Wavelet. Coefficients. Fmicros() (micros) Wavelet. Wavelet Coefficients. Fmasses() (masses) Wavelet Coefficients (stellate) Fstellate()

Size: px
Start display at page:

Download "Wavelet. Coefficients. Fmicros() (micros) Wavelet. Wavelet Coefficients. Fmasses() (masses) Wavelet Coefficients (stellate) Fstellate()"

Transcription

1 Enhanceent via Fusion of Maographic Features Iztok oren y, Andrew Laine z, and Fred Taylor y y Dept. of Electrical and Coputer Engineering z Center for Bioedical Engineering University of Florida, Gainesville, FL Colubia University, New York, NY Abstract Maographic iage enhanceent ethods are typically aied at either iproveent of the overall visibility of features or enhanceent of a specific sign of alignancy. In this paper, we present a synthesis of the two paradigs by eans of iage fusion. After a redundant B-spline wavelet transfor decoposition is carried out, the transfor coefficients are processed for enhanceent of icrocalcifications, circuscribed asses, and stellate lesions. The odified coefficients are then fused for reconstruction of an enhanced iage with iproved visualization of alignancies. Both processing for enhanceent of selected features and fusion of the resultant iages are accoplished within a single wavelet transfor fraework which contributes to the coputational efficiency of the described ethod. The devised algorith not only allows for efficient cobination of specific features of iportance in the contrast enhanced iages, but also provides a flexible fraework for incorporation of different enhanceent ethods and their independent optiization. 1 Introduction Maography is the best ethod for early detection of breast cancer at a tie when approxiately 80 percent of woen diagnosed with breast cancer have no identifiable risk factors for this disease. The early detection of breast cancer is essential since therapeutic actions are ore likely to be successful in the early stages. Finding sall alignancies and subtle lesions is often difficult with false-negative rate being due both to difficulty with discerning subtle features on the coplex noral anatoy background and oversight of abnoralities. Contrast enhanceent can ake ore obvious unseen or barely seen features of a aogra without requiring additional radiation. Better visibility of suspicious structures can increase effectiveness and efficiency, and thus iprove the diagnostic perforance of aography. Existing ethods of aographic iage enhanceent can be divided roughly into two categories: (1) ethods aied at better visualization of all features present in an iage [1, 2, 10, 12], and (2) ethods that target specific features of iportance (e.g., icrocalcifications [13, 14, 16], stellate lesions [8]). Methods fro the first category are not optiized for a specific type of cancer and soeties not even for aography. Rather, they try to iprove the perceptual quality of the entire iage and are often developed with a fraework ore general than aography alone in ind. The second category ethods concentrate on revelation of particular signs of alignancy. They can be very successful in their area of specialization; however, in order to process aogra for presence of various features, one would need to apply different algoriths independently resulting in both larger nuber of iages to be interpreted by a radiologist and increased coputational coplexity of such a procedure. In this paper, we present an approach which overcoes these shortcoings and probleatic liitations via synthesis of the two paradigs by eans of iage fusion. 2 Methodology The goal of our ethod is to adapt specific enhanceent schees for distinct aographic features, and then cobine the set of processed iages into an enhanced iage. The aographic iage is first processed for enhanceent of icrocalcifications, asses, and stellate lesions. Fro the resulting enhanced iages, the final enhanced iage is synthesized by eans of iage fusion [7]. based iage enhanceent and fusion are erged into a unified fraework, so that there is no need for carrying out the two operations independently (i.e., coputing wavelet decopositions, odifying wavelet coefficients for enhanceent of specific features, reconstructing the enhanced iages, perforing wavelet transfors of the enhanced iages, fusing transfor coefficients, and obtaining the final result by reconstruction fro fused wavelet coefficients). Both enhanceent and fusion are therefore iplicit (i.e., perfored in the wavelet doain only).

2 Ficros() (icros) Input Maogra Decoposition Fasses() (asses) Fusion of Enhanced Maogra Fstellate() (stellate) Figure 1: Overview of the algorith. Figure 1 presents a block schee of the overall algorith. The algorith consists of two ajor steps: (1) wavelet coefficients are odified distinctly for each type of alignancy; (2) the obtained ultiple sets of wavelet coefficients are fused into a single set fro which the reconstruction is coputed. The devised schee allows efficient deployent of an enhanceent strategy appropriate for clinical screening protocols: enhanceent algorith is first developed for each specific type of feature independently, and the results are then cobined using an appropriate fusion strategy. The structure of the algorith also enables independent developent and optiization of enhanceent strategies for individual aographic features as well as the fusion odule. 2.1 B-Spline Transfor Since diagnostic features in aogras appear in a variety of shapes and sizes, traditional iage enhanceent techniques such as histogra equalization and unsharp asking seldo produce satisfactory results and are clearly outperfored by ore sophisticated ethods [10, 12]. Recognizing the benefit of aographic iage processing across different scales have resulted in a variety ofwavelet-based techniques; however, the choice of an appropriate wavelet transfor is of crucial iportance. In enhanceent ofa- ogras, for exaple, it is essential to iprove the visibility of features without distorting their appearance and shape. Algorith introduced artifacts are dangerous since they can lead to isdiagnosis, and lack of translation invariance of the transfor has been identified as a possible source of artifacts. In the light of this ajor shortcoing of orthogonal and biorthogonal wavelet transfors, translation-invariantovercoplete wavelet representations of signals have becoepopular [2, 10, 13,14]. In two diensions, the lack of rotation invariance affects the processing results as well, and several steerable [3] wavelet transfors have been devised to address this proble [1, 8, 9]. Translation and rotation invariance are equally iportant for iage fusion applications, and our experients have shown eliination of orthogonal and biorthogonal wavelet transfor caused artifacts when the steerable dyadic wavelet transfor based fusion ethod [7] has been used. Here, we eploy a generalization of the discrete dyadic wavelet transfor [11] with wavelets being equal to the second derivative of a central B-spline. This ultiscale spline derivative-based transfor [5] has several nice properties: (1) it is translationinvariant and approxiately steerable, (2) it is well suited for incorporating flexibility fro a variety of ethods [1, 2, 4, 8,10,13,14], and (3) it can be ipleented as a filter bank consisting of one-diensional filters only. The wavelets can be expressed as where ψ(x; y) %(x; 2 ; %(x; y) =fi p+2 (x)fi p+2 (y) and fi p (x) denotes a central B-spline of order p 2 N. Since central B-splines can closely approxiate a Gaussian probability density function (in fact, they converge to a Gaussian as their order tends to infinity), %(x; y) can be ade approxiately circularly syetric and, consequently, ψ(x; y) approxiately steerable. A rotation of ψ(x; y) by 0 can therefore be approxiated by ψ 0 (x; y) ' (cos 0 @x + 2 cos 2 0 sin 2 + +(sin 0 2 %(x; y); so that the set of basis functions that approxiately steer the wavelets ψ(x; y) is g. 2 Figure 2 shows the building blocks of a filter bank ipleentation of the transfor which uses the set of

