Wavelet Convolutional Neural Networks for Texture Classification

Fujieda, Shin; Takayama, Kohei; Hachisuka, Toshiya

doi:10.48550/arxiv.1707.07394

Cited by 31 publications

(38 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conventional 2D CNN can be considered a limited version of a multi-resolution CNN that can consider both spectral and spatial information [26]. Previous works have been successful in establishing the convolution and pooling function in a 2D CNN as filtering and downsampling [27]. A basic CNN can be mathematically represented as the weighed sum of nearest neighbours with an added constant bias.…”

Section: Spectralnetmentioning

confidence: 99%

SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

Chakraborty,

Trehan

2021

Preprint

View full text Add to dashboard Cite

Hyperspectral Image (HSI) classification using Convolutional Neural Networks (CNN) is widely found in the current literature. Approaches vary from using SVMs to 2D CNNs, 3D CNNs, 3D-2D CNNs. Besides 3D-2D CNNs and FuSENet, the other approaches do not consider both the spectral and spatial features together for HSI classification task, thereby resulting in poor performances. 3D CNNs are computationally heavy and are not widely used, while 2D CNNs do not consider multiresolution processing of images, and only limits itself to the spatial features. Even though 3D-2D CNNs try to model the spectral and spatial features their performance seems limited when applied over multiple dataset. In this article, we propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification. A wavelet CNN uses layers of wavelet transform to bring out spectral features. Computing a wavelet transform is lighter than computing 3D CNN. The spectral features extracted are then connected to the 2D CNN which bring out the spatial features, thereby creating a spatialspectral feature vector for classification. Overall a better model is achieved that can classify multi-resolution HSI data with high accuracy. Experiments performed with SpectralNET on benchmark dataset, i.e. Indian Pines, University of Pavia, and Salinas Scenes confirm the superiority of proposed SpectralNET with respect to the state-of-the-art methods. The code is publicly available in https://github.com/tanmay-ty/SpectralNET.

show abstract

Section: Spectralnetmentioning

confidence: 99%

SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

Chakraborty,

Trehan

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Wavelet-based methods have been explored in some computer vision tasks, including classification [7,38,29,57], network compression [28,11], face aging [36], super-resolution [19,35], style transfer [63], etc. Fujieda et al [7] proposed wavelet CNNs that utilize spectral information to classify the textures. Liu et al [36] used a wavelet-based method to capture agerelated texture details at multiple scales in the frequency domain.…”

Section: Related Workmentioning

confidence: 99%

“…We argue that image demoiréing can be more easily handled in the frequency domain. Wavelet-based methods have been explored in computer vision and shown good performance, e.g., in classification [7,38], network compression [28,11], and face super-resolution [19]. However, due to their taskspecific design, these methods cannot be directly used for image demoiréing.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-Based Dual-Branch Network for Image Demoireing

Liu

Yuan

et al. 2020

Preprint

View full text Add to dashboard Cite

When smartphone cameras are used to take photos of digital screens, usually moiré patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoiréing. Existing image restoration methods working in the RGB domain have difficulty in distinguishing moiré patterns from true scene texture. Unlike these methods, our network removes moiré patterns in the wavelet domain to separate the frequencies of moiré patterns from the image content. The network combines dense convolution modules and dilated convolution modules supporting large receptive fields. Extensive experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moiré artifacts on non-screen images. Although designed for image demoiréing, WDNet has been applied to two other low-level vision tasks, outperforming state-of-the-art image deraining and deraindrop methods on the Rain100h and Raindrop800 data sets, respectively.

show abstract

“…In their work, they proposed that features extracted by the fully connected layers of CNN architectures like AlexNet [9], based on shape information , are of very little importance in texture understanding. Wavelet CNNs proposed by S Fujieda et al [10] incorporate spectral information to enhance texture classification.…”

Section: Related Workmentioning

confidence: 99%

On-device Filtering of Social Media Images for Efficient Storage

Jain

Mohanty

Roy

et al. 2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Artificially crafted images such as memes, seasonal greetings, etc are flooding the social media platforms today. These eventually start occupying a lot of internal memory of smartphones and it gets cumbersome for the user to go through hundreds of images and delete these synthetic images. To address this, we propose a novel method based on Convolutional Neural Networks (CNNs) for the on-device filtering of social media images by classifying these synthetic images and allowing the user to delete them in one go. The custom model uses depthwise separable convolution layers to achieve low inference time on smartphones. We have done an extensive evaluation of our model on various camera image datasets to cover most aspects of images captured by a camera. Various sorts of synthetic social media images have also been tested. The proposed solution achieves an accuracy of 98.25% on the Places-365 dataset and 95.81% on the Synthetic image dataset that we have prepared containing 30K instances.

show abstract

Wavelet Convolutional Neural Networks for Texture Classification

Cited by 31 publications

References 25 publications

SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

Wavelet-Based Dual-Branch Network for Image Demoireing

On-device Filtering of Social Media Images for Efficient Storage

Contact Info

Product

Resources

About