Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification

Huang, Wei; Yao, Hongxun; Wang, Hua; Liu, Yan; Shim, Hiuk Jae

doi:10.1109/jstars.2020.3014492

Cited by 33 publications

(14 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dataset: Composed of 112 reflectance images, HyTexiLa [14] is a dataset of spectrally and spatially high resolution texture from five categories i.e. food (10), stone (4), textile (65), vegetation (15), and wood (18). Each image measures 1024 × 1024 pixels with L = 186 spectral bands.…”

Section: A Texture Classification On Hytexilamentioning

confidence: 99%

“…This demonstrates the easy adaptation of RSDOM in a given context thanks to its metrological constructions as opposed to some state-of-the-art which fuzz the spectral and spatial char-acterization. As for GLCM, Gabor filter and LBP approaches, we consider their cross-channel versions applied on the top three principal components (PCs) in line with the common practice in the community [63]- [65]. For ICONES-HSI, this corresponds to an average (over all images) explained variance of 98.0%.…”

Section: B Content-based Image Retrieval On Icones-hsimentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial Distribution

Chu¹,

Richard²,

Chatoux³

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Texture characterization from the metrological point of view is addressed in order to establish a physically relevant and directly interpretable feature. In this regard, a generic formulation is proposed to simultaneously capture the spectral and spatial complexity in hyperspectral images. The feature, named relative spectral difference occurrence matrix (RSDOM) is thus constructed in a multireference, multidirectional, and multiscale context. As validation, its performance is assessed in three versatile tasks. In texture classification on HyTexiLa, content-based image retrieval (CBIR) on ICONES-HSI, and land cover classification on Salinas, RSDOM registers 98.5% accuracy, 80.3% precision (for the top 10 retrieved images), and 96.0% accuracy (after post-processing) respectively, outcompeting GLCM, Gabor filter, LBP, SVM, CCF, CNN, and GCN. Analysis shows the advantage of RSDOM in terms of feature size (a mere 126, 30, and 20 scalars using GMM in order of the three tasks) as well as metrological validity in texture representation regardless of the spectral range, resolution, and number of bands.

show abstract

Section: A Texture Classification On Hytexilamentioning

confidence: 99%

Section: B Content-based Image Retrieval On Icones-hsimentioning

confidence: 99%

Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial Distribution

Chu¹,

Richard²,

Chatoux³

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The above process was implemented iteratively on the input images to create the entire pyramid. Each phase of pyramid generation was realized on OpenCV [23]. The target size was set to the default input size of our CNN: 32*32; the output image size was strictly controlled to half the size of the original image.…”

Section: Preprocessing Of Financial Instrumentsmentioning

confidence: 99%

An Image Classification Algorithm of Financial Instruments Based on Convolutional Neural Network

Dong¹,

Li²

2020

View full text Add to dashboard Cite

The boom of global economy has caused an explosive growth in the issuance and use of financial instruments. Traditionally, the financial instruments are recognized and classified manually, which increases the burden of financial staff and consumes lots of financial time. To solve the problems, this paper designs a convolutional neural network (CNN) for classification of financial instruments, covering components like traditional CNN, shallow convolutional layers, and cropping structure. Then, the momentum weight update was combined with weight attenuation to accelerate the model learning. In addition, the authors designed a preprocessing method for rapid pixel-level adjustment of financial instruments, enabling the proposed CNN to classify financial instruments of various sizes. Experiments show that our CNN can identify various financial instruments, and classify them at an accuracy as high as 96%.

show abstract

“…The development of emerging computing technologies (e.g., cloud computing) have brought opportunity for various industries, such as hyperspectral remote sensing image algorithms [1,2], classification algorithms [3], matrix operations under linear systems [4,5], and data generated by Internet of Things (IoT) devices. If the data in a solution is stored in the cloud or the calculation is outsourced to the cloud, the local storage and calculation pressure will be greatly reduced.…”

Section: Introductionmentioning

confidence: 99%

A Privacy Protection Scheme for IoT Big Data Based on Time and Frequency Limitation

Zhang

Huo

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Various applications of the Internet of Things assisted by deep learning such as autonomous driving and smart furniture have gradually penetrated people’s social life. These applications not only provide people with great convenience but also promote the progress and development of society. However, how to ensure that the important personal privacy information in the big data of the Internet of Things will not be leaked when it is stored and shared on the cloud is a challenging issue. The main challenges include (1) the changes in access rights caused by the flow of manufacturers or company personnel while sharing and (2) the lack of limitation on time and frequency. We propose a data privacy protection scheme based on time and decryption frequency limitation that can be applied in the Internet of Things. Legitimate users can obtain the original data, while users without a homomorphic encryption key can perform operation training on the homomorphic ciphertext. On the one hand, this scheme does not affect the training of the neural network model, on the other hand, it improves the confidentiality of data. Besides that, this scheme introduces a secure two-party agreement to improve security while generating keys. While revoking, each attribute is specified for the validity period in advance. Once the validity period expires, the attribute will be revoked. By using storage lists and setting tokens to limit the number of user accesses, it effectively solves the problem of data leakage that may be caused by multiple accesses in a long time. The theoretical analysis demonstrates that the proposed scheme can not only ensure safety but also improve efficiency.

show abstract

Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification

Cited by 33 publications

References 59 publications

Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial Distribution

Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial Distribution

An Image Classification Algorithm of Financial Instruments Based on Convolutional Neural Network

A Privacy Protection Scheme for IoT Big Data Based on Time and Frequency Limitation

Contact Info

Product

Resources

About