The Experts below are selected from a list of 60051 Experts worldwide ranked by ideXlab platform
Jianjiun Ding - One of the best experts on this subject based on the ideXlab platform.
-
occluded face recognition using low rank regression with generalized Gradient Direction
arXiv: Image and Video Processing, 2019Co-Authors: Jianjiun DingAbstract:In this paper, a very effective method to solve the contiguous face occlusion recognition problem is proposed. It utilizes the robust image Gradient Direction features together with a variety of mapping functions and adopts a hierarchical sparse and low-rank regression model. This model unites the sparse representation in dictionary learning and the low-rank representation on the error term that is usually messy in the Gradient domain. We call it the "weak low-rankness" optimization problem, which can be efficiently solved by the framework of Alternating Direction Method of Multipliers (ADMM). The optimum of the error term has a similar weak low-rank structure as the reference error map and the recognition performance can be enhanced by leaps and bounds using weak low-rankness optimization. Extensive experiments are conducted on real-world disguise / occlusion data and synthesized contiguous occlusion data. These experiments show that the proposed Gradient Direction-based hierarchical adaptive sparse and low-rank (GD-HASLR) algorithm has the best performance compared to state-of-the-art methods, including popular convolutional neural network-based methods.
-
occluded face recognition using low rank regression with generalized Gradient Direction
Pattern Recognition, 2018Co-Authors: Jianjiun DingAbstract:Abstract In this paper, we propose a the Gradient Direction-based hierarchical adaptive sparse and low-rank (GD-HASLR) model, to solve the real-world occluded face recognition problem. In the real-world scenario, neutral face images as training data are very few, usually a single image per subject. The proposed GD-HASLR has the ability to tackle this scenario. We first utilize the robustness of image Gradient Direction features with the proposed generalized image Gradient Direction. We then propose a novel hierarchical sparse and low-rank model, which combines sparse representation on dictionary learning and low-rank representation on the error, which are usually messy in the Gradient Direction domain. We call this scenario the weak low-rankness optimization. We solve this problem efficiently under the alternating Direction method of multipliers framework, resulting in the optimum error term that has a similar weak low-rank structure as the reference error map. The recognition accuracy can be enhanced greatly via weak low-rankness optimization. Extensive experiments are conducted using real-world disguise/occlusion data and synthesized contiguous occlusion data. These results show that with very few neutral face images as training data, the proposed GD-HASLR model has the best performance compared to other state-of-the-art methods, including popular convoluntional neural nework-based methods.
-
efficient edge oriented based image interpolation algorithm for non integer scaling factor
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017Co-Authors: Jianjiun DingAbstract:Though image interpolation has been developed for many years, most of state-of-the-art methods, including machine learning based methods, can only zoom the image with the scaling factor of 2, 3, 2k, or other integer values. Hence, the bicubic interpolation method is still a popular method for the non-integer scaling problem. In this paper, we propose a novel interpolation algorithm for image zooming with non-integer scaling factors based on the Gradient Direction. The proposed method first estimates the Gradient Direction for each pixel in the low resolution image. Then, we construct the Gradient map for the high resolution image by the spline interpolation method. Finally, the intensity of missing pixels can be computed by the weighted sum of the pixels in the pre-defined window. To preserve the edge information during the interpolation process, the weight is determined by the inner product of the estimated Gradient vector and the vector from the missing pixel to the known data point. Simulations show that the proposed method has higher performance than other non-integer time scaling methods and is helpful for superresolution.
Tian Junwei - One of the best experts on this subject based on the ideXlab platform.
-
sub pixel edge detection algorithm based on gauss fitting
Journal of Computer Applications, 2011Co-Authors: Tian JunweiAbstract:Concerning the low accuracy in localization and sensitivity to noise in traditional edge detection algorithms,a sub-pixel edge detection algorithm based on function curve fitting,Gauss fitting of Gradient Direction sub-pixel edge detection algorithm was proposed.This method firstly chosed a series of points near the edge,then got the grey level of these points,and then tried to get the Gradient level of these points.Then Gauss curves were used to fit the Gradient levels of these points.Finally the axis of the Gauss curves was got by fitting,and the position of axis would be the sub-pixel edge position.The experimental results show that this algorithm can localize the sub-pixel edge position accurately.The comparision with other two algorithms shows that the running time of this algorithm is shorter,and the efficiency is relatively higher.
Rabab K Ward - One of the best experts on this subject based on the ideXlab platform.
