PaperlayerView exact revision on arXiv

Source-linked AI summary

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Qiangqiang Yuan, Qiang Zhang, Jie Li, Huanfeng Shen, Liangpei Zhang

arXiv:1806.00183v3cs.CV

TL;DR

HSI noise harms subsequent interpretation, while existing approaches face spectral, tuning, and generality challenges. The paper proposes HSID-CNN, a combined spatial-spectral residual CNN with multi-scale extraction and multi-level representation. Simulated and real-data experiments report stronger denoising evaluation, visual quality, and classification accuracy than mainstream methods.

Abstract

from arXiv · show

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.

I. INTRODUCTION

HSI noise degrades later interpretation, while existing denoising methods struggle with spectral distortion, per-image parameter tuning, and complex spatial-spectral noise. The paper addresses these limitations with HSID-CNN, combining spatial-spectral learning and deep end-to-end restoration.

  • HSIs contain spatial and spectral information but are affected by random noise, stripe noise, and dead pixels.Source: §I · p. 1
  • Noise substantially affects subsequent HSI information interpretation and understanding, making denoising important before analysis.Source: §I · p. 1
  • Band-by-band denoising methods often cause larger spectral distortion because they do not jointly preserve HSI spectral correlations.Source: §I · p. 1
  • Spatial-spectral methods can improve results but require precise parameter tuning for each HSI, making processing unintelligent and time-consuming.Source: §I · p. 1
  • HSI denoising needs a method combining spatial-spectral constraints with deep learning because generic image denoisers do not model spectral redundancy.Source: §I · p. 2
  • HSID-CNN learns a nonlinear end-to-end mapping from noisy to clean HSIs using combined 2D spatial and 3D spatial-spectral convolutions.Source: §I · p. 2

A. Hyperspectral Noise Degradation Model

The section contrasts transform- and spatial-domain HSI denoising approaches with the need for a faster, more efficient, and more universal framework across diverse HSI data.

III. METHODOLOGY

HSID-CNN combines noisy-band spatial data with adjacent-band spectral data in a residual deep CNN, adding multi-scale extraction and multi-level feature fusion for restoration.

The Proposed Framework Description

Joint Spatial-Spectral Multi-Scale Feature Extraction

Deep CNN with Residual Learning Strategy

Multi-Level Feature Representation for Restoration

IV. EXPERIMENTAL RESULTS AND DISCUSSION

The experiments evaluate HSID-CNN against mainstream HSI denoising methods on simulated and real data using normalized imagery and multiple quality measures. The design uses fixed adjacent-band context and datasets from Washington DC Mall, Indian Pines, and University of Pavia.

Experimental Setup

  • HSID-CNN is compared with HSSNR, LRTA, BM4D, and LRMR using MPSNR, MSSIM, and MSA in simulated experiments.Source: §IV · p. 5

Parameter Setting and Network Training

Data and Training

Test Data Sets

A. Simulated-Data Experiments

Table II presents the simulated-experiment results.

  • Table II reports results for the simulated experiments.Source: Table II · p. 6
  • The table is part of the simulated-data experiments section.Source: Table II · p. 6
  • The supplied table passage identifies the results table but provides no individual values.Source: Table II · p. 6

QUANTITATIVE EVALUATION OF THE DENOISING RESULTS OF THE SIMULATED EXPERIMENTS

The simulated experiments evaluate denoising under multiple noise settings using quantitative, visual, spectral, and spectral-difference analyses. HSID-CNN achieves the strongest reported overall performance and preserves spectral features more reliably than the compared methods.

Quantitative evaluation

  • HSID-CNN achieves the highest MPSNR and MSSIM and the lowest MSA across all simulated noise levels.The comparison covers the noise conditions summarized in Table II.Source: QUANTITATIVE EVALUATION OF THE… · p. 6

Visual comparison

  • BM4D suppresses noise under uniform and non-uniform intensities but can over-smooth small texture features.LRTA can generate artifacts, while HSSNR leaves residual noise under strong noise.Source: QUANTITATIVE EVALUATION OF THE… · p. 6

Spectral analysis

  • For pixel (83, 175), the proposed method’s spectral curve is closest to the ground truth among the compared methods.The spectral plots use DN values across band numbers.Source: QUANTITATIVE EVALUATION OF THE… · p. 8
  • The proposed method produces smoother spectral-difference curves with residual values closer to zero for roof, grass, and road classes.The curves compare restoration results with the noise-free HSI across spectral bands.Source: QUANTITATIVE EVALUATION OF THE… · p. 8

B. Real-Data Experiments

Real-world HSI experiments compare denoising methods through supervised classification using a common SVM evaluation setup. Overall accuracy and the kappa coefficient are the reported evaluation indexes.

Real-data evaluation

Classification evaluation

1) AVIRIS Indian Pines Data Set:

On the AVIRIS Indian Pines data set, HSID-CNN removes noise and stripes while retaining local detail and structure. It also achieves the best reported SVM classification performance after denoising.

Denoising results

  • HSID-CNN effectively removes noise and stripes while preserving local details and structural information.The comparison includes HSSNR, LRTA, BM4D, and LRMR restoration results.Source: 1) AVIRIS Indian Pines Data Set · p. 9

Classification results

  • The Indian Pines experiment evaluates 16 ground-truth classes using supervised SVM classification.Training uses 10% of the test samples randomly generated from each class.Source: 1) AVIRIS Indian Pines Data Set · p. 9
  • 85.65% OA and 0.8338 kappa are the highest reported classification values for HSID-CNN.Before denoising, OA and kappa are 75.96% and 0.7220, respectively.Source: 1) AVIRIS Indian Pines Data Set · p. 9

2) ROSIS University of Pavia Data Set:

On Pavia University data, HSID-CNN produced the strongest reported denoising and classification results among the compared methods, while reducing fragmentary effects.

C. Further Discussion

Further experiments examine spectral-band selection, feature modules, deep-learning baselines, and runtime. They identify K = 24 as optimal in the reported experiment and describe HSID-CNN as computationally efficient in GPU mode.

Adjacent spectral band number K

  • The spatial-spectral input uses the current band together with K adjacent spectral bands to exploit redundant correlated information.Source: C. Further Discussion · p. 10
  • HSID-CNN performance first increased with adjacent-band number K and reached its highest MPSNR at K = 24 before declining.Source: C. Further Discussion · pp. 10–11

Multi-scale feature extraction

Multi-level feature representation

Comparisons with DL-based Denoising Methods

Runtime Comparisons

V. CONCLUSION

The paper concludes that HSID-CNN combines spatial-spectral deep learning with multi-scale feature extraction for HSI denoising. Simulated and real-data experiments reported advantages across evaluation indexes, visual quality, and classification accuracy, while future work targets mixed noise and spectral distortion.

  • HSID-CNN learns a non-linear end-to-end mapping from noisy to clean HSIs with a combined spatial-spectral convolutional network.Source: §V · p. 12
  • The network jointly uses spatial information and adjacent correlated bands, with multi-scale extraction for spatial and spectral features.Source: §V · p. 12
  • Experiments on simulated and real data reported better evaluation indexes, visual effects, and classification accuracy than many mainstream methods.Source: §V · p. 12
  • Future work will investigate more efficient structures for mixed noise, including stripe noise, impulse noise, and dead lines.Source: §V · p. 12
  • Future work will also consider priori constraints or structures to reduce spectral distortion and improve texture details.Source: §V · p. 12

Related papers

Loading 1806.00183v3…