Active Learning for Hyper spectral Image Classification
Gaussian process (GP) classifiers represent a powerful and interesting theoretical framework for the Bayesian classification of hyperspectralimages. However, the collection of labeled samples is time consuming and costly for hyperspectral data, and the training samples available are often not enough for an adequate learning of the GP classifier. Moreover, the computational cost of performing inference using GP classifiers scales cubically with the size of the training set. To address the limitations of GP classifiers for hyperspectral image classification, reducing the label cost and keeping the training set in a moderate size, this paper introduces an active learning (AL) strategy to collect the most informative training samples for manual labeling.
First, we propose three new AL heuristics based on the probabilistic output of GP classifiers aimed at actively selecting the most uncertain and confusing candidate samples from the unlabeled data. Moreover, we develop an incremental model updating scheme to avoid the repeated training of the GP classifiers during the AL process. The proposed approaches are tested on the classification of two realworld hyperspectral data. Comparison with random sampling method reveals a better accuracy gain and faster convergence with the number of queries, and comparison with recent active learning approaches shows a competitive performance. Experimental results also verified the efficiency of the incremental model updating scheme.
Related Image Processing Project Titles:
- Deblurred Images Post-Processing by Poisson Warping.
- Terahertz Imaging Radar With Inverse Aperture Synthesis Techniques: System Structure, Signal Processing, and Experiment Results.
- Colloidal Quantum Dot-Based Light Emitting Diodes With Solution Processed Electron Transporting Layer for Cellular Imaging.
- Image Pair Analysis With Matrix Value Operator.
- Online High Precision Probabilistic Localization of Robotic Fish Using Visual and Inertial Cues.
- Stable Mean Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote Sensing Images.
- Breast Segmentation and Density Estimation in Breast MRI: A Fully Automatic Framework.
- Estimation of Sunlight Direction Using 3D Object Models.
- Spatial Response Matched Filter and Its Application in Radiometric Accuracy Improvement of FY 2 Satellite Thermal Infrared Band.
- Compressed Sensing of a Remote Sensing Image Based on the Priors of the Reference Image.
- Four Class Classification of Skin Lesions With Task Decomposition Strategy.
- A Learning Framework for Age Rank Estimation Based on Face Images With Scattering Transform.
- Microstructural characterization of the pia arachnoid complex using optical coherence tomography.
- Operational BRDF Effects Correction for Wide-Field-of-View Optical Scanners (BREFCOR).
- Influence of the Contact Opening Speed on DC Vacuum Arc.
- Precise Three Dimensional Stereo Localization of Corner Reflectors and Persistent Scatterers With TerraSAR-X.
- Quantifying Tidal Mud Flat Elevations From Fixed-Platform Long-Wave Infrared Imagery.
- Trigger Wave Asynchronous Cellular Logic Array for Fast Binary Image Processing.
- Image Processing for Identification of Sea-Ice Floes and the Floe Size Distributions.
- Hipacc: A Domain Specific Language and Compiler for Image Processing.
- Extraction of Energy Information From Analog Meters Using Image Processing.
- Efficient Learning of Image Super-resolution and Compression Artifact Removal with Semi local Gaussian Processes.
- Combining image processing and laser fault injections for characterizing a hardware AES.
- Image Processing and Analysis for Single Molecule Localization Microscopy: Computation for nanoscale imaging.