This study applies genetic algorithms to select financial statement variables which are used to predict the direction of one-year-ahead earnings change. To evaluate the forecasting ability of GA-based-linear discrimin...
详细信息
ISBN:
(纸本)9781424409907
This study applies genetic algorithms to select financial statement variables which are used to predict the direction of one-year-ahead earnings change. To evaluate the forecasting ability of GA-based-linear discriminant analysis (GA-LDA), this study compares it with probabilistic neural network and decision tree model. The experiment results show that the GA-LDA model outperforms other classification methods.
Recent years have witnessed a growing interest in developing objective image quality assessment (IQA) algorithms that can measure the image quality consistently with subjective evaluations. For the full reference (FR)...
详细信息
ISBN:
(纸本)9781467325332;9781467325349
Recent years have witnessed a growing interest in developing objective image quality assessment (IQA) algorithms that can measure the image quality consistently with subjective evaluations. For the full reference (FR) IQA problem, great progress has been made in the past decade. On the other hand, several new large scale image datasets have been released for evaluating FR IQA methods in recent years. Meanwhile, no work has been reported to evaluate and compare the performance of state-of-the-art and representative FR IQA methods on all the available datasets. In this paper, we aim to fulfill this task by reporting the performance of eleven selected FR IQA algorithms on all the seven public IQA image datasets. Our evaluation results and the associated discussions will be very helpful for relevant researchers to have a clearer understanding about the status of modern FR IQA indices. Evaluation results presented in this paper are also online available at http://***/linzhang/IQA/***.
In this paper, we describe the developed hovering-type AUV called "Cyclops" and discuss characteristics of imaging sonar DIDSON as an tool for AUV application. The Cyclops was designed to perform an advanced...
详细信息
ISBN:
(纸本)9788993215090
In this paper, we describe the developed hovering-type AUV called "Cyclops" and discuss characteristics of imaging sonar DIDSON as an tool for AUV application. The Cyclops was designed to perform an advanced mission like object recognition, and its symmetric design enable to maximize the mobility of the vehicle. This hardware structure makes the maintenance of the vehicle fast and convenient. We introduce sonar image process algorithms from simple to advanced ones for AUV application. The algorithm includes segmentation for the extraction of reverberation shapes in sonar images, speckle reduction after segmentation, edge detection, and shape matching analysis.
Performance measures of image enhancement are traditionally subjective and have difficulty quantifying the improvement made by the algorithm. In this paper, we present the image enhancement measures and show how utili...
详细信息
ISBN:
(纸本)0819461040
Performance measures of image enhancement are traditionally subjective and have difficulty quantifying the improvement made by the algorithm. In this paper, we present the image enhancement measures and show how utilizing logarithmic arithmetic based addition, subtraction, and multiplication provides better results than previously used measures. In addition, for illustration of the performance of developed measures, we present a comprehensive study of several image enhancement algorithms from all three domains, including spatial, transform, and logarithmic algorithms.
To deal with the problem of restoring degraded images with non-Gaussian noise, this paper proposes a novel cooperative neural fusion regularization (CNFR) algorithm for image restoration. Compared with conventional re...
详细信息
To deal with the problem of restoring degraded images with non-Gaussian noise, this paper proposes a novel cooperative neural fusion regularization (CNFR) algorithm for image restoration. Compared with conventional regularization algorithms for image restoration, the proposed CNFR algorithm can relax need of the optimal regularization parameter to be estimated. Furthermore, to enhance the quality of restored images, this paper presents a cooperative neural fusion (CNF) algorithm for image fusion. Compared with existing signal-level image fusion algorithms, the proposed CNF algorithm can greatly reduce the loss of contrast information under blind Gaussian noise environments. The performance analysis shows that the proposed two neural fusion algorithms can converge globally to the robust and optimal image estimate. Simulation results confirm that in different noise environments, the proposed two neural fusion algorithms can obtain a better image estimate than several well known image restoration and image fusion methods.
Cloud computing opens up new fields of application for imageprocessing. In this article we present an embedded scalable imageprocessing system (vision system) that is universally designed for cloud computing applica...
详细信息
ISBN:
(纸本)9789531841917
Cloud computing opens up new fields of application for imageprocessing. In this article we present an embedded scalable imageprocessing system (vision system) that is universally designed for cloud computing applications. It supports the implementation of imageprocessingalgorithms in software (using C/C++) as well as in hardware (using a hardware description language). An application of our vision system is presented on the example of room monitoring.
In this paper we study the computation error tolerance properties of motion estimation algorithms. We are motivated by two scenarios where hardware systems may introduce computation errors. First, we consider hardware...
详细信息
ISBN:
(纸本)9781424404810
In this paper we study the computation error tolerance properties of motion estimation algorithms. We are motivated by two scenarios where hardware systems may introduce computation errors. First, we consider hardware faults such as those arising in a typical fabrication process. Second, we consider "soft" errors due to voltage scaling, which can arise when operating at a lower voltage than specified for the system. Current practice is to discard all faulty systems. However there is an increasing interest in tools that can identify faulty systems which provide acceptable performance. We show that motion estimation (ME) algorithms exhibit significant error tolerance in these two scenarios. We propose simple error models and use these to provide insights into what features in these ME algorithms lead to increased error tolerance. Our comparison of the full search ME and a state of the art fast ME approach in the context of H.264/AVC shows that while both techniques are error tolerant, the faster algorithm is in fact more robust to computation errors.
Hyperspectral imaging exploits the information contained in the spectrum of light, and has many applications. systems require specialized cameras and application-specific imageprocessing. As an example, we describe a...
详细信息
ISBN:
(纸本)9781557529107
Hyperspectral imaging exploits the information contained in the spectrum of light, and has many applications. systems require specialized cameras and application-specific imageprocessing. As an example, we describe an airborne system with real-time imageprocessing.
The serial video processor (SVP) is a general-purpose mask-programmable SIMD RISC (single instruction multiple-data, reduced instruction set computer) device capable of executing, in real time, the three-dimensional a...
详细信息
The serial video processor (SVP) is a general-purpose mask-programmable SIMD RISC (single instruction multiple-data, reduced instruction set computer) device capable of executing, in real time, the three-dimensional algorithms required for imageprocessing and digital television. Its architecture, application, and development environment are described. Using this approach, the turn-around time to develop, evaluate, and produce a digital-based video application is significantly reduced.< >
We have developed a novel approach to performing automatic detection of concealed threat objects in passive MMW imagery of people scanned in a portal setting. It is applicable to the significant class of imaging scann...
详细信息
ISBN:
(纸本)9780819471390
We have developed a novel approach to performing automatic detection of concealed threat objects in passive MMW imagery of people scanned in a portal setting. It is applicable to the significant class of imaging scanners that use the protocol of having the subject rotate in front of the camera in order to image them from several closely spaced directions. Customary methods of dealing with MMW sequences rely on the analysis of the spatial images in a frame-by-frame manner, with information extracted from separate frames combined by some subsequent technique of data association and tracking over time. We contend that the pooling of information over time in traditional methods is not as direct as can be and potentially less efficient in distinguishing threats from clutter. We have formulated a more direct approach to extracting information about the scene as it evolves over time. We propose an atypical spatio-temporal arrangement of the MMW image data - to which we give the descriptive name Row Evolution image (REI) sequence. This representation exploits the singular aspect of having the subject rotate in front of the camera. We point out which features in REIs are most relevant to detecting threats, and describe the algorithms we have developed to extract them. We demonstrate results of successful automatic detection of threats, including ones whose faint image contrast renders their disambiguation from clutter very challenging. We highlight the ease afforded by the REI approach in permitting specialization of the detection algorithms to different parts of the subject body. Finally, we describe the execution efficiency advantages of our approach, given its natural fit to parallel processing.
暂无评论