3 G (2 ω ) 2 x G (2 ω ) G (2 ω ) 1 x 1 y G 2(2 ω y) H(2 ω x) (a) H(2 ω y) 2(2 ω x ) L (2 ω y) 1(2 ω x) 1(2 ω y) L (2 ω x) 2(2 ω y) H(2 ω x) H(2 ω y) (b) Figure 2: Filter bank ipleentation of a ultiscale spline derivative-based transfor with a second derivative wavelet. Basic processing odules for (a) decoposition and (b) reconstruction at a scale 2. basis functions needed to approxiately steer ψ(x; y). The filters were specified as G 2 d d (!) j!( =e 2 )! 2j sin 2 d;! H(!) = cos 2 2p; L(!) =jh(!)j 2 ; and 2 d j!( 2 d d (!) = 1 (2j) d e 2 ) sin! 2 P2p 1 =0 cos! 2; 2 where d 2f1; 2g. All the filters are either syetric or antisyetric, a property which enables an additional speedup when a syetric (e.g., irror extended) input signal is used [6]. B-spline approxiations are also well suited for carrying out the proper initialization of the wavelet transfor by eans of siple prefiltering. Such a spline based initialization can significantly iprove the accuracy of processing at finer scales. 2.2 Enhanceent and Fusion After the wavelet decoposition, the obtained coefficients are odified for iproved visualization of features of diagnostic iportance. Local enhanceent of icrocalcifications, circuscribed asses, and stellate lesions has been developed for each type of alignancy separately. An advantage of the ethod represented by Figure 1 is the fact that the entire processing algorith can be split into subprobles which can be tackled independently. For enhanceent of icrocalcifications, second derivatives along directions of x and y-axis are added to for an approxiation to a Laplacian of Gaussian. The obtained coefficients are thresholded, and the original coefficients at the corresponding locations ultiplied by a gain factor. Siilar enhanceent through detection was used by Strickland and Hahn [13, 14]. To reduce the nuber of false-positive elongated saples, the strength of local orientation was coputed by eploying second derivative wavelets in conjunction with their Hilbert transfor pairs for ultiscale orientation analysis. Note that, although not ipleented for the purpose of this paper, it is possible to obtain voices of the transfor as well (e.g., octaves 2.5" and 3.5" [13, 14]); central B-spline properties enable coputation of the transfor at any integer scale [15]. Enhanceent of circuscribed asses is carried out by applying a piecewise linear enhanceent function [2] to wavelet coefficients at scales 2 3 through 2 5. The selection of the scale range was based upon the pixel resolution (116μ) of digitized aogras in the University of Florida database. Stellate lesions are contrast enhanced according to the observation that they introduce a distortion into a radial orientation pattern fro the nipple to the chest wall [4]. The 1-nor of differences between local orientation and average orientation within a sliding window is used as an input to a soft thresholding function at each dyadic scale independently [8]. The choice of enhanceent paraeters controls the aggressiveness/subtleness of each resultant enhanceent (i.e., proinence of the targeted feature with respect to the surrounding tissue). Note also that it is possible to put different weights on features, and exclude certain features fro the final result. 3 Experiental Results Our ethod was applied to digitized aogras fro the University of Florida database, and showed proising results in ters of iproved visibility and detection of subtle features. Figure 3 deonstrates the results of processing using the ultiscale analysis contrast enhanceent algorith [10], and using the proposed fusion of enhanced features ethod. In this exaple, the fusion of enhanced features ephasizes the appearance of a ass which is surrounded by dense parenchya of the breast. Our preliinary results suggest that this type of iage is ore easily interpreted by radiologists copared to iages produced via global enhanceent techniques; however, the ultiscale analysis contrast enhanceent algorith [10] is being refined as well. A powerful aspect of the enhanceent via fusion schee lies in its flexibility: the ultiscale analysis based global contrast enhanceent algorith [10] can be readily incorporated into the schee as one of the branches before the fusion odule.

4 4 Conclusion The described ethod incorporates a variety of properties of aographic iage enhanceent ethods tailored to specific signs of alignancy into a unified coputational fraework. Multiscale spline derivative-based transfor has proved flexible enough for iplicit enhanceent of individual types of aographic features and thus enabled processing within a single wavelet transfor decoposition. In addition to its efficiency, the algorith is also well suited for further refineents; optiizations can be perfored for each type of alignancy alone, and separately for the fusion strategy. Our preliinary experients iply that the enhanceent via fusion approach can provide ore obvious clues for radiologists. Further clinical tests are planned to verify that the versatility of this paradig can provide a better viewing environent for an easier and a ore reliable interpretation of aogras. Acknowledgent This work was supported by the U.S. Ary Medical Research and Materiel Coand under DAMD References [1] C.-M. Chang and A. Laine, Enhanceent of aogras fro oriented inforation," in Proc. IEEE Int. Conf. Iage Process., Santa Barbara, CA, Oct. 1997, vol. 3, pp [2] J. Fan and A. Laine, Multiscale contrast enhanceent and denoising in digital radiographs," in s in Medicine and Biology, A. Aldroubi and M. Unser, Eds., CRC Press, Boca Raton, FL, 1996, pp [3] W. T. Freean and E. H. Adelson, The design and use of steerable filters," IEEE Trans. Pattern Anal. Machine Intell., vol. 13, pp , [4] W. P. egeleyer, J. M. Pruneda, P. D. Bourland, A. Hillis, M. V. Riggs, and M. L. Nipper, Coputer-aided aographic screening for spiculated lesions," Radiology, vol. 191, pp , [5] I. oren, A Multiscale Spline Derivative-Based Transfor for Iage Fusion and Enhanceent, Ph.D. thesis, Departent of Electrical and Coputer Engineering, University of Florida, Gainesville, FL, [6] I. oren and A. Laine, A discrete dyadic wavelet transfor for ultidiensional feature analysis," in M. Akay (Editor), Tie-Frequency and s in Bioedical Signal Engineering, New York, NY: IEEE Press, 1998, pp [7] I. oren, A. Laine, and F. Taylor, Iage fusion using steerable dyadic wavelet transfor," in Proc. IEEE Int. Conf. Iage Process., Washington, D.C., Oct. 1995, vol. 3, pp [8] I. oren, A. Laine, F. Taylor, and M. Lewis, Interactive wavelet processing and techniques applied to digital aography," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process.,Atlanta, GA, May 1996, vol. 3, pp [9] A. Laine, I. oren, W. Yang, and F. Taylor, A steerable dyadic wavelet transfor and interval wavelets for enhanceent of digital aography," in Applications II, H. H. Szu, Ed., Proc. SPIE, Orlando, FL, Apr. 1995, vol. 2491, pp [10] A. F. Laine, S. Schuler, J. Fan, and W. Huda, Maographic feature enhanceent by ultiscale analysis," IEEE Trans. Med. Iaging, vol. 13, pp , [11] S. Mallat and S. Zhong, Characterization of signals fro ultiscale edges," IEEE Trans. Pattern Anal. Machine Intell., vol. 14, pp , [12] W. M. Morrow, R. B. Paranjape, R. M. Rangayyan, and J. E. L. Desautels, Region-based contrast enhanceent of aogras," IEEE Trans. Med. Iaging, vol. 11, pp , [13] R. N. Strickland and H. I. Hahn, transfor atched filters for the detection and classification of icrocalcifications in aography," in Proc. IEEE Int. Conf. Iage Process., Washington, D.C., Oct. 1995, vol. 1, pp [14] R. N. Strickland and H. I. Hahn, transfors for detecting icrocalcifications in aogras," IEEE Trans. Med. Iaging, vol. 15, pp , [15] M. Unser, A. Aldroubi, and S. J. Schiff, Fast ipleentation of the continuous wavelet transfor with integer scales," IEEE Trans. Signal Process., vol. 42, pp , [16] H. Yoshida, W. Zhang, W. Cai,. Doi, R. M. Nishikawa, and M. L. Giger, Optiizing wavelet transfor based on supervised learning for detection of icrocalcifications in digital aogras," in Proc. IEEE Int. Conf. Iage Process., Washington, D.C., Oct. 1995, vol. 3, pp

