Shuigen Wang

NMF-Based Image Quality Assessment Using Extreme Learning Machine

Numerous state-of-the-art perceptual image quality assessment (IQA) algorithms share a common two-stage process: distortion description followed by distortion effects pooling. As for the first stage, the distortion descriptors or measurements are expected to be effective representatives of human visual variations, while the second stage should well express the relationship among quality descriptors and the perceptual visual quality. However, most of the existing quality descriptors (e.g., luminance, contrast, and gradient) do not seem to be consistent with human perception, and the effects pooling is often done in ad-hoc ways. In this paper, we propose a novel full-reference IQA metric. It applies non-negative matrix factorization (NMF) to measure image degradations by making use of the parts-based representation of NMF. On the other hand, a new machine learning technique [extreme learning machine (ELM)] is employed to address the limitations of the existing pooling techniques. Compared with neural networks and support vector regression, ELM can achieve higher learning accuracy with faster learning speed. Extensive experimental results demonstrate that the proposed metric has better performance and lower computational complexity in comparison with the relevant state-of-the-art approaches.

Gradient-based no-reference image blur assessment using extreme learning machine

The increasing number of demanding consumer digital multimedia applications has boosted interest in no-reference (NR) image quality assessment (IQA). In this paper, we propose a perceptual NR blur evaluation method using a new machine learning technique, i.e., extreme learning machine (ELM). The proposed metric, Blind Image Blur quality Evaluator (BIBE), exploits scene statistics of gradient magnitudes to model the properties of blurred images, and then the underlying blur features are derived by fitting gradient magnitudes distribution. The resultant feature is finally mapped into an associated quality score using ELM. As subjective evaluation scores by human beings are integrated into training, machine learning techniques can predict image quality more accurately than those traditional methods. Compared with other learning techniques such as support vector machine (SVM), ELM has better learning performance and faster learning speed. Experimental results on public databases show that the proposed BIBE correlates well with human perceived blurriness, and outperforms the state-of-the-art specific NR blur evaluation metrics as well as generic NR IQA methods. Moreover, the application of automatic focusing system for digital cameras further confirms the capability of BIBE.

Fast and Accurate Spatiotemporal Fusion Based Upon Extreme Learning Machine

Spatiotemporal fusion is important in providing high spatial resolution earth observations with a dense time series, and recently, learning-based fusion methods have been attracting broad interest. These algorithms project image patches onto a feature space with the enforcement of a simple mapping to predict the fine resolution patches from the corresponding coarse ones. However, the sophisticated projection, e.g., sparse representation, is always computationally complex and difficult to be implemented on large patches, which cannot grasp enough local structural information in the coarse patches. To address these issues, a novel spatiotemporal fusion method is proposed in this letter, using a powerful learning technique, i.e., extreme learning machine (ELM). Unlike traditional approaches, we devote to learning a mapping function on difference images directly, rather than the sophisticated feature representation followed by a simple mapping. Characterized by good generalization performance and fast speed, the ELM is employed to achieve accurate and fast fine patches prediction. The proposed algorithm is evaluated by five actual data sets of Landsat enhanced thematic mapper plus-moderate resolution imaging spectroradiometer acquisitions and experimental results show that our method obtains better fusion results while achieving much greater speed.

A novel SVD-based image quality assessment metric

Image distortion can be categorized into two aspects: content-dependent degradation and content-independent one. An existing full-reference image quality assessment (IQA) metric cannot deal with these two different impacts well. Singular value decomposition (SVD) as a useful mathematical tool has been used in various image processing applications. In this paper, SVD is employed to separate the structural (content-dependent) and the content-independent components. For each portion, we design a specific assessment model to tailor for its corresponding distortion properties. The proposed models are then fused to obtain the final quality score. Experimental results with the TID database demonstrate that the proposed metric achieves better performance in comparison with the relevant state-of-the-art quality metrics.

