The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Convolutional Neural Network (CNN) has received remarkable achievements in hyperspectral image (HSI) classification. However, how to effectively implement spatial context that has been demonstrated to be crucial for classification of HSI is still an open issue. Current CNNs for hyperspectral classification are restricted into a small scale due to small-scale input and limited training samples. Therefore,...
Convolutional neural networks have shown great success on feature extraction from raw input data such as images. Although convolutional neural networks are invariant to translations on the inputs, they are not invariant to other transformations, including rotation and flip. Recent attempts have been made to incorporate more invariance in image recognition applications, but they are not applicable...
Many applications demand proper design and implementation of 0-1 binary compressive sensing (CS) measurement matrices. This paper presents a construction method for such binary CS measurement matrices by training a convolutional neural network (CNN) with 0-1 weights. The desired CS performance of resultant binary measurement matrices can be achieved by designing a proper CNN training procedure. For...
Brain tumors, especially high-grade gliomas, are one of the most lethal cancers for humankind today. Early and accurate diagnosis of tumor grading is the key for subsequent therapy and treatment. In the past, conventional computer-aided diagnosis relies on handcrafted features from magnetic resonance images (MRI), which are usually inaccurate and laborious. Recently, deep neural networks have been...
In functional genomics, small interfering RNA (siRNA) can be used to knockdown gene expression. Usually, a target gene has numerous potential siRNAs, but their efficiencies of gene silencing often varies. Thus, for a successful RNA interference (RNAi), selecting the most effective siRNA is a critical step. Despite various computational algorithms have been developed, the efficacy prediction accuracy...
The challenge in blind image deblurring is to remove the effects of blur with limited prior information about the nature of the blur process. Existing methods often assume that the blur image is produced by linear convolution with additive Gaussian noise. However, including even a small number of outliers to this model in the kernel estimation process can significantly reduce the resulting image quality...
Solving blind image deblurring usually requires defining a data fitting function and image priors. While existing algorithms mainly focus on developing image priors for blur kernel estimation and non-blind deconvolution, only a few methods consider the effect of data fitting functions. In contrast to the state-of-the-art methods that use a single or a fixed data fitting term, we propose a data-driven...
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the...
Recently, with the obvious increasing number of cardiovascular disease, the automatic classification research of Electrocardiogram signals (ECG) has been playing a significantly important part in the clinical diagnosis of cardiovascular disease. In this paper, a 1D convolution neural network (CNN) based method is proposed to classify ECG signals. The proposed CNN model consists of five layers in addition...
With the development of algorithms and computer skills, deep learning using CNN (convolutional neural network) has been applied to various fields, especially in image processing field. In this paper, we designed an improved model based on ResNet with CNN structure, and learned the database. The Chaucer Database used in the experiment consisted of 824 Chinese characters among the Chinese characters...
This work addresses the task of non-blind image deconvolution. Motivated to keep up with the constant increase in image size, with megapixel images becoming the norm, we aim at pushing the limits of efficient FFT-based techniques. Based on an analysis of traditional and more recent learning-based methods, we generalize existing discriminative approaches by using more powerful regularization, based...
We present an approach for blind image deblurring, which handles non-uniform blurs. Our algorithm has two main components: (i) A new method for recovering the unknown blur-field directly from the blurry image, and (ii) A method for deblurring the image given the recovered non-uniform blur-field. Our blur-field estimation is based on analyzing the spectral content of blurry image patches by Re-blurring...
Considering the problems of low recognition rate and poor robustness in traditional recognition algorithms, we propose a license plate character recognition algorithm based on convolution neural network. In this paper, we adopt a coarse-to-fine strategy for designing the network architecture. Through the convolutional layers and pooling layers, features of input images will be extracted and then sent...
This paper deals with the problem of audio source separation. To handle the complex and ill-posed nature of the problems of audio source separation, the current state-of-the-art approaches employ deep neural networks to obtain instrumental spectra from a mixture. In this study, we propose a novel network architecture that extends the recently developed densely connected convolutional network (DenseNet),...
Deep learning is a new field in machine learning research. Convolution neural network is the most important factor in image recognition. This paper mainly focuses on the network design and parameter optimization of convolution neural network. This paper is first based on the traditional handwritten digital classification framework LeNet-5 to improve, and implements the test on the ten and twenty-five...
Crowd counting on still images is very challenging due to heavy occlusions and scale variations. In this paper, we aim to develop a method that can accurately estimate the crowd count from a still image. Recently, convolutional neural networks have been shown effective in many computer vision tasks including crowd counting. To this end, we propose a fully convolutional network (FCN) architecture to...
Recently, convolutional neural networks (CNNs) have achieved great success in fields such as computer vision, natural language processing, and artificial intelligence. Many of these applications utilize parallel processing in GPUs to achieve higher performance. However, it remains a daunting task to optimize for GPUs, and most researchers have to rely on vendor-provided libraries for such purposes...
This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection...
In a convolutional neural network (CNN), convolution calculation can account for about 90% of the total processing work. This paper presents the design of a convolution hardware accelerator (CHA) which can support efficient matrix multiplication to speed up the convolution calculation. In our experiment, when a RISC-V Rocket processor is used to simulate the operation of a CNN for image classification,...
One of the most important ways to explore the information in hyperspectral images (HSIs) is accurate classification of targets. Deep learning algorithm has made a great breakthrough in many areas due to its strong ability of data mining. Typical deep learning models such as convolutional neural network (CNN), deep belief network (DBN) and so on, not only combines the advantages of unsupervised and...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.