5 (a) (b) (c) Figure 3: (a) Original aogra. (b) Contrast enhanceent by ultiscale analysis [10]. obtained by fusion of enhanced features. (c) Enhanceent

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 13

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 13 Coputer Aided Drafting, Design and Manufacturing Volue 26, uber 2, June 2016, Page 13 CADDM 3D reconstruction of coplex curved objects fro line drawings Sun Yanling, Dong Lijun Institute of Mechanical

More information

COLOR HISTOGRAM AND DISCRETE COSINE TRANSFORM FOR COLOR IMAGE RETRIEVAL

COLOR HISTOGRAM AND DISCRETE COSINE TRANSFORM FOR COLOR IMAGE RETRIEVAL COLOR HISTOGRAM AND DISCRETE COSINE TRANSFORM FOR COLOR IMAGE RETRIEVAL 1 Te-Wei Chiang ( 蔣德威 ), 2 Tienwei Tsai ( 蔡殿偉 ), 3 Jeng-Ping Lin ( 林正平 ) 1 Dept. of Accounting Inforation Systes, Chilee Institute

More information

HIGH PERFORMANCE PRE-SEGMENTATION ALGORITHM FOR SONAR IMAGES

HIGH PERFORMANCE PRE-SEGMENTATION ALGORITHM FOR SONAR IMAGES HIGH PERFORMANCE PRE-SEGMENTATION ALGORITHM FOR SONAR IMAGES Benjain Lehann*, Konstantinos Siantidis*, Dieter Kraus** *ATLAS ELEKTRONIK GbH Sebaldsbrücker Heerstraße 235 D-28309 Breen, GERMANY Eail: benjain.lehann@atlas-elektronik.co

More information

The optimization design of microphone array layout for wideband noise sources

The optimization design of microphone array layout for wideband noise sources PROCEEDINGS of the 22 nd International Congress on Acoustics Acoustic Array Systes: Paper ICA2016-903 The optiization design of icrophone array layout for wideband noise sources Pengxiao Teng (a), Jun

More information

TensorFlow and Keras-based Convolutional Neural Network in CAT Image Recognition Ang LI 1,*, Yi-xiang LI 2 and Xue-hui LI 3

TensorFlow and Keras-based Convolutional Neural Network in CAT Image Recognition Ang LI 1,*, Yi-xiang LI 2 and Xue-hui LI 3 2017 2nd International Conference on Coputational Modeling, Siulation and Applied Matheatics (CMSAM 2017) ISBN: 978-1-60595-499-8 TensorFlow and Keras-based Convolutional Neural Network in CAT Iage Recognition

More information

Image Filter Using with Gaussian Curvature and Total Variation Model

Image Filter Using with Gaussian Curvature and Total Variation Model IJECT Vo l. 7, Is s u e 3, Ju l y - Se p t 016 ISSN : 30-7109 (Online) ISSN : 30-9543 (Print) Iage Using with Gaussian Curvature and Total Variation Model 1 Deepak Kuar Gour, Sanjay Kuar Shara 1, Dept.

More information

EE 364B Convex Optimization An ADMM Solution to the Sparse Coding Problem. Sonia Bhaskar, Will Zou Final Project Spring 2011

EE 364B Convex Optimization An ADMM Solution to the Sparse Coding Problem. Sonia Bhaskar, Will Zou Final Project Spring 2011 EE 364B Convex Optiization An ADMM Solution to the Sparse Coding Proble Sonia Bhaskar, Will Zou Final Project Spring 20 I. INTRODUCTION For our project, we apply the ethod of the alternating direction

More information

A Novel 2D Texture Classifier For Gray Level Images

A Novel 2D Texture Classifier For Gray Level Images 2012, TextRoad Publication ISSN 2090-4304 Journal of Basic and Applied Scientific Research www.textroad.co A Novel 2D Texture Classifier For Gray Level Iages B.S. Mousavi 1 Young Researchers Club, Zahedan

More information

POSITION-PATCH BASED FACE HALLUCINATION VIA LOCALITY-CONSTRAINED REPRESENTATION. Junjun Jiang, Ruimin Hu, Zhen Han, Tao Lu, and Kebin Huang

POSITION-PATCH BASED FACE HALLUCINATION VIA LOCALITY-CONSTRAINED REPRESENTATION. Junjun Jiang, Ruimin Hu, Zhen Han, Tao Lu, and Kebin Huang IEEE International Conference on ultiedia and Expo POSITION-PATCH BASED FACE HALLUCINATION VIA LOCALITY-CONSTRAINED REPRESENTATION Junjun Jiang, Ruiin Hu, Zhen Han, Tao Lu, and Kebin Huang National Engineering

More information

Feature Based Registration for Panoramic Image Generation

Feature Based Registration for Panoramic Image Generation IJCSI International Journal of Coputer Science Issues, Vol. 10, Issue 6, No, Noveber 013 www.ijcsi.org 13 Feature Based Registration for Panoraic Iage Generation Kawther Abbas Sallal 1, Abdul-Mone Saleh

More information

AN APPROACH ON BIMODAL BIOMETRIC SYSTEMS

AN APPROACH ON BIMODAL BIOMETRIC SYSTEMS AN APPROACH ON BIODAL BIOETRIC SYSTES Eugen LUPU, Siina EERICH Technical University of Cluj-Napoca, 26-28 Baritiu str. Cluj-Napoca phone: +40-264-40-266; fax: +40-264-592-055; e-ail: Eugen.Lupu @co.utcluj.ro

More information

Boosted Detection of Objects and Attributes

Boosted Detection of Objects and Attributes L M M Boosted Detection of Objects and Attributes Abstract We present a new fraework for detection of object and attributes in iages based on boosted cobination of priitive classifiers. The fraework directly

More information

Novel Image Representation and Description Technique using Density Histogram of Feature Points

Novel Image Representation and Description Technique using Density Histogram of Feature Points Novel Iage Representation and Description Technique using Density Histogra of Feature Points Keneilwe ZUVA Departent of Coputer Science, University of Botswana, P/Bag 00704 UB, Gaborone, Botswana and Tranos

More information

Image Processing for fmri John Ashburner. Wellcome Trust Centre for Neuroimaging, 12 Queen Square, London, UK.