A novel NMF-based image quality assessment metric using extreme learning machine

In this paper, we propose a novel image quality assessment (IQA) metric based on nonnegative matrix factorization (NM-F). With nonnegativity and parts-based properties, NMF well demonstrates how human brain learns the parts of objects. This makes NMF distinguished from other feature extraction methods like singular value decomposition (SVD), principal components analysis (PCA), etc. Inspired by this, we adopt NMF to extract image features from reference and distorted images. Extreme learning machine (ELM) [10] is then employed for feature pooling to obtain the overall quality score. Compared with other machine learning techniques such as neural networks and support vector machines (SVMs), ELM provides better generalization performance with much faster learning speed and less human intervene. Experimental results with the TID database demonstrate that the proposed metric achieves better performance in comparison with the relevant state-of-the-art quality metrics and has lower computational complexity.

Saturation-based quality assessment for colorful multi-exposure image fusion

Multi-exposure image fusion is becoming increasingly influential in enhancing the quality of experience of consumer electronics. However, until now few works have been conducted on the performance evaluation of multi-exposure image fusion, especially colorful multi-exposure image fusion. Conventional quality assessment methods for multi-exposure image fusion mainly focus on grayscale information, while ignoring the color components, which also convey vital visual information. We propose an objective method for the quality assessment of colored multi-exposure image fusion based on image saturation, together with texture and structure similarities, which are able to measure the perceived color, texture, and structure information of fused images. The final image quality is predicted using an extreme learning machine with texture, structure, and saturation similarities as image features. Experimental results for a public multi-exposure image fusion database show that the proposed model can accurately predict colored multi-exposure image fusion image quality and correlates well with human perception. Compared with state-of-the-art image quality assessment models for image fusion, the proposed metric has better evaluation performance.

Coarse-to-fine wavelet-based airport detection

Airport detection on optical remote sensing images has attracted great interest in the applications of military optics scout and traffic control. However, most of the popular techniques for airport detection from optical remote sensing images have three weaknesses: 1) Due to the characteristics of optical images, the detection results are often affected by imaging conditions, like weather situation and imaging distortion; and 2) optical images contain comprehensive information of targets, so that it is difficult for extracting robust features (e.g., intensity and textural information) to represent airport area; 3) the high resolution results in large data volume, which makes real-time processing limited. Most of the previous works mainly focus on solving one of those problems, and thus, the previous methods cannot achieve the balance of performance and complexity. In this paper, we propose a novel coarse-to-fine airport detection framework to solve aforementioned three issues using wavelet coefficients. The framework includes two stages: 1) an efficient wavelet-based feature extraction is adopted for multi-scale textural feature representation, and support vector machine(SVM) is exploited for classifying and coarsely deciding airport candidate region; and then 2) refined line segment detection is used to obtain runway and landing field of airport. Finally, airport recognition is achieved by applying the fine runway positioning to the candidate regions. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy and processing efficiency.

Cloud-cover assessment: From spectral properties to spatial domain natural scene statistic

Cloud contamination is the most common defect leading to quality degradation in remote sensing images. Numerous cloud-cover assessment (CCA) methods have been developed in the literature. The traditional Landsat 7 CCA algorithm attempted to detect clouds by taking advantages of different spectral properties from five spectral bands. However, it suffers the weakness of omitting thin cirrus clouds and the requirement of thermal bands. In this paper, we derived an automated CCA (ACCA) model that measures statistical deviations in spatial domain between cloud and clear images. Moreover, it only conducts on panchromatic band image, which can successfully address the limitation of unavailable thermal bands for satellite missions without thermal infrared sensors on board. A database with 400 clear/cloud images is then built for performance testing. Experimental results on the database show that our approach is more consistent with ground truths than the latest Landsat 8 ACCA results.

Kurtosis-Based Blind Noisy Image Quality Assessment in Wavelet Domain

Noise distortions introduced in natural images generally break the initial probability distributions by dispersing image pixels randomly. We found that there exists a big difference between the distributions of Discrete Wavelet Transform (DWT) coefficients of natural images and noisy images: (1) for natural images, their distributions are sharp with high peaked ness and slight tail, (2) for noisy images, the shapes are much flatter with lower peaked ness and heavier tail. Kurtosis is able to measure and differentiate the probability distributions of noisy images with various noise levels. Moreover, the kurtosis values of DWT coefficients are stable for varying frequency filters. In this paper, we propose a Blind Noisy Image Quality Assessment model using Kurtosis (BNIQAK). Five types of noisy images in the three biggest databases are taken for testing BNIQAK. Experimental results show that BNIQAK has better evaluation performance compared with existing blind noisy models, as well as some general blind and full-reference (FR) methods.