By Topic

Image and Signal Processing (CISP), 2013 6th International Congress on

Date 16-18 Dec. 2013

Go

Filter Results

Displaying Results 1 - 25 of 113
  • Robust face recognition method based on SIFT features using Levenberg-Marquardt Backpropagation neural networks

    Publication Year: 2013, Page(s):1000 - 1005
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (529 KB) | HTML iconHTML

    Face recognition from image or video is a popular topic in biometrics research. It has many important practical applications, like surveillance and access control. It is concerned with the problem of correctly identifying facial images and assigning them to persons in a database. This paper proposes an efficient face recognition method based on Scale Invariant Feature Transform (SIFT) for feature ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle detection and tracking with 2D laser range finders

    Publication Year: 2013, Page(s):1006 - 1013
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (471 KB) | HTML iconHTML

    Dynamic environment perception is an important component for unmanned ground vehicle navigation. In this paper, we focus on the vehicle detection and tracking with two low cost 2D laser range finders. Firstly, a foreground segmentation method is proposed based on a combination of the time cue and motion cue. The modified laser beam model is proposed for the tilted 2D laser range finder in the fore... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video flame detection algorithm based on region growing

    Publication Year: 2013, Page(s):1014 - 1018
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1004 KB) | HTML iconHTML

    This paper proposes a region growing based video flame detection algorithm. Firstly, it estimates class-conditional probability density of flame and background with hand-labeled samples, and five discrimination models are proposed using maximum a-posteriori theory. Secondly, it proposes four rules for flame detection with difference of RGB channels, and ROC analysis is used to estimate rule parame... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel efficient method for training sparse auto-encoders

    Publication Year: 2013, Page(s):1019 - 1023
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB) | HTML iconHTML

    The success of machine learning algorithms generally depends on data representation. So far there has been a great deal of literature on unsupervised feature learning and joint training of deep learning. There is little specific guidance, however, on combining hand-designed features or the operations on them with features which are learned from unsupervised learning. In this paper, using MNIST (&#... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A privacy preserving method based on random projection for social networks

    Publication Year: 2013, Page(s):1024 - 1028
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (281 KB) | HTML iconHTML

    Social networks consist of entities connected by links representing relations. The researchers can benefit through social networks analysis, however, it also brings about certain risks for the people involved in them. We put forward a privacy preserving method for weighted social networks based on random projection. The method described social networks as high dimensional edge spaces and adopted r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient initialization method for D-KSVD algorithm for image classification

    Publication Year: 2013, Page(s):1029 - 1034
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (431 KB) | HTML iconHTML

    In the fields of pattern recognition and signal processing, there has been a growing interest in task-driven dictionary learning, which is effective in applications in computer vision such as face recognition and image classification. Discriminative K-SVD (D-KSVD), a newly proposed dictionary learning method, has better discrimination ability since it incorporates the classification error into its... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cancer detection in mammograms estimating feature weights via Kullback-Leibler measure

    Publication Year: 2013, Page(s):1035 - 1040
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (449 KB) | HTML iconHTML

    In this study the aim is to determine cancerous possibility of suspicious lesions in mammograms. With this aim, probabilistic values of suspicious lesions in the image are found via exponential curve fitting and texture features in order to find weight values in the objective function. Afterwards, images are classified as normal, malign, and benign by utilizing Kullback Leibler method. Here, 3�... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient and robust optic disc detection with vessel characteristics

    Publication Year: 2013, Page(s):1041 - 1045
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (938 KB) | HTML iconHTML

    A novel efficient and robust optic disc (OD) center detection method is proposed by using vessel distribution and directional characteristics. A feature describing local vessel density, compactness and uniformity of vessel distribution characteristics is presented to locate column ordinate of OD center. Then according to the global vessel direction characteristic, a General Hough Transformation (G... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image fusion based on non-negative matrix factorization and infrared feature extraction