Image Processing for fmri John Ashburner. Wellcome Trust Centre for Neuroimaging, 12 Queen Square, London, UK. Iage Processing for fmri John Ashburner Wellcoe Trust Centre for Neuroiaging, 12 Queen Square, London, UK. Contents * Preliinaries * Rigid-Body and Affine Transforations * Optiisation and Objective Functions

More information

Wavelets for Computer Graphics: A Primer Part 1

Wavelets for Computer Graphics: A Primer Part 1 Wavelets for Coputer Graphics: A Prier Part Eric J. Stollnitz Tony D. DeRose David H. Salesin University of Washington Introduction Wavelets are a atheatical tool for hierarchically decoposing functions.

More information

INTERLEAVED DIMENSION DECOMPOSITION: A NEW DECOMPOSITION METHOD FOR WAVELETS AND ITS APPLICATION TO COMPUTER GRAPHICS

INTERLEAVED DIMENSION DECOMPOSITION: A NEW DECOMPOSITION METHOD FOR WAVELETS AND ITS APPLICATION TO COMPUTER GRAPHICS INTERLEAVED DIMENSION DECOMPOSITION: A NEW DECOMPOSITION METHOD FOR WAVELETS AND ITS APPLICATION TO COMPUTER GRAPHICS Manfred Kopp and Werner Purgathofer Vienna University of Technology Institute of Coputer

More information

Action Recognition Using Local SpatioTemporal Oriented Energy Features and Additive. Kernel SVMs

Action Recognition Using Local SpatioTemporal Oriented Energy Features and Additive. Kernel SVMs International Journal of Electronics and Electrical Engineering Vol., No., June, 4 Action Recognition Using Local SpatioTeporal Oriented Energy Features and Additive Kernel SVMs Jiangfeng Yang and Zheng

More information

Region Segmentation Region Segmentation

Region Segmentation Region Segmentation /7/ egion Segentation Lecture-7 Chapter 3, Fundaentals of Coputer Vision Alper Yilaz,, Mubarak Shah, Fall UCF egion Segentation Alper Yilaz,, Mubarak Shah, Fall UCF /7/ Laer epresentation Applications

More information

Clustering. Cluster Analysis of Microarray Data. Microarray Data for Clustering. Data for Clustering

Clustering. Cluster Analysis of Microarray Data. Microarray Data for Clustering. Data for Clustering Clustering Cluster Analysis of Microarray Data 4/3/009 Copyright 009 Dan Nettleton Group obects that are siilar to one another together in a cluster. Separate obects that are dissiilar fro each other into

More information

Data pre-processing framework in SPM. Bogdan Draganski

Data pre-processing framework in SPM. Bogdan Draganski Data pre-processing fraework in SPM Bogdan Draganski Outline Why do we need pre-processing? Overview Structural MRI pre-processing fmri pre-processing Why do we need pre-processing? What do we want? Reason

More information

Verdict Accuracy of Quick Reduct Algorithm using Clustering, Classification Techniques for Gene Expression Data

Verdict Accuracy of Quick Reduct Algorithm using Clustering, Classification Techniques for Gene Expression Data Verdict Accuracy of Quick Reduct Algorith using Clustering, Classification Techniques for Gene Expression Data T.Chandrasekhar 1, K.Thangavel 2 and E.N.Sathishkuar 3 1 Departent of Coputer Science, eriyar

More information

A Broadband Spectrum Sensing Algorithm in TDCS Based on ICoSaMP Reconstruction

A Broadband Spectrum Sensing Algorithm in TDCS Based on ICoSaMP Reconstruction MATEC Web of Conferences 73, 03073(08) https://doi.org/0.05/atecconf/087303073 SMIMA 08 A roadband Spectru Sensing Algorith in TDCS ased on I Reconstruction Liu Yang, Ren Qinghua, Xu ingzheng and Li Xiazhao

More information

Quantitative Comparison of Sinc-Approximating Kernels for Medical Image Interpolation

Quantitative Comparison of Sinc-Approximating Kernels for Medical Image Interpolation Quantitative Coparison of Sinc-Approxiating Kernels for Medical Iage Interpolation Erik H. W. Meijering, Wiro J. Niessen, Josien P. W. Plui, Max A. Viergever Iage Sciences Institute, Utrecht University

More information

Solving the Damage Localization Problem in Structural Health Monitoring Using Techniques in Pattern Classification

Solving the Damage Localization Problem in Structural Health Monitoring Using Techniques in Pattern Classification Solving the Daage Localization Proble in Structural Health Monitoring Using Techniques in Pattern Classification CS 9 Final Project Due Dec. 4, 007 Hae Young Noh, Allen Cheung, Daxia Ge Introduction Structural

More information

Affine Invariant Texture Analysis Based on Structural Properties 1

Affine Invariant Texture Analysis Based on Structural Properties 1 ACCV: The 5th Asian Conference on Coputer Vision, --5 January, Melbourne, Australia Affine Invariant Texture Analysis Based on tructural Properties Jianguo Zhang, Tieniu Tan National Laboratory of Pattern

More information

Classification and Segmentation of Glaucomatous Image Using Probabilistic Neural Network (PNN), K-Means and Fuzzy C- Means(FCM)

Classification and Segmentation of Glaucomatous Image Using Probabilistic Neural Network (PNN), K-Means and Fuzzy C- Means(FCM) IJSRD - International Journal for Scientific Research & Developent Vol., Issue 7, 03 ISSN (online): 3-063 Classification and Segentation of Glaucoatous Iage Using Probabilistic Neural Network (PNN), K-Means

More information

THE rounding operation is performed in almost all arithmetic

THE rounding operation is performed in almost all arithmetic This is the author's version of an article that has been published in this journal. Changes were ade to this version by the publisher prior to publication. The final version of record is available at http://dx.doi.org/.9/tvlsi.5.538

More information

MGS-SIFT: A New Illumination Invariant Feature Based on SIFT Descriptor

MGS-SIFT: A New Illumination Invariant Feature Based on SIFT Descriptor International Journal of Coputer Theory and Engineering, Vol 5, No, February 0 MGS-SIFT: A New Illuination Invariant Feature Based on SIFT Descriptor Reza Javanard Alitappeh and Fariborz Mahoudi Abstract

More information

Galois Homomorphic Fractal Approach for the Recognition of Emotion

Galois Homomorphic Fractal Approach for the Recognition of Emotion Galois Hooorphic Fractal Approach for the Recognition of Eotion T. G. Grace Elizabeth Rani 1, G. Jayalalitha 1 Research Scholar, Bharathiar University, India, Associate Professor, Departent of Matheatics,

More information

OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS

OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS Key words SOA, optial, coplex service, coposition, Quality of Service Piotr RYGIELSKI*, Paweł ŚWIĄTEK* OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS One of the ost iportant tasks in service oriented

More information

NON-RIGID OBJECT TRACKING: A PREDICTIVE VECTORIAL MODEL APPROACH

NON-RIGID OBJECT TRACKING: A PREDICTIVE VECTORIAL MODEL APPROACH NON-RIGID OBJECT TRACKING: A PREDICTIVE VECTORIAL MODEL APPROACH V. Atienza; J.M. Valiente and G. Andreu Departaento de Ingeniería de Sisteas, Coputadores y Autoática Universidad Politécnica de Valencia.

