The Experts below are selected from a list of 9336 Experts worldwide ranked by ideXlab platform
Peter A N Bosman - One of the best experts on this subject based on the ideXlab platform.
-
on the usefulness of Gradient Information in multi objective deformable image registration using a b spline based dual dynamic transformation model comparison of three optimization algorithms
Proceedings of SPIE, 2015Co-Authors: Kleopatra Pirpinia, Peter A N Bosman, Janjakob Sonke, Marcel Van Herk, Tanja AlderliestenAbstract:The use of Gradient Information is well-known to be highly useful in single-objective optimization-based image registration methods. However, its usefulness has not yet been investigated for deformable image registration from a multi-objective optimization perspective. To this end, within a previously introduced multi-objective optimization framework, we use a smooth B-spline-based dual-dynamic transformation model that allows us to derive Gradient Information analytically, while still being able to account for large deformations. Within the multi-objective framework, we previously employed a powerful evolutionary algorithm (EA) that computes and advances multiple outcomes at once, resulting in a set of solutions (a so-called Pareto front) that represents efficient trade-offs between the objectives. With the addition of the B-spline-based transformation model, we studied the usefulness of Gradient Information in multiobjective deformable image registration using three different optimization algorithms: the (Gradient-less) EA, a Gradientonly algorithm, and a hybridization of these two. We evaluated the algorithms to register highly deformed images: 2D MRI slices of the breast in prone and supine positions. Results demonstrate that Gradient-based multi-objective optimization significantly speeds up optimization in the initial stages of optimization. However, allowing sufficient computational resources, better results could still be obtained with the EA. Ultimately, the hybrid EA found the best overall approximation of the optimal Pareto front, further indicating that adding Gradient-based optimization for multiobjective optimization-based deformable image registration can indeed be beneficial
-
Medical Imaging: Image Processing - On the usefulness of Gradient Information in multi-objective deformable image registration using a B-spline-based dual-dynamic transformation model: comparison of three optimization algorithms
Proceedings of SPIE, 2015Co-Authors: Kleopatra Pirpinia, Peter A N Bosman, Janjakob Sonke, Marcel Van Herk, Tanja AlderliestenAbstract:The use of Gradient Information is well-known to be highly useful in single-objective optimization-based image registration methods. However, its usefulness has not yet been investigated for deformable image registration from a multi-objective optimization perspective. To this end, within a previously introduced multi-objective optimization framework, we use a smooth B-spline-based dual-dynamic transformation model that allows us to derive Gradient Information analytically, while still being able to account for large deformations. Within the multi-objective framework, we previously employed a powerful evolutionary algorithm (EA) that computes and advances multiple outcomes at once, resulting in a set of solutions (a so-called Pareto front) that represents efficient trade-offs between the objectives. With the addition of the B-spline-based transformation model, we studied the usefulness of Gradient Information in multiobjective deformable image registration using three different optimization algorithms: the (Gradient-less) EA, a Gradientonly algorithm, and a hybridization of these two. We evaluated the algorithms to register highly deformed images: 2D MRI slices of the breast in prone and supine positions. Results demonstrate that Gradient-based multi-objective optimization significantly speeds up optimization in the initial stages of optimization. However, allowing sufficient computational resources, better results could still be obtained with the EA. Ultimately, the hybrid EA found the best overall approximation of the optimal Pareto front, further indicating that adding Gradient-based optimization for multiobjective optimization-based deformable image registration can indeed be beneficial
-
GECCO - Exploiting Gradient Information in numerical multi--objective evolutionary optimization
Proceedings of the 2005 conference on Genetic and evolutionary computation - GECCO '05, 2005Co-Authors: Peter A N Bosman, Edwin D De JongAbstract:Various multi--objective evolutionary algorithms (MOEAs) have obtained promising results on various numerical multi--objective optimization problems. The combination with Gradient--based local search operators has however been limited to only a few studies. In the single--objective case it is known that the additional use of Gradient Information can be beneficial. In this paper we provide an analytical parametric description of the set of all non--dominated (i.e. most promising) directions in which a solution can be moved such that its objectives either improve or remain the same. Moreover, the parameters describing this set can be computed efficiently using only the Gradients of the individual objectives. We use this result to hybridize an existing MOEA with a local search operator that moves a solution in a randomly chosen non--dominated improving direction. We test the resulting algorithm on a few well--known benchmark problems and compare the results with the same MOEA without local search and the same MOEA with Gradient--based techniques that use only one objective at a time. The results indicate that exploiting Gradient Information based on the non--dominated improving directions is superior to using the Gradients of the objectives separately and that it can furthermore improve the result of MOEAs in which no local search is used, given enough evaluations.
-
exploiting Gradient Information in numerical multi objective evolutionary optimization
Genetic and Evolutionary Computation Conference, 2005Co-Authors: Peter A N Bosman, Edwin D De JongAbstract:Various multi--objective evolutionary algorithms (MOEAs) have obtained promising results on various numerical multi--objective optimization problems. The combination with Gradient--based local search operators has however been limited to only a few studies. In the single--objective case it is known that the additional use of Gradient Information can be beneficial. In this paper we provide an analytical parametric description of the set of all non--dominated (i.e. most promising) directions in which a solution can be moved such that its objectives either improve or remain the same. Moreover, the parameters describing this set can be computed efficiently using only the Gradients of the individual objectives. We use this result to hybridize an existing MOEA with a local search operator that moves a solution in a randomly chosen non--dominated improving direction. We test the resulting algorithm on a few well--known benchmark problems and compare the results with the same MOEA without local search and the same MOEA with Gradient--based techniques that use only one objective at a time. The results indicate that exploiting Gradient Information based on the non--dominated improving directions is superior to using the Gradients of the objectives separately and that it can furthermore improve the result of MOEAs in which no local search is used, given enough evaluations.
-
exploiting Gradient Information in continuous iterated density estimation evolutionary algorithms
2001Co-Authors: Peter A N Bosman, Dirk ThierensAbstract:For continuous optimization problems, evolutionary algorithms (EAs) that build and use probabilistic models have obtained promising results. However, the local Gradient Information of the fitness function is not used in these EAs. In the case of optimization of continuous differentiable functions, it may be less efficient to disregard this Information. In this paper, we therefore hybridize pure continuous iterated density estimation evolutionary algorithms (IDEAs) by using the conjugate Gradient algorithm on a selection of the solutions. We test the resulting algorithm on a few well known difficult continuous differentiable function optimization problems. The results indicate that exploiting Gradient Information in probabilistic model building EAs leads to more efficient continuous optimization
Zheng Wang - One of the best experts on this subject based on the ideXlab platform.
-
Method of Detection Optimization Based on Vector Electric Field Multi-electrode Gradient Information
Lecture Notes in Electrical Engineering, 2017Co-Authors: Chao Wu, Zheng Wang, Yubo Wang, Chengbo Hu, Yongling Lu, Xujie HeAbstract:This paper presents a method that the algorithm of calculating the electric field combining with vector electric field multi-electrode Gradient Information is optimized by using the compression-aware greedy reconstruction algorithm, which can effectively identify the electric field Gradient Information and improve the accuracy rate of the voltage level detection judgment, through the research on the calculation method of the electric field Gradient Information of the electrical equipment in the substation. This method can accurately calculate the electric field distribution and voltage level around the high voltage conductor by analyzing the electric field Information around the charged body. The distribution of the field strength at one interval of the charged carrier is obtained by tested in complex power frequency electric field environment of the 110 kV substation equipment. The results show that the method can effectively improve the detection capability of the voltage level of the charged carrier and the response speed of the electric field around the charged body, and improve the safety of the staff working in the complex electric field.
-
hole filling for dibr based on depth and Gradient Information
International Journal of Advanced Robotic Systems, 2015Co-Authors: Dan Wang, Zheng Wang, Yan Zhao, Hexin ChenAbstract:Depth image-based rendering (DIBR) is a method for generating new virtual images from known viewpoints. However, holes often appear in the rendered virtual images due to occlusion and inaccurate depth Information. In this paper, we present a novel hole-filling algorithm to improve the image quality of DIBR. In the proposed method, depth Information is added to the priority calculation function when determining the order of hole-filling. Then, the Gradient Information is used as auxiliary Information when searching for the optimal matching block. Experimental results show that the proposed algorithm achieves better objective quality and also improves the subjective quality of the rendered images.
-
A hole filling algorithm for depth image based rendering based on Gradient Information
2013 Ninth International Conference on Natural Computation (ICNC), 2013Co-Authors: Dan Wang, Yan Zhao, Jing-yuan Wang, Zheng WangAbstract:The Depth Image Based Rendering (DIBR) is a method for generating new virtual images from known viewpoints, and the hole problem is one of the most critical issues in DIBR. In this paper, a new hole-filling technique based on Gradient informaton is proposed to improve the quality of the images generated by 3D image warping. Firstly, a virtual image is created by DIBR. Then, the Gradient Information is used as auxiliary Information when searching for the best matching block. Experimental results show that the presented algorithm provides better effects than others.
-
ICNC - A hole filling algorithm for depth image based rendering based on Gradient Information
2013 Ninth International Conference on Natural Computation (ICNC), 2013Co-Authors: Dan Wang, Yan Zhao, Jing-yuan Wang, Zheng WangAbstract:The Depth Image Based Rendering (DIBR) is a method for generating new virtual images from known viewpoints, and the hole problem is one of the most critical issues in DIBR. In this paper, a new hole-filling technique based on Gradient informaton is proposed to improve the quality of the images generated by 3D image warping. Firstly, a virtual image is created by DIBR. Then, the Gradient Information is used as auxiliary Information when searching for the best matching block. Experimental results show that the presented algorithm provides better effects than others.
Hao Zheng - One of the best experts on this subject based on the ideXlab platform.
-
exploring deep Gradient Information for biometric image feature representation
Neurocomputing, 2016Co-Authors: Jianjun Qian, Jian Yang, Hao ZhengAbstract:Abstract This paper presents a novel but simple biometric image feature representation method, called exploring deep Gradient Information (DGI). DGI first captures the local structure of an image by computing the histogram of Gradient orientation of each macro-pixel (local patch around the reference pixel). Thus, one image can be decomposed into L sub-images (sub-orientation images) according to the Gradient Information of each macro-pixel since there are L bins in the local histogram. To enrich the Gradient Information, we also consider the Gradient orientation and magnitude of original image as sub-images. For each sub-image, histogram of oriented Gradient (HOG) is used to further explore the Gradient orientation Information. All HOG features are concatenated into one augmented super-vector. Finally, fisher linear discriminate analysis (FLDA) is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW, the PolyU Finger-Knuckle-Print database and the PolyU Palmprint database. Experimental results clearly demonstrate the effectiveness of the proposed DGI compared with state-of-the-art algorithms, e.g., SIFT, HOG, LBP, POEM, LARK and IDLS.
Jianjun Qian - One of the best experts on this subject based on the ideXlab platform.
-
CCCV (2) - Exploring Deep Gradient Information for Face Recognition
Communications in Computer and Information Science, 2020Co-Authors: Jianjun Qian, Jian YangAbstract:This paper presents a novel and simple image feature extraction method, called exploring deep Gradient Information (DGI), for face recognition. DGI first captures the local structure of an image by computing the histogram of Gradient orientation of each macro-pixel (local patch around the central pixel). One image can be decomposed into L sub-images (also called orientation images) according to the structure Information of each macro-pixel since there are L bins in the local histogram. For each orientation image, dense scale invariant feature transform (DSIFT) is used to further explore the Gradient orientation Information. All DSIFT feature are concatenated into one augmented super-vector. Finally, dimensionality reduction technology is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW. In all experiments, DGI achieves competitive results compared with state-of-the-art algorithms.
-
exploring deep Gradient Information for biometric image feature representation
Neurocomputing, 2016Co-Authors: Jianjun Qian, Jian Yang, Hao ZhengAbstract:Abstract This paper presents a novel but simple biometric image feature representation method, called exploring deep Gradient Information (DGI). DGI first captures the local structure of an image by computing the histogram of Gradient orientation of each macro-pixel (local patch around the reference pixel). Thus, one image can be decomposed into L sub-images (sub-orientation images) according to the Gradient Information of each macro-pixel since there are L bins in the local histogram. To enrich the Gradient Information, we also consider the Gradient orientation and magnitude of original image as sub-images. For each sub-image, histogram of oriented Gradient (HOG) is used to further explore the Gradient orientation Information. All HOG features are concatenated into one augmented super-vector. Finally, fisher linear discriminate analysis (FLDA) is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW, the PolyU Finger-Knuckle-Print database and the PolyU Palmprint database. Experimental results clearly demonstrate the effectiveness of the proposed DGI compared with state-of-the-art algorithms, e.g., SIFT, HOG, LBP, POEM, LARK and IDLS.
Shaomin Zhang - One of the best experts on this subject based on the ideXlab platform.
-
ISCID (2) - Research of Non-rigid Medical Image Registration Based on Gradient Information
2017 10th International Symposium on Computational Intelligence and Design (ISCID), 2017Co-Authors: Shaomin ZhangAbstract:In many clinical applications, non-rigid transforms are often used to describe the spatial relationships between images. The conventional image registration approaches often consider intensity Information, ignoring the spatial Information between pixels. To solve the problem, this paper proposes a non-rigid medical image registration algorithm based on Gradient Information. First, Gradient feature of each sample point is obtained for the reference image and floating image. Second, the pixel intensity and the Gradient feature are applied into non-rigid medical image registration. Comparison results of the images obtained from lung and brain images showed that the proposed algorithm provides better accuracy than both the conventional rigid registration algorithm and the non-rigid registration algorithm based on single pixel gray values.
-
Research of Non-rigid Medical Image Registration Based on Gradient Information
2017 10th International Symposium on Computational Intelligence and Design (ISCID), 2017Co-Authors: Shaomin ZhangAbstract:In many clinical applications, non-rigid transforms are often used to describe the spatial relationships between images. The conventional image registration approaches often consider intensity Information, ignoring the spatial Information between pixels. To solve the problem, this paper proposes a non-rigid medical image registration algorithm based on Gradient Information. First, Gradient feature of each sample point is obtained for the reference image and floating image. Second, the pixel intensity and the Gradient feature are applied into non-rigid medical image registration. Comparison results of the images obtained from lung and brain images showed that the proposed algorithm provides better accuracy than both the conventional rigid registration algorithm and the non-rigid registration algorithm based on single pixel gray values.