-
robust image watermarking based on multiscale Gradient Direction quantization
IEEE Transactions on Information Forensics and Security, 2011Co-Authors: Ehsan Nezhadarya, Z J Wang, Rabab K WardAbstract:We propose a robust quantization-based image watermarking scheme, called the Gradient Direction watermarking (GDWM), based on the uniform quantization of the Direction of Gradient vectors. In GDWM, the watermark bits are embedded by quantizing the angles of significant Gradient vectors at multiple wavelet scales. The proposed scheme has the following advantages: 1) increased invisibility of the embedded watermark because the watermark is embedded in significant Gradient vectors, 2) robustness to amplitude scaling attacks because the watermark is embedded in the angles of the Gradient vectors, and 3) increased watermarking capacity as the scheme uses multiple-scale embedding. The Gradient vector at a pixel is expressed in terms of the discrete wavelet transform (DWT) coefficients. To quantize the Gradient Direction, the DWT coefficients are modified based on the derived relationship between the changes in the coefficients and the change in the Gradient Direction. Experimental results show that the proposed GDWM outperforms other watermarking methods and is robust to a wide range of attacks, e.g., Gaussian filtering, amplitude scaling, median filtering, sharpening, JPEG compression, Gaussian noise, salt & pepper noise, and scaling.
-
a new scheme for robust Gradient vector estimation in color images
IEEE Transactions on Image Processing, 2011Co-Authors: Ehsan Nezhadarya, Rabab K WardAbstract:Gradient estimators are mostly designed to yield accurate and robust estimates of the Gradient magnitude, not the Gradient Direction. This paper proposes a method for the accurate and robust estimation of both the Gradient magnitude and Direction. It robustly estimates the Gradient in the x- and y-Directions. The robustness against noise is achieved by prefiltering and postfiltering of the Gradient in each Direction. To reduce edge blurring effects introduced by these filters, the Gradient in a certain Direction is obtained by applying the prefilter and postfilter in the perpendicular Direction. The basic elements employed in each window are: highpass, lowpass and aggregation operators. The highpass operator is used as a Gradient estimator, the lowpass operator is for prefiltering and postfiltering, and the aggregation operator is for aggregating the prefiltered and postfiltered Gradients. Four different combinations of highpass, lowpass and aggregation operators are proposed: MVD-Median-Mean, MVD-Median-Max, RCMG-Median-Mean, and RCMG-Median-Max. Experimental results show that the RCMG-Median-Mean has the best performance in estimating the Gradient and detecting the edges in noisy color images. It is computationally more efficient than the state-of-the-art Gradient estimators and is able to accurately estimate the Gradient Direction as well as the Gradient magnitude. Computer simulation results show that the proposed method outperforms other recently proposed color Gradient estimators and edge detectors.
Siddhivinayak Kulkarni - One of the best experts on this subject based on the ideXlab platform.
-
A new reliability analysis method based on the conjugate Gradient Direction
Structural and Multidisciplinary Optimization, 2015Co-Authors: Ghasem Ezzati, Musa Mammadov, Siddhivinayak KulkarniAbstract:Reliability-based design optimization (RBDO) is an important area in structural optimization. A principal step of the RBDO process is to solve a reliability analysis problem. This problem has been considered in inner loop of double-loop RBDO approaches. Although many algorithms have been developed for solving this problem, there are still some challenges. Existing algorithms do not have good convergence rates and often diverge. There is a need to develop more efficient and stable algorithms that can be used for evaluating all performance functions sufficiently. In this paper, a new method, called “Conjugate Gradient Analysis (CGA) Method”, is proposed to apply in the reliability analysis problems. This method is based on the conjugate Gradient method. Some mathematical problems are provided in order to demonstrate the advantages of the proposed method compared with the existing methods.
Laurent J Michot - One of the best experts on this subject based on the ideXlab platform.
-
orientational order of colloidal disk shaped particles under shear flow conditions a rheological small angle x ray scattering study
Journal of Physical Chemistry B, 2010Co-Authors: Isabelle Bihannic, Christophe Baravian, Jerome F L Duval, Erwan Paineau, Florian Meneau, Pierre Levitz, Johann Patrick De Silva, Patrick Davidson, Laurent J MichotAbstract:The structure of a colloidal dispersion consisting of anisometric natural clay particles (beidellite) was followed under shear-flow conditions by small-angle X-ray scattering (SAXS) measurements in a Couette-type cell. It is shown that in this shear-thinning dispersion an orientational order develops with increasing shear rate. By use of two different geometrical configurations for SAXS measurements, corresponding to incident beam parallel and perpendicular to flow velocity Gradient (radial and tangential configurations, respectively), it is observed that SAXS patterns are anisotropic in both geometries, meaning that particles tend to align along a preferred orientation with their normal in velocity Gradient Direction, and further they partly rotate around flow streamlines. Quantitative interpretation of these results is successfully achieved upon derivation of a probability distribution function accounting for biaxial particle orientation. From this distribution and following geometrical arguments, the v...
