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.
In this paper, we solve blind image deconvolution problem that is to remove blurs form a signal degraded image without any knowledge of the blur kernel. Since the problem is ill-posed, an image prior plays a significant role in accurate blind deconvolution. Traditional image prior assumes coefficients in filtered domains are sparse. However, it is assumed here that there exist additional structures...
Image blur and image noise are common distortions during image acquisition. In this paper, we systematically study the effect of image distortions on the deep neural network (DNN) image classifiers. First, we examine the DNN classifier performance under four types of distortions. Second, we propose two approaches to alleviate the effect of image distortion: re-training and fine-tuning with noisy images...
Large-scale convolutional neural network (CNN), conceptually mimicking the operational principle of visual perception in human brain, has been widely applied to tackle many challenging computer vision and artificial intelligence applications. Unfortunately, despite of its simple architecture, a typically-sized CNN is well known to be computationally intensive. This work presents a novel stochastic-based...
Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end smart devices such as smart phones. We propose a CNN compression method based on CP-decomposition and Tensor Power Method. We also propose an iterative fine tuning,...
A booming number of computer vision, speech recognition, and signal processing applications, are increasingly benefiting from the use of deep convolutional neural networks (DCNN) stemming from the seminal work of Y. LeCun et al. [1] and others that led to winning the 2012 ImageNet Large Scale Visual Recognition Challenge with AlexNet [2], a DCNN significantly outperforming classical approaches for...
The binary-weight CNN is one of the most efficient solutions for mobile CNNs. However, a large number of operations are required to process each image. To reduce such a huge operation count, we propose an energy-efficient kernel decomposition architecture, based on the observation that a large number of operations are redundant. In this scheme, all kernels are decomposed into sub-kernels to expose...
Convolution is a fundamental operation in many applications, such as computer vision, natural language processing, image processing, etc. Recent successes of convolutional neural networks in various deep learning applications put even higher demand on fast convolution. The high computation throughput and memory bandwidth of graphics processing units (GPUs) make GPUs a natural choice for accelerating...
With increasing resolutions the volume of data generated by image processing applications is escalating dramatically. When coupled with real-time performance requirements, reducing energy con- sumption for such a large volume of data is proving challenging.
Convolution neural network can gain optional solution by training dataset many times. But persons without experiments are very difficult to seek a good learning rate or a good convergence criterion. We propose a framework, which only are composed by many cheap computers, and by improved convolution network to handle this problem. In the framework, we use terminal server to dispatch initial parameter...
Recently, deep learning became very popular, and was applied to many fields. The convolutional neural networks are often used for representing the layers for deep learning. In this paper, we propose Convolutional Self Organizing Map, which can be applicable to deep learning. Conventional Self Organizing Map uses single layered architecture, and can visualizes and classifies the input data on 2 dimensional...
The Liquid State Machine (LSM) is a biologically plausible model of computation for recurrent spiking neural networks, which offers promising solutions to real-world applications in both software and hardware based systems. At the same time, deep feedforward rate-based neural networks such as convolutional neural networks (CNNs) have achieved great success in many computer vision related applications...
This paper addresses the problem of automatic machine analysis based severity scoring of psoriasis skin disease. Three different disease parameters namely, erythema, scaling and induration are considered for such severity grading. Given an image containing a psoriatic plaque the task is to predict severity scores for all the three parameters. This paper presents a novel deep CNN based architecture...
In this paper, we develop a new transitive aligned Weisfeiler-Lehman subtree kernel. This kernel not only overcomes the shortcoming of ignoring correspondence information between isomorphic substructures that arises in existing R-convolution kernels, but also guarantees the transitivity between the correspondence information that is not available for existing matching kernels. Our kernel outperforms...
The Square Kilometre Array (SKA) project will be the world largest radio telescope array. With the growth of the number of antennas, the signals that need to be processed increase dramatically. One import element of the SKA central signal processor (CSP) package is pulsar search. This paper focuses on the FPGA-based acceleration of the frequency-domain acceleration search (FDAS) module, part of SKA...
Convolutional Neural Networks (CNNs) have gained significant traction in the field of machine learning, particularly due to their high accuracy in visual recognition. Recent works have pushed the performance of GPU implementations of CNNs showing significant improvements in their classification and training times. With these improvements, many frameworks have become available for implementing CNNs...
Bai and Hancock recently proposed a novel edge-based matching kernel for graphs [1], by aligning depth-based representations. Unfortunately, one drawback arising in their kernel is the computational inefficiency for large graphs. This follows the fact that their kernel is essentially defined on directed line graphs. Moreover, the computational complexity of the kernel is cubic in the vertex number...
The geometric remapping of pixel values during the processing of digital imagery, such as magnification, warping and registration, can significantly affect the final image quality. Many medical imaging systems include a resampler/interpolator, such as bicubic, as part of their processing, that acts as a variable low pass filter. This not only degrades the spatial frequency response of the image and...
Pushing supply voltages in the near-threshold region is today one of the main avenues to minimize power consumption in digital integrated circuits. This works well with logic units, but memory operations on standard six-transistor static RAM (6T-SRAM) cells become unreliable at low voltages. Standard cell memory (SCM) works fully reliably at near-threshold voltages, but has much lower area density...
With recent advances in deep convolutional neural networks (CNN), deep learning has brought significant quality improvement and flexibility on single image super resolution (SR). In this paper, we describe how CNN based SR can be accelerated on integrated GPUs. To this end, we employ a CNN model from an existing single image SR approach, and develop the model within a well-known deep learning framework...
The paper proposes a method for human action recognition which focuses on solving the problems resulting from complex hand-crafted features. The method aggregates both spatial and temporal features and can be divided into two parts: multi-channel feature fusion and action classification. For adding motion and shape information, it firstly combines gray, optical flow and Difference of Gaussian(Dog)...
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.