    Publication Year: 2013, Page(s):1046 - 1050
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (893 KB) | HTML iconHTML

    A new effective fusion method based on non-negative matrix factorization (NMF) and infrared target extraction is presented for infrared and visible images fusion. The two source images are taken as original data in NMF analysis, from which the feature base containing the global features of the source images can be extracted. The feature base image is replaced by the adjusted visible image, which i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved median linear discriminant analysis for face recognition

    Publication Year: 2013, Page(s):1051 - 1055
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (275 KB) | HTML iconHTML

    Traditional linear discriminant analysis (LDA) exaggerates the contribution of distant samples in center calculation for identification, resulting in suboptimal shortcoming. This paper proposes an improved method based on LDA, which is named as KDA method in this paper because it gives different weights to different training samples according to K nearest neighbor idea in within-class scatter matr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-layer pointillism

    Publication Year: 2013, Page(s):1056 - 1060
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (852 KB) | HTML iconHTML

    This paper presents an image-based artistic rendering algorithm for the automatic pointillism style. At first, stroke locations are randomly generated based on a target image; then stroke size and rendering order are pre-calculated by a standard deviation map of the image; at last, the rendering runs layer-by-layer from large stroke size to small stroke size so as to reserve the detailed parts of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pattern recognition based on weighted fuzzy C-means clustering

    Publication Year: 2013, Page(s):1061 - 1065
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (174 KB) | HTML iconHTML

    In data mining, fuzzy C-means clustering algorithm has demonstrated advantage in dealing with the challenges posed by large collections of vague and uncertain data. This paper reviews concept of fuzzy C-means clustering which is widely used in context of pattern recognition. Based on the study of the fuzzy C-means algorithm, we propose a weighted local fuzzy regression model. The efficiency of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Saliency detection via boundary and center priors

    Publication Year: 2013, Page(s):1066 - 1071
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (12957 KB) | HTML iconHTML

    This paper proposes a novel method for saliency detection in HSL color space. We firstly divide the traditional global contrast based saliency into background saliency and foreground saliency. Background saliency is then simplified into boundary saliency according to background priors. Furthermore, upper and lower boundary saliency maps are obtained. To overcome the defects of foreground saliency,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Target detection and tracking based on spatially multiplexed and superposition imaging

    Publication Year: 2013, Page(s):1072 - 1077
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (820 KB) | HTML iconHTML

    Addressing continuous target detection and tracking over a large field of view in surveillance application, a novel method to detect and track target is presented in a wide field of view based on spatially multiplexed and superposition imaging technique. This system architecture is proposed by using the spherical lens array and confocal plane with the character of wide field and compressive sampli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new attribute reduction algorithm in inconsistent decision information systems

    Publication Year: 2013, Page(s):1078 - 1084
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (227 KB) | HTML iconHTML

    This paper mainly deals with attribute reductions of inconsistent decision information system. In inconsistent decision system, improper selection of rules may lead to lose useful information. A new attribute reduction algorithm is proposed in this paper. By using this method, inconsistent rules are eliminated without affecting the useful information. It is a useful method to deal with small sampl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Demand elasticity analysis by least squares support vector machine

    Publication Year: 2013, Page(s):1085 - 1089
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (246 KB) | HTML iconHTML

    Demand-side management (DSM) has been introduced and paid much effort in the electricity industry for such a long time, and become more and more focused in the most of the electricity markets recent years, because of its effect on the modification of consumer demand for energy through various methods especially financial incentives. But due to the complexity of the influence factors, the demand el... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting parameters of high frequency signals with frequency modulation stochastic resonance

    Publication Year: 2013, Page(s):1090 - 1095
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (355 KB) | HTML iconHTML

    In order to settle the limitation of stochastic resonance to detect big parameters signal, frequency modulation stochastic resonance is proposed to detect the parameters of high frequency signal. The principle of frequency modulation stochastic resonance is to modulate the signal's frequency firstly and then detect the signal's frequency by the use of stochastic resonance. The paper analyzes the t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Magnetic Flux Leakage signal processing in strip steel flaw area detection

    Publication Year: 2013, Page(s):1096 - 1100
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (319 KB) | HTML iconHTML

    The strip steel is widely used in industries, but there always exists some flaws during its manufacturing. The flaws are difficult to be detected and the analysis of the data obtained from Magnetic Flux Leakage (MFL) inspection of the strip steel is quite a challenge. In order to solve this problem, the MFL data is first processed with difference method, and then removed the baseline drift by wave... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified algorithm based on the Bloom Filter

    Publication Year: 2013, Page(s):1101 - 1105
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB) | HTML iconHTML

    This paper presents a modified algorithm based on the Bloom Filter. Considering a set A of n elements, if ai is an element of A, then ai could be mapped to a part of the filter by some hash functions. Some eigenvalues are extracted from ai, and then all eigenvalues are combined into a whole: ai*. The ai* is mapped to another part of the filter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Component-based modeling for complex digital logic systems

    Publication Year: 2013, Page(s):1106 - 1111
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (137 KB) | HTML iconHTML

    With the rapidly increasing of digital logic systems' complexity, its design flows become more and more tedious. In order to increase its efficiency and reduce the cost of engineering, design cycles should tend to be more convenient. This paper presents a modeling methodology for complex digital logic components. It contains formal definition and calculation system of components. Component-based m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and implementation of a 1024-point high-speed FFT processor based on the FPGA

    Publication Year: 2013, Page(s):1112 - 1116
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (241 KB) | HTML iconHTML

    To design a Fast Fourier Transform (FFT) processor to meet the needs for high-speed and real-time signal processing. A 1024-point, 32-bit, fixed, complex FFT processor is designed based on a field programmable gate array (FPGA) by using the radix-2 decimation in frequency (DIF) algorithm and the pipeline structure in the butterfly module and the ping-pone operation in data storage unit. When the p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human motion capture data segmentation based on graph partition

    Publication Year: 2013, Page(s):1117 - 1121
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB) | HTML iconHTML

    For better reuse of motion capture data, long motion sequences need to be segmented into multiple motion clips of simple motion types. In this paper, we propose a method for motion capture data segmentation based on graph partition. Each frame of motion sequence is viewed as a node in an undirected weighted graph, and the weight of an edge is the similarity between two frames corresponding to the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measurement of discrete phase concentration and velocity in gas/solid two-phase flow

    Publication Year: 2013, Page(s):1122 - 1126
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (367 KB) | HTML iconHTML

    Research of the velocity, dimension, position and manifold of the gas/solid two-phase flow is of great significance, as the flow is a widely existed and complicated pattern of multiphase flows in industrial processes. In this paper, the discrete phase concentration and velocity measurement of gas/solid two-phase fluid which cocurrent flows from bottom to top in vertical pipe is simulated and studi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Obstacle detection based on a 2D large range sonar model

    Publication Year: 2013, Page(s):1127 - 1131
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1108 KB) | HTML iconHTML

    The current state-of-the-art in Autonomous Ground Vehicle (AGV) technology requires expensive, delicate laser range finders to apperceive the environmental impact of driving. The situation of too costly ladar represents a large barrier to adoption of AGV in the future, whereas provides an opportunity for close-to-market large range sonar sensor. In this paper, we propose an obstacle detection algo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An empirical envelope estimation algorithm

    Publication Year: 2013, Page(s):1132 - 1136
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (302 KB) | HTML iconHTML

    Envelope is the vital part of one-dimensional data. The estimation of envelope can be treated as a demodulation problem. However, the definition of envelope is ambiguous and lack of an exact mathematical definition. It is commonly agreed that envelope varies slowly and in some empirical view it should pass the prominent peaks of the data smoothly. In this study, we propose an algorithm to directly... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.