More information

! What is mrmr feature selection. ! Applications in cancer classification. ! Applications in image pattern recognition. ! Theoretical basis of mrmr

! What is mrmr feature selection. ! Applications in cancer classification. ! Applications in image pattern recognition. ! Theoretical basis of mrmr Miniu Redundancy and Maxiu Relevance Feature election and Its Applications Hanchuan Peng Janelia Far Research Capus, Howard Hughes Medical Institute What is RMR feature selection Applications in cancer

More information

Reconfigurable Architecture for VLSI 9/7-5/3 Wavelet Filter

Reconfigurable Architecture for VLSI 9/7-5/3 Wavelet Filter Reconfigurable Architecture for VSI 9/7-5/3 Wavelet Filter Tze-Yun Sung * Hsi-Chin Hsin ** * Departent of Microelectronics Engineering Chung Hua University 77, Sec., Wufu Road, Hsinchu City 3- TAIWAN bobsung@chu.edu.tw

More information

Designing High Performance Web-Based Computing Services to Promote Telemedicine Database Management System

Designing High Performance Web-Based Computing Services to Promote Telemedicine Database Management System Designing High Perforance Web-Based Coputing Services to Proote Teleedicine Database Manageent Syste Isail Hababeh 1, Issa Khalil 2, and Abdallah Khreishah 3 1: Coputer Engineering & Inforation Technology,

More information

An Efficient Approach for Content Delivery in Overlay Networks

An Efficient Approach for Content Delivery in Overlay Networks An Efficient Approach for Content Delivery in Overlay Networks Mohaad Malli, Chadi Barakat, Walid Dabbous Projet Planète, INRIA-Sophia Antipolis, France E-ail:{alli, cbarakat, dabbous}@sophia.inria.fr

More information

Evaluation of a multi-frame blind deconvolution algorithm using Cramér-Rao bounds

Evaluation of a multi-frame blind deconvolution algorithm using Cramér-Rao bounds Evaluation of a ulti-frae blind deconvolution algorith using Craér-Rao bounds Charles C. Beckner, Jr. Air Force Research Laboratory, 3550 Aberdeen Ave SE, Kirtland AFB, New Mexico, USA 87117-5776 Charles

More information

Effective Tracking of the Players and Ball in Indoor Soccer Games in the Presence of Occlusion

Effective Tracking of the Players and Ball in Indoor Soccer Games in the Presence of Occlusion Effective Tracking of the Players and Ball in Indoor Soccer Gaes in the Presence of Occlusion Soudeh Kasiri-Bidhendi and Reza Safabakhsh Airkabir Univerisity of Technology, Tehran, Iran {kasiri, safa}@aut.ac.ir

More information

THE rapid growth and continuous change of the real

THE rapid growth and continuous change of the real IEEE TRANSACTIONS ON SERVICES COMPUTING, VOL. 8, NO. 1, JANUARY/FEBRUARY 2015 47 Designing High Perforance Web-Based Coputing Services to Proote Teleedicine Database Manageent Syste Isail Hababeh, Issa

More information

Vision Based Mobile Robot Navigation System

Vision Based Mobile Robot Navigation System International Journal of Control Science and Engineering 2012, 2(4): 83-87 DOI: 10.5923/j.control.20120204.05 Vision Based Mobile Robot Navigation Syste M. Saifizi *, D. Hazry, Rudzuan M.Nor School of

More information

A Novel Fast Constructive Algorithm for Neural Classifier

A Novel Fast Constructive Algorithm for Neural Classifier A Novel Fast Constructive Algorith for Neural Classifier Xudong Jiang Centre for Signal Processing, School of Electrical and Electronic Engineering Nanyang Technological University Nanyang Avenue, Singapore

More information

ENHANCEMENT OF MAMMOGRAPHIC IMAGES FOR DETECTION OF MICROCALCIFICATIONS

ENHANCEMENT OF MAMMOGRAPHIC IMAGES FOR DETECTION OF MICROCALCIFICATIONS ENHANCEMENT OF MAMMOGRAPHIC IMAGES FOR DETECTION OF MICROCALCIFICATIONS Damir Seršiæ and Sven Lonèariæ Department of Electronic Systems and Information Processing, Faculty of Electrical Engineering and

More information

Research Article Three-Class Mammogram Classification Based on Descriptive CNN Features

Research Article Three-Class Mammogram Classification Based on Descriptive CNN Features Hindawi BioMed Research International Volue 017, Article ID 3640901, 11 pages https://doi.org/10.1155/017/3640901 Research Article Three-Class Maogra Classification Based on Descriptive CNN Features M.

More information

Optimal Route Queries with Arbitrary Order Constraints

Optimal Route Queries with Arbitrary Order Constraints IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL.?, NO.?,? 20?? 1 Optial Route Queries with Arbitrary Order Constraints Jing Li, Yin Yang, Nikos Maoulis Abstract Given a set of spatial points DS,

More information

Speckle Noise Reduction in Ultrasound Images using Fuzzy Shrinking Technique

Speckle Noise Reduction in Ultrasound Images using Fuzzy Shrinking Technique Speckle Noise Reduction in Ultrasound Iages using Fuzzy Shrinking Technique Bikesh Kuar Singh *, P. Batra, Kesari Vera, A.S. Thoke National Institute of Technology, Raipur, G.E Road Raipur, Chhattisgarh,

More information

Shape Optimization of Quad Mesh Elements

Shape Optimization of Quad Mesh Elements Shape Optiization of Quad Mesh Eleents Yufei Li 1, Wenping Wang 1, Ruotian Ling 1, and Changhe Tu 2 1 The University of Hong Kong 2 Shandong University Abstract We study the proble of optiizing the face

More information

Investigation of The Time-Offset-Based QoS Support with Optical Burst Switching in WDM Networks

Investigation of The Time-Offset-Based QoS Support with Optical Burst Switching in WDM Networks Investigation of The Tie-Offset-Based QoS Support with Optical Burst Switching in WDM Networks Pingyi Fan, Chongxi Feng,Yichao Wang, Ning Ge State Key Laboratory on Microwave and Digital Counications,

More information

Hand Gesture Recognition for Human-Computer Interaction

Hand Gesture Recognition for Human-Computer Interaction Journal of Coputer Science 6 (9): 002-007, 200 ISSN 549-3636 200 Science Publications Hand Gesture Recognition for Huan-Coputer Interaction S. ohaed ansoor Rooi, R. Jyothi Priya and H. Jayalakshi Departent

More information

MULTI-INDEX VOTING FOR ASYMMETRIC DISTANCE COMPUTATION IN A LARGE-SCALE BINARY CODES. Chih-Yi Chiu, Yu-Cyuan Liou, and Sheng-Hao Chou

MULTI-INDEX VOTING FOR ASYMMETRIC DISTANCE COMPUTATION IN A LARGE-SCALE BINARY CODES. Chih-Yi Chiu, Yu-Cyuan Liou, and Sheng-Hao Chou MULTI-INDEX VOTING FOR ASYMMETRIC DISTANCE COMPUTATION IN A LARGE-SCALE BINARY CODES Chih-Yi Chiu, Yu-Cyuan Liou, and Sheng-Hao Chou Departent of Coputer Science and Inforation Engineering, National Chiayi

More information

Fast Bilateral Filter With Arbitrary Range and Domain Kernels

Fast Bilateral Filter With Arbitrary Range and Domain Kernels 269 IEEE TRANSACTIONS ON IAGE PROCESSING, VOL. 2, NO. 9, SEPTEBER 2 [26] D. L. Donoho and I.. Johnstone, Adapting to unknown soothness via wavelet shrinkage, J. Aer. Statist. Assoc., vol. 9, no. 432, pp.

More information

Image Reconstruction. R.D. Badawi. Department of Radiology Department of Biomedical Engineering. Page 1

Image Reconstruction. R.D. Badawi. Department of Radiology Department of Biomedical Engineering. Page 1 First ever X-ray iage - 895 Iage Reconstruction R.D. Badawi Departent of Radiology Departent of Bioedical Engineering X-ray Projection Iaging Requires straight line trajectory of unattenuated x-rays Nuclear

More information

Joint Measurement- and Traffic Descriptor-based Admission Control at Real-Time Traffic Aggregation Points

Joint Measurement- and Traffic Descriptor-based Admission Control at Real-Time Traffic Aggregation Points Joint Measureent- and Traffic Descriptor-based Adission Control at Real-Tie Traffic Aggregation Points Stylianos Georgoulas, Panos Triintzios and George Pavlou Centre for Counication Systes Research, University

More information

A wireless sensor network for visual detection and classification of intrusions

A wireless sensor network for visual detection and classification of intrusions A wireless sensor network for visual detection and classification of intrusions ANDRZEJ SLUZEK 1,3, PALANIAPPAN ANNAMALAI 2, MD SAIFUL ISLAM 1 1 School of Coputer Engineering, 2 IntelliSys Centre Nanyang

More information

A Learning Framework for Nearest Neighbor Search

A Learning Framework for Nearest Neighbor Search A Learning Fraework for Nearest Neighbor Search Lawrence Cayton Departent of Coputer Science University of California, San Diego lcayton@cs.ucsd.edu Sanjoy Dasgupta Departent of Coputer Science University

More information

Massive amounts of high-dimensional data are pervasive in multiple domains,

Massive amounts of high-dimensional data are pervasive in multiple domains, Challenges of Feature Selection for Big Data Analytics Jundong Li and Huan Liu, Arizona State University Massive aounts of high-diensional data are pervasive in ultiple doains, ranging fro social edia,

More information

Rule Extraction using Artificial Neural Networks

Rule Extraction using Artificial Neural Networks Rule Extraction using Artificial Neural Networks S. M. Karuzzaan 1 Ahed Ryadh Hasan 2 Abstract Artificial neural networks have been successfully applied to a variety of business application probles involving

More information

An Optimization Clustering Algorithm Based on Texture Feature Fusion for Color Image Segmentation

An Optimization Clustering Algorithm Based on Texture Feature Fusion for Color Image Segmentation Algoriths 2015, 8, 234-247; doi:10.3390/a8020234 Article OPEN ACCESS algoriths ISSN 1999-4893 www.dpi.co/journal/algoriths An Optiization Clustering Algorith Based on Texture Feature Fusion for Color Iage

More information

Detecting Anomalous Structures by Convolutional Sparse Models

Detecting Anomalous Structures by Convolutional Sparse Models Detecting Anoalous Structures by Convolutional Sparse Models Diego Carrera, Giacoo Boracchi Dipartiento di Elettronica, Inforazione e Bioingegeria Politecnico di Milano, Italy {giacoo.boracchi, diego.carrera}@polii.it

More information

Classification of Benign and Malignant DCE-MRI Breast Tumors by Analyzing the Most Suspect Region

Classification of Benign and Malignant DCE-MRI Breast Tumors by Analyzing the Most Suspect Region Classification of Benign and Malignant DCE-MRI Breast Tuors by Analyzing the Most Suspect Region Sylvia Glaßer 1, Uli Nieann 1, Uta Prei 2, Bernhard Prei 1, Myra Spiliopoulou 3 1 Departent for Siulation

More information

Grid Density Based Clustering Algorithm

Grid Density Based Clustering Algorithm Grid Density Based Clustering Algorith Aandeep Kaur Mann, Navneet Kaur Abstract Clustering is the one of the ost iportant task of the data ining. Clustering is the unsupervised ethod to find the relations

More information

Smarter Balanced Assessment Consortium Claims, Targets, and Standard Alignment for Math

Smarter Balanced Assessment Consortium Claims, Targets, and Standard Alignment for Math Sarter Balanced Assessent Consortiu s, s, Stard Alignent for Math The Sarter Balanced Assessent Consortiu (SBAC) has created a hierarchy coprised of clais targets that together can be used to ake stateents

More information

Reconstruction of Time Series using Optimal Ordering of ICA Components

Reconstruction of Time Series using Optimal Ordering of ICA Components Reconstruction of Tie Series using Optial Ordering of ICA Coponents Ar Goneid and Abear Kael Departent of Coputer Science & Engineering, The Aerican University in Cairo, Cairo, Egypt e-ail: goneid@aucegypt.edu

More information

(Geometric) Camera Calibration

(Geometric) Camera Calibration (Geoetric) Caera Calibration CS635 Spring 217 Daniel G. Aliaga Departent of Coputer Science Purdue University Caera Calibration Caeras and CCDs Aberrations Perspective Projection Calibration Caeras First

More information

Abstract. 2. Segmentation Techniques. Keywords. 1. Introduction. 3. Threshold based Image Segmentation

Abstract. 2. Segmentation Techniques. Keywords. 1. Introduction. 3. Threshold based Image Segmentation International Journal of Advanced Coputer Research (ISSN (print): 49-777 ISSN (online): 77-7970) Volue-3 Nuber- Issue-8 March-03 MRI Brain Iage Segentation based on hresholding G. Evelin Sujji, Y.V.S.

More information

Design Optimization of Mixed Time/Event-Triggered Distributed Embedded Systems

Design Optimization of Mixed Time/Event-Triggered Distributed Embedded Systems Design Optiization of Mixed Tie/Event-Triggered Distributed Ebedded Systes Traian Pop, Petru Eles, Zebo Peng Dept. of Coputer and Inforation Science, Linköping University {trapo, petel, zebpe}@ida.liu.se

More information

Medical Biophysics 302E/335G/ st1-07 page 1

Medical Biophysics 302E/335G/ st1-07 page 1 Medical Biophysics 302E/335G/500 20070109 st1-07 page 1 STEREOLOGICAL METHODS - CONCEPTS Upon copletion of this lesson, the student should be able to: -define the ter stereology -distinguish between quantitative

More information

The Method of Flotation Froth Image Segmentation Based on Threshold Level Set

The Method of Flotation Froth Image Segmentation Based on Threshold Level Set Advances in Molecular Iaging, 5, 5, 38-48 Published Online April 5 in SciRes. http://www.scirp.org/journal/ai http://dx.doi.org/.436/ai.5.54 The Method of Flotation Froth Iage Segentation Based on Threshold

More information

Supplementary Section. A. Algorithm. B. Datasets. C. More on Labeling Functions

Supplementary Section. A. Algorithm. B. Datasets. C. More on Labeling Functions Suppleentary Section In this section, we include ore details about our algorith, labeling functions, datasets as well as additional results and coparisons, which could not be included in the ain paper

More information

Feature Selection to Relate Words and Images

Feature Selection to Relate Words and Images The Open Inforation Systes Journal, 2009, 3, 9-13 9 Feature Selection to Relate Words and Iages Wei-Chao Lin 1 and Chih-Fong Tsai*,2 Open Access 1 Departent of Coputing, Engineering and Technology, University

More information

A Learning Framework for Nearest Neighbor Search

A Learning Framework for Nearest Neighbor Search A Learning Fraework for Nearest Neighbor Search Lawrence Cayton Departent of Coputer Science University of California, San Diego lcayton@cs.ucsd.edu Sanjoy Dasgupta Departent of Coputer Science University

More information

Effects of Interleaving on RTP Header Compression

Effects of Interleaving on RTP Header Compression Effects of Interleaving on RTP Header Copression Colin Perkins Jon Crowcroft Departent of Coputer Science University College London Gower Street London WCE 6BT Abstract We discuss the use of interleaving

More information

Identifying Converging Pairs of Nodes on a Budget

Identifying Converging Pairs of Nodes on a Budget Identifying Converging Pairs of Nodes on a Budget Konstantina Lazaridou Departent of Inforatics Aristotle University, Thessaloniki, Greece konlaznik@csd.auth.gr Evaggelia Pitoura Coputer Science and Engineering

More information

COMPUTER GENERATED HOLOGRAMS Optical Sciences 627 W.J. Dallas (Monday, August 23, 2004, 12:38 PM) PART III: CHAPTER ONE DIFFUSERS FOR CGH S

COMPUTER GENERATED HOLOGRAMS Optical Sciences 627 W.J. Dallas (Monday, August 23, 2004, 12:38 PM) PART III: CHAPTER ONE DIFFUSERS FOR CGH S COPUTER GEERATED HOLOGRAS Optical Sciences 67 W.J. Dallas (onday, August 3, 004, 1:38 P) PART III: CHAPTER OE DIFFUSERS FOR CGH S Part III: Chapter One Page 1 of 8 Introduction Hologras for display purposes

More information

LOSSLESS COMPRESSION OF BAYER MASK IMAGES USING AN OPTIMAL VECTOR PREDICTION TECHNIQUE

LOSSLESS COMPRESSION OF BAYER MASK IMAGES USING AN OPTIMAL VECTOR PREDICTION TECHNIQUE 1th European Signal Processing Conference (EUSIPCO 2006), Florence, Italy, Septeber -8, 2006, copyright by EUASIP LOSSLESS COMPESSION OF AYE MASK IMAES USIN AN OPTIMAL VECTO PEDICTION TECHNIQUE Stefano

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. Professor Willia Hoff Dept of Electrical Engineering &Coputer Science http://inside.ines.edu/~whoff/ 1 Caera Calibration 2 Caera Calibration Needed for ost achine vision and photograetry tasks (object

More information

QUERY ROUTING OPTIMIZATION IN SENSOR COMMUNICATION NETWORKS

QUERY ROUTING OPTIMIZATION IN SENSOR COMMUNICATION NETWORKS QUERY ROUTING OPTIMIZATION IN SENSOR COMMUNICATION NETWORKS Guofei Jiang and George Cybenko Institute for Security Technology Studies and Thayer School of Engineering Dartouth College, Hanover NH 03755

More information

Geo-activity Recommendations by using Improved Feature Combination

Geo-activity Recommendations by using Improved Feature Combination Geo-activity Recoendations by using Iproved Feature Cobination Masoud Sattari Middle East Technical University Ankara, Turkey e76326@ceng.etu.edu.tr Murat Manguoglu Middle East Technical University Ankara,

More information

The Internal Conflict of a Belief Function

The Internal Conflict of a Belief Function The Internal Conflict of a Belief Function Johan Schubert Abstract In this paper we define and derive an internal conflict of a belief function We decopose the belief function in question into a set of

More information

Modal Masses Estimation in OMA by a Consecutive Mass Change Method.

Modal Masses Estimation in OMA by a Consecutive Mass Change Method. Modal Masses Estiation in OMA by a Consecutive Mass Change Method. F. Pelayo University of Oviedo, Departent of Construction and Manufacturing Engineering, Gijón, Spain M. López-Aenlle University of Oviedo,

More information

I-0 Introduction. I-1 Introduction. Objectives: Quote:

I-0 Introduction. I-1 Introduction. Objectives: Quote: I-0 Introduction Objectives: Explain necessity of parallel/ultithreaded algoriths Describe different fors of parallel processing Present coonly used architectures Introduce a few basic ters Coents: Try

More information

Relief shape inheritance and graphical editor for the landscape design

Relief shape inheritance and graphical editor for the landscape design Relief shape inheritance and graphical editor for the landscape design Egor A. Yusov Vadi E. Turlapov Nizhny Novgorod State University after N. I. Lobachevsky Nizhny Novgorod Russia yusov_egor@ail.ru vadi.turlapov@cs.vk.unn.ru

More information

News Events Clustering Method Based on Staging Incremental Single-Pass Technique

News Events Clustering Method Based on Staging Incremental Single-Pass Technique News Events Clustering Method Based on Staging Increental Single-Pass Technique LI Yongyi 1,a *, Gao Yin 2 1 School of Electronics and Inforation Engineering QinZhou University 535099 Guangxi, China 2

More information

An Automatic Detection Method for Liver Lesions Using Abdominal Computed Tomography

An Automatic Detection Method for Liver Lesions Using Abdominal Computed Tomography n utoatic Detection Method for Liver Lesions Using bdoinal Coputed Toography Sheng-Fang Huang Departent of Medical Inforatics Tzu Chi University Hualien, Taiwan SFhuang@ail.tcu.edu.tw Kuo-Hsien Chiang

More information

Automatic Die Inspection for Post-sawing LED Wafers

Automatic Die Inspection for Post-sawing LED Wafers Proceedings of the 009 IEEE International Conference on Systes, Man, and Cybernetics San Antonio, TX, USA - ctober 009 Autoatic Die Inspection for Post-sawing ED Wafers Chuan-Yu Chang 1, Chun-Hsi i, Yung-Chi

More information

A Directional Space-scale Based Analysis Method for Three-dimensional Profile Detection by Fringe Projection Technique

A Directional Space-scale Based Analysis Method for Three-dimensional Profile Detection by Fringe Projection Technique International Journal of Optics and Applications 213, 3(5): 111-117 DOI: 1.5923/j.optics.21335.5 A Directional Space-scale Based Analysis Method for Three-diensional Profile Detection by Fringe Projection

More information

EFFICIENT VIDEO SEARCH USING IMAGE QUERIES A. Araujo1, M. Makar2, V. Chandrasekhar3, D. Chen1, S. Tsai1, H. Chen1, R. Angst1 and B.

EFFICIENT VIDEO SEARCH USING IMAGE QUERIES A. Araujo1, M. Makar2, V. Chandrasekhar3, D. Chen1, S. Tsai1, H. Chen1, R. Angst1 and B. EFFICIENT VIDEO SEARCH USING IMAGE QUERIES A. Araujo1, M. Makar2, V. Chandrasekhar3, D. Chen1, S. Tsai1, H. Chen1, R. Angst1 and B. Girod1 1 Stanford University, USA 2 Qualco Inc., USA ABSTRACT We study

More information

A Model Free Automatic Tuning Method for a Restricted Structured Controller. by using Simultaneous Perturbation Stochastic Approximation

A Model Free Automatic Tuning Method for a Restricted Structured Controller. by using Simultaneous Perturbation Stochastic Approximation 28 Aerican Control Conference Westin Seattle Hotel, Seattle, Washington, USA June -3, 28 WeC9.5 A Model Free Autoatic Tuning Method for a Restricted Structured Controller by Using Siultaneous Perturbation

More information

A robust incremental learning framework for accurate skin region segmentation in color images

A robust incremental learning framework for accurate skin region segmentation in color images Pattern Recognition 40 (2007) 3621 3632 www.elsevier.co/locate/pr A robust increental learning fraework for accurate skin region segentation in color iages Bin Li a,, Xiangyang Xue a, Jianping Fan b a

More information

IMAGE MOSAICKING FOR ESTIMATING THE MOTION OF AN UNDERWATER VEHICLE. Rafael García, Xevi Cufí and Lluís Pacheco

IMAGE MOSAICKING FOR ESTIMATING THE MOTION OF AN UNDERWATER VEHICLE. Rafael García, Xevi Cufí and Lluís Pacheco IMAGE MOSAICKING FOR ESTIMATING THE MOTION OF AN UNDERWATER VEHICLE Rafael García, Xevi Cufí and Lluís Pacheco Coputer Vision and Robotics Group Institute of Inforatics and Applications, University of

More information

LookNN: Neural Network with No Multiplication

LookNN: Neural Network with No Multiplication LookNN: Neural Network with No Multiplication Mohaad Saragh Razlighi, Mohsen Iani, Farinaz Koushanfar and Tajana Rosing ECE Departent, CSE Departent, UC San Diego, La Jolla, CA 993, USA {saragh, oiani,

More information

A NOVEL EFFICIENT MEDICAL IMAGE SEGMENTATION METHODOLOGY

A NOVEL EFFICIENT MEDICAL IMAGE SEGMENTATION METHODOLOGY A NOVEL EFFICIENT MEDICAL IMAGE SEGMENTATION METHODOLOGY Yvonne Bernard Departent of ECE, UCLA, California, USA Architecture 37 Perloff Hall, Los Angeles, CA 90095-467 ABSTRACT Iage segentation plays a

More information

Preprocessing of fmri data (basic)

Preprocessing of fmri data (basic) Preprocessing of fmri data (basic) Practical session SPM Course 2016, Zurich Andreea Diaconescu, Maya Schneebeli, Jakob Heinzle, Lars Kasper, and Jakob Sieerkus Translational Neuroodeling Unit (TNU) Institute

More information

G045 3D Multiple Attenuation and Depth Imaging of Ocean Bottom Seismic Data

G045 3D Multiple Attenuation and Depth Imaging of Ocean Bottom Seismic Data G045 3D Multiple Attenuation and Depth Iaging of Ocean Botto Seisic Data J. Mispel* (StatoilHydro ASA), B. Arntsen (StatoilHydro ASA), A. Kritski (StatoilHydro ASA), L. Aundsen (StatoilHydro ASA), M. Thopson

More information

Comparative Evaluation of Color-Based Video Signatures in the Presence of Various Distortion Types

Comparative Evaluation of Color-Based Video Signatures in the Presence of Various Distortion Types Coparative Evaluation of Color-Based Video Signatures in the Presence of Various Distortion Types Aritz Sánchez de la Fuente, Patrick Ndjiki-Nya, Karsten Sühring, Tobias Hinz, Karsten üller, and Thoas

More information

Preprocessing I: Within Subject John Ashburner

Preprocessing I: Within Subject John Ashburner Preprocessing I: Within Subject John Ashburner Pre-processing Overview Statistics or whatever fmri tie-series Anatoical MRI Teplate Soothed Estiate Spatial Nor Motion Correct Sooth Coregister 11 21 31

More information

A High-Speed VLSI Fuzzy Inference Processor for Trapezoid-Shaped Membership Functions *

A High-Speed VLSI Fuzzy Inference Processor for Trapezoid-Shaped Membership Functions * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 21, 607-626 (2005) A High-Speed VLSI Fuzzy Inference Processor for Trapezoid-Shaped Mebership Functions * SHIH-HSU HUANG AND JIAN-YUAN LAI + Departent of

More information

Biomedical Research 2016; Special Issue: S324-S331 ISSN X

Biomedical Research 2016; Special Issue: S324-S331 ISSN X Bioedical Research 2016; Special Issue: S324-S331 ISSN 0970-938X www.bioedres.info A novel region based segentation of hepatic tuors and hepatic vein in low contrast CTA iages using Bernstein polynoials.

More information

PROBABILISTIC LOCALIZATION AND MAPPING OF MOBILE ROBOTS IN INDOOR ENVIRONMENTS WITH A SINGLE LASER RANGE FINDER

PROBABILISTIC LOCALIZATION AND MAPPING OF MOBILE ROBOTS IN INDOOR ENVIRONMENTS WITH A SINGLE LASER RANGE FINDER nd International Congress of Mechanical Engineering (COBEM 3) Noveber 3-7, 3, Ribeirão Preto, SP, Brazil Copyright 3 by ABCM PROBABILISTIC LOCALIZATION AND MAPPING OF MOBILE ROBOTS IN INDOOR ENVIRONMENTS

More information

Summary. Reconstruction of data from non-uniformly spaced samples

Summary. Reconstruction of data from non-uniformly spaced samples Is there always extra bandwidth in non-unifor spatial sapling? Ralf Ferber* and Massiiliano Vassallo, WesternGeco London Technology Center; Jon-Fredrik Hopperstad and Ali Özbek, Schluberger Cabridge Research

More information

Classification and Prediction of Motion Trajectories using Spatiotemporal Approximations

Classification and Prediction of Motion Trajectories using Spatiotemporal Approximations Classification and Prediction of Motion Trajectories using Spatioteporal Approxiations Andrew Naftel & Shehzad Khalid School of Inforatics University of Manchester Manchester, M6 1QD a.naftel@anchester.ac.uk;

More information

2013 IEEE Conference on Computer Vision and Pattern Recognition. Compressed Hashing

2013 IEEE Conference on Computer Vision and Pattern Recognition. Compressed Hashing 203 IEEE Conference on Coputer Vision and Pattern Recognition Copressed Hashing Yue Lin Rong Jin Deng Cai Shuicheng Yan Xuelong Li State Key Lab of CAD&CG, College of Coputer Science, Zhejiang University,

More information