Foreign Fiber Image Segmentation Based on Maximum Entropy and Genetic Algorithm
|
|
- George Fields
- 6 years ago
- Views:
Transcription
1 Journal of Compuer and Communicaions, 215, 3, 1-7 Published Online November 215 in SciRes. hp:// hp://dx.doi.org/1.4236/jcc Foreign Fiber Image Segmenaion Based on Maximum Enropy and Geneic Algorihm Liping Chen, Xiangyang Chen, Sile Wang, Wenzhu Yang, