite
|
Sign up to set email alerts
|

Wavelet based edge feature enhancement for convolutional neural networks

Abstract: Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two wavelet-based edge feature enhancement methods to preprocess the input images to convolutional neural networks. The first method develops feature enhanced representations by decomposing the input images using wavelet transform and limited reconstructing subsequently. The second met… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
13
0

Year Published

2019
2019
2020
2020

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 13 publications
(13 citation statements)
references
References 27 publications
0
13
0
Order By: Relevance
“…Moreover, we have compared our findings with several previous work done in the wavelets and neural networks domain. [48] and wavelet based preprocessing for CNN [10] have also compared. Both previous work process inputs in wavelet domain using fixed wavelets without any wavelet learning.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Moreover, we have compared our findings with several previous work done in the wavelets and neural networks domain. [48] and wavelet based preprocessing for CNN [10] have also compared. Both previous work process inputs in wavelet domain using fixed wavelets without any wavelet learning.…”
Section: Resultsmentioning
confidence: 99%
“…In terms of deep learning, wavelet-based methods have been used in many computer vision applications through Convolutional Neural Networks (CNN) due its ability of diverse information extraction. Texture classification using wavelet CNN [11], multi-scale face super-resolution [16], image super-resolution [13] and edge feature enhancing [10] are notable applications. A multi-level wavelet CNN model for image restoration has been introduced by Liu et al [21].…”
Section: Related Workmentioning
confidence: 99%
“…Cai et al 6 used the image processing of intelligent buildings as the basic theoretical platform, and based on the pattern recognition technology, studied image processing, image extraction, and image recognition in image processing of building intelligent environment, and proposed reasonable solutions. De Silva et al 7 proposed and evaluated two wavelet-based edge feature enhancement methods to pre-process the input image by CNN, developed a new pre-processing layer, and attached it to the network architecture. The results show that the proposed method is superior to the baseline and previously published work.…”
Section: Related Workmentioning
confidence: 99%
“…Various methods utilizing wavelet-based features in neural networks have also been explored to capitalize on multiscale features of wavelets in the computer vision domain [37][38][39]. Multiscale convolutional neural networks have also been used for classification [40,41]. Fully convolutional networks have shown improved performance for classification [42][43][44].…”
Section: Related Workmentioning
confidence: 99%