Delu Zeng

A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation

In this paper, a new probabilistic method for image enhancement is presented based on a simultaneous estimation of illumination and reflectance in the linear domain. We show that the linear domain model can better represent prior information for better estimation of reflectance and illumination than the logarithmic domain. A maximum a posteriori (MAP) formulation is employed with priors of both illumination and reflectance. To estimate illumination and reflectance effectively, an alternating direction method of multipliers is adopted to solve the MAP problem. The experimental results show the satisfactory performance of the proposed method to obtain reflectance and illumination with visually pleasing enhanced results and a promising convergence rate. Compared with other testing methods, the proposed method yields comparable or better results on both subjective and objective assessments.

A fusion-based enhancing method for weakly illuminated images

We propose a straightforward and efficient fusion-based method for enhancing weakly illumination images that uses several mature image processing techniques. First, we employ an illumination estimating algorithm based on morphological closing to decompose an observed image into a reflectance image and an illumination image. We then derive two inputs that represent luminance-improved and contrast-enhanced versions of the first decomposed illumination using the sigmoid function and adaptive histogram equalization. Designing two weights based on these inputs, we produce an adjusted illumination by fusing the derived inputs with the corresponding weights in a multi-scale fashion. Through a proper weighting and fusion strategy, we blend the advantages of different techniques to produce the adjusted illumination. The final enhanced image is obtained by compensating the adjusted illumination back to the reflectance. Through this synthesis, the enhanced image represents a trade-off among detail enhancement, local contrast improvement and preserving the natural feel of the image. In the proposed fusion-based framework, images under different weak illumination conditions such as backlighting, non-uniform illumination and nighttime can be enhanced. HighlightsA fusion-based method for enhancing various weakly illuminated images is proposed.The proposed method requires only one input to obtain the enhanced image.Different mature image processing techniques can be blended in our framework.Our method has an efficient computation time for practical applications.

Removing Rain from Single Images via a Deep Detail Network

We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN). Inspired by the deep residual network (ResNet) that simplifies the learning process by changing the mapping form, we propose a deep detail network to directly reduce the mapping range from input to output, which makes the learning process easier. To further improve the de-rained result, we use a priori image domain knowledge by focusing on high frequency detail during training, which removes background interference and focuses the model on the structure of rain in images. This demonstrates that a deep architecture not only has benefits for high-level vision tasks but also can be used to solve low-level imaging problems. Though we train the network on synthetic data, we find that the learned network generalizes well to real-world test images. Experiments show that the proposed method significantly outperforms state-of-the-art methods on both synthetic and real-world images in terms of both qualitative and quantitative measures. We discuss applications of this structure to denoising and JPEG artifact reduction at the end of the paper.

Remote Sensing Image Enhancement Using Regularized-Histogram Equalization and DCT

In this letter, an effective enhancement method for remote sensing images is introduced to improve the global contrast and the local details. The proposed method constitutes an empirical approach by using the regularized-histogram equalization (HE) and the discrete cosine transform (DCT) to improve the image quality. First, a new global contrast enhancement method by regularizing the input histogram is introduced. More specifically, this technique uses the sigmoid function and the histogram to generate a distribution function for the input image. The distribution function is then used to produce a new image with improved global contrast by adopting the standard lookup table-based HE technique. Second, the DCT coefficients of the previous contrast improved image are automatically adjusted to further enhance the local details of the image. Compared with conventional methods, the proposed method can generate enhanced remote sensing images with higher contrast and richer details without introducing saturation artifacts.

A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation

We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image. We show that, though it is widely adopted for ease of modeling, the log-transformed image for this task is not ideal. Based on the previous investigation of the logarithmic transformation, a new weighted variational model is proposed for better prior representation, which is imposed in the regularization terms. Different from conventional variational models, the proposed model can preserve the estimated reflectance with more details. Moreover, the proposed model can suppress noise to some extent. An alternating minimization scheme is adopted to solve the proposed model. Experimental results demonstrate the effectiveness of the proposed model with its algorithm. Compared with other variational methods, the proposed method yields comparable or better results on both subjective and objective assessments.

Saliency Detection With Spaces of Background-Based Distribution

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background. Concretely, given the backgroundness prior, eigendecomposition is utilized to create four spaces of background-based distribution (SBD) to model the background, in which a more appropriate metric (Mahalanobis distance) is quoted to delicately measure the saliency of every image patch away from the background. After that, a coarse saliency map is obtained by integrating the four adjusted Mahalanobis distance maps, each of which is formed by the distances between all the patches and background in the corresponding SBD. To be more discriminative, the coarse saliency map is further enhanced into the posterior probability map within Bayesian perspective. Finally, the final saliency map is generated by properly refining the posterior probability map with geodesic distance. Experimental results on two usual datasets show that the proposed method is effective compared with the state-of-the-art algorithms.

Single-trial ERPs denoising via collaborative filtering on ERPs images

The single-trial denoising is still a challenge in both the neuroscience research and signal processing due to poor signal-to-noise ratio. The Event-related Potentials (ERPs) denoising using ERPs image processing has received a significant attention in recent years. Considering the importance of latency and amplitude details in the ERPs analysis, the desirable methods for ERPs denoising are supposed to remove the large noise effectively while keeping the important information of the ERPs signal, latency and amplitude. A collaborative filtering that includes image patch grouping, shrinkage in 3D transform domain, and aggregation is applied to remove the background noise from the ERPs images. The denoising experiments have been evaluated on simulated data and real data using waveform observation, objective criteria calculation, and single-trial classification. The validations have demonstrated that the collaborative filtering is able to remove the noise effectively compared to wavelet and non local means. Moreover, it also preserves the details of the ERPs signals for latency and amplitude estimation simultaneously.

Arranging and Interpolating Sparse Unorganized Feature Points With Geodesic Circular Arc

A novel method to reconstruct object boundaries with geodesic circular arc is proposed in this paper. Within this framework, an energy of circular arc spline is utilized to simultaneously arrange and interpolate each member in the set of sparse unorganized feature points from the desired boundaries. A general form for a family of parametric circular arc spline is firstly derived and followed by a novel method of arranging these feature points by minimizing an energy term depending on the circular arc spline configuration defined on these feature points. With regard to the fact that the energy function is usually nonconvex and nondifferentiable at its critical points, an improved scheme of particle swarm optimizer is given to find the minimum for the energy in this paper. With this improved scheme, each pair of neighboring feature points along the boundaries of the desired objects are picked out from the set of sparse unorganized feature points, and the corresponding directional chord tangent angles are computed simultaneously to finish interpolation. We show experimentally and comparatively that the proposed method can perform effectively to restrict leakage on weak boundaries and premature convergence on long concave boundaries. Besides, it has good noise robustness and can as well extract multiple and open boundaries.

A variational framework for single low light image enhancement using bright channel prior

Low light image enhancement is prerequisite in many fields, such as surveillance systems, road safety and waterway transport. In this paper, a new variational framework using bright channel prior is proposed to address the low light image enhancement problem within a single image. An alternating direction optimization method is employed to solve the variational problem. Experiment results show that the new method can better eliminate the black halo and suppressing the issues of over-enhancement and color distortion when compared with other existing methods.

Pan-sharpening with structural consistency and ℓ1/2 gradient prior

ABSTRACT In this letter, a variational method is proposed for panchromatic (Pan)-sharpening by fusing a low-resolution multispectral image with a high-resolution Pan image to generate a high-resolution multispectral image. Most methods focus on spatial intensity preservation while the proposed method tends to preserve the consistency of the spatial structure information. In addition, an metric is used to estimate gradient prior. The alternating direction method of multipliers and the difference of convex algorithm are used to guarantee the convergence of the algorithm. A large number of experiments show that the proposed method has obvious advantages compared with other advanced methods both subjectively and objectively.