Search

Image denoising is a fundamental tool in the fields of image processing and computer vision. With the rapid development of multimedia and cloud computing, it has become popular for resource-constrained users to outsource the storage and denoising of massive images. However, it may cause privacy concerns and response delays. In this scenario, we propose an ef F icient priv A cy-prese R ving I mage de N oising sch E me (FARINE) for outsourcing digital images. By introducing a key conversion mechanism, FARINE allows removing noise from a given noisy image using a non-local mean way without leaking any information about the plaintext content. Due to its low computational latency/communication cost, edge computing is considered to improve the user experience. To achieve a dynamic user set efficiently, we design a fine-grained access control mechanism to support user authorization and revocation in multi-user scenarios. Extensive experiments over several benchmark data sets show that FARINE obtains comparable performance to plaintext image denoising.

Image stitching can be employed to stitch images taken from different times, perspectives, or devices into a panorama with a wider view. However, the imaging specification of images to be stitched is strict. If the imaging specification is not satisfied, artefacts caused by inaccurate alignment and unnatural distortion will occur. Semantic segmentation can solve the classification problem at the pixel level; however, image stitching significantly depends on the accuracy of feature points. Therefore, this paper proposes an image stitching algorithm based on semantic segmentation to guide feature point classification and seam fusion. First, the images are recognized by a cascade semantic segmentation network, and the image feature points are classified. Thereafter, the corresponding homography transformations are calculated using different class feature points, and the best homography mapping for the entire target image is selected. Finally, a seam-cutting algorithm based on semantic segmentation is used to compute the seam, and a feathering Poisson fusion with distance transformation is used to eliminate artefacts and light differences. Experiments show that the algorithm can generate transitional natural and perceptual stitching results even under the influence of perspective and light differences.

Internal patch prior (e.g. self-similarity) has achieved a great success in image denoising. However, it is a challenging task to utilize clean external natural patches for denoising. Natural image patch comes from very complex distributions which are hard to learn without supervision. In this paper, we use an autoencoder to discover and utilize these underlying distributions to learn a compact representation that is more robust to realistic noises. By exploiting learned external prior and internal self-similarity jointly, we develop an efficient patch sparse coding scheme for real-world image denoising. Numerical experiments demonstrate that the proposed method outperforms many state-of-the-art denoising methods, especially on removing realistic noise.

Modeling the implied volatility has received extensive attention, as the implied volatility is an important parameter in option pricing. Usually the implied volatility can be approximated by fitting a polynomial about the strike and the maturity or by stochastic methods. In this article, a Gaussian semi-parametric model is proposed based on the quadratic polynomial semi-parametric model suggested by Borovkova. In the new model, the Gaussian function is used to construct a smooth term substituting the quadratic term in the polynomial model, and the arbitrage-free constraints are used to calibrate the model. The empirical tests show that the Gaussian semi-parametric model has a better performance in fitting and forecasting.

The geodesic active contour (GAC) model has been widely used due to the high precision of edge detection and the continuity of boundaries. However, compared to the gradient vector flow (GVF) field, it usually has poor performance in the object boundaries with concave shape. In this paper, the improvements that integrate the good performance of the GAC model and the GVF field are described in detail and the GAC_GVF&B model combining the GAC model with the GVF field and a balloon force is proposed. The experimental results demonstrate that the proposed method is insensitive to the positions of initial curves and can segment complex-shape or multi-objects images correctly with higher convergence.

PDE-based image segmentation based on the active contour model attracts many researchers due to its high precision of edge detection and the continuity of boundaries. Its basic idea is to define an energy functional on a dynamic curve which achieves its minimum when the curve conforms to the boundary of the objects. Thus, the image segmentation problem is in essence an optimization problem. The most widely used optimization method is the gradient descent method in PDE-based image segmentation. However, the convergence of the gradient descent method is very poor. In this paper, a quasi-Newton method is extended to the generalized quasi-Newton method, and then the generalized Newton method and the generalized quasi-Newton method are used to solve a simple region-based model and compared with the gradient decent method. Experimental results show that the generalized quasi-Newton method has accurate segmentation results in the least possible number of iteration. Moreover it is able to segment noisy images correctly.

Wafer dicing is a basic step in building electronic devices such as CPU or GPU. It is automatically accomplished in the wafer Dicing Machine in which a little misalignment of wafers may lead to damaged chips. The information of misalignment may be obtained by detecting the paddle vat to calculate the misalignment between the blade and the part of the wafer which has been diced in real-time. In this paper, methods for detecting the paddle vat are studied. For most of simple wafer images where the intensities of paddle vats are quite different from that of the background, a binary segmentation approach is used to detect the paddle vat of the wafer image. The threshold for binarization is calculated by the grey-scale histogram of the wafer image which is smoothed by using exponentially smoothed method. For wafer images with complex backgrounds, the improved Canny detection algorithm with anisotropic diffusion is used to detect the edges of paddle vats. Experimental results show the validity of the methods.

Digital image inpainting technique has been widely used in many socioeconomic areas and methods based on partial differential equations (PDE) attract intensive research in the hope of an automatic inpainting methodology. However the methods based on PDE are very time-consuming because they need to be solved by numerical integration along the temporal axis. In this paper, a fast convergent image inpainting method is proposed by combining Richardson extrapolation with an improved BSCB inpainting model, which improves the convergence rate of the numerical iterations. Experimental results show that the new model is effective and efficient.

Fourth-order partial differential equation (PDE) proposed by You and Kaveh (You-Kaveh fourth-order PDE), which replaces the gradient operator in classical second-order nonlinear diffusion methods with a Laplacian operator, is able to avoid blocky effects often caused by second-order nonlinear PDEs. However, the equation brought forward by You and Kaveh tends to leave the processed images with isolated black and white speckles. Although You and Kaveh use median filters to filter these speckles, median filters can blur the processed images to some extent, which weakens the result of You-Kaveh fourth-order PDE. In this paper, the reason why You-Kaveh fourth-order PDE can leave the processed images with isolated black and white speckles is analyzed, and a new fourth-order PDE based on the changes of Laplacian (LC fourth-order PDE) is proposed and tested. The new fourth-order PDE preserves the advantage of You-Kaveh fourth-order PDE and avoids leaving isolated black and white speckles. Moreover, the new fourth-order PDE keeps the boundary from being blurred and preserves the nuance in the processed images, so, the processed images look very natural.