The Experts below are selected from a list of 74448 Experts worldwide ranked by ideXlab platform
Tony Vladusich - One of the best experts on this subject based on the ideXlab platform.
-
Enhanced Image classification with a fast learning shallow convolutional neural network
International Joint Conference on Neural Network, 2015Co-Authors: Mark D. Mcdonnell, Tony VladusichAbstract:We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and the absence of iteratively-tuned parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to Image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) Image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods.
-
Enhanced Image classification with a fast-learning shallow convolutional neural network
Proceedings of the International Joint Conference on Neural Networks, 2015Co-Authors: Mark D. Mcdonnell, Tony VladusichAbstract:We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to Image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) Image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods.
Guangming Shi - One of the best experts on this subject based on the ideXlab platform.
-
Image enhancement by entropy maximization and quantization resolution upconversion
IEEE Transactions on Image Processing, 2016Co-Authors: Yi Niu, Guangming ShiAbstract:This article introduces a new contrast enhancement algorithm of tone-preserving entropy maximization. Its design objective is to present the maximal amount of information content in the Enhanced Image, or being optimal in an information theoretical sense, while preventing the loss of tone continuity. The resulting optimization problem can be graph theoretically modeled as the construction of the $K$ -edges maximum-weight path, and it can be solved efficiently by dynamic programming. Moreover, the proposed algorithm is made more effective by being combined with a preprocess of Image restoration that aims to correct quantization errors caused by the analog-to-digital conversion of Image signals. Empirical evidences are provided to demonstrate the superior visual quality obtained by the new Image enhancement algorithm.
-
Image enhancement by entropy maximization and quantization resolution upconversion
International Conference on Image Processing, 2014Co-Authors: Yi Niu, Guangming ShiAbstract:This article introduces a new contrast enhancement algorithm of tone-preserving entropy maximization. Its design objective is to present the maximal amount of information content in the Enhanced Image, or being optimal in an information theoretical sense, while preventing the loss of tone continuity. The resulting optimization problem can be graph-theoretically modeled as the construction of K-edge maximum-weight path, and it can be solved efficiently by dynamic programming. Moreover, the proposed algorithm is made more effective by being combined with a preprocess of Image restoration that aims to correct quantization errors caused by the analog-to-digital conversion of Image signals. Empirical evidences are provided to demonstrate the superior visual quality obtained by the new Image enhancement algorithm.
Huijun Gao - One of the best experts on this subject based on the ideXlab platform.
-
gradient histogram estimation and preservation for texture Enhanced Image denoising
IEEE Transactions on Image Processing, 2014Co-Authors: Wangmeng Zuo, Lei Zhang, Chunwei Song, David Zhang, Huijun GaoAbstract:Natural Image statistics plays an important role in Image denoising, and various natural Image priors, including gradient-based, sparse representation-based, and nonlocal self-similarity-based ones, have been widely studied and exploited for noise removal. In spite of the great success of many denoising algorithms, they tend to smooth the fine scale Image textures when removing noise, degrading the Image visual quality. To address this problem, in this paper, we propose a texture Enhanced Image denoising method by enforcing the gradient histogram of the denoised Image to be close to a reference gradient histogram of the original Image. Given the reference gradient histogram, a novel gradient histogram preservation (GHP) algorithm is developed to enhance the texture structures while removing noise. Two region-based variants of GHP are proposed for the denoising of Images consisting of regions with different textures. An algorithm is also developed to effectively estimate the reference gradient histogram from the noisy observation of the unknown Image. Our experimental results demonstrate that the proposed GHP algorithm can well preserve the texture appearance in the denoised Images, making them look more natural.
Joachim E Wildberger - One of the best experts on this subject based on the ideXlab platform.
-
evaluation of low energy contrast Enhanced spectral mammography Images by comparing them to full field digital mammography using euref Image quality criteria
European Radiology, 2015Co-Authors: Ulrich Lalji, Cecile R L P N Jeukens, Ivo Houben, Patty J Nelemans, R E Van Engen, E Van Wylick, R G H Beetstan, Joachim E WildbergerAbstract:Objective Contrast-Enhanced spectral mammography (CESM) examination results in a low-energy (LE) and contrast-Enhanced Image. The LE appears similar to a full-field digital mammogram (FFDM). Our aim was to evaluate LE CESM Image quality by comparing it to FFDM using criteria defined by the European Reference Organization for Quality Assured Breast Screening and Diagnostic Services (EUREF).
Mark D. Mcdonnell - One of the best experts on this subject based on the ideXlab platform.
-
Enhanced Image classification with a fast learning shallow convolutional neural network
International Joint Conference on Neural Network, 2015Co-Authors: Mark D. Mcdonnell, Tony VladusichAbstract:We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and the absence of iteratively-tuned parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to Image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) Image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods.
-
Enhanced Image classification with a fast-learning shallow convolutional neural network
Proceedings of the International Joint Conference on Neural Networks, 2015Co-Authors: Mark D. Mcdonnell, Tony VladusichAbstract:We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to Image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) Image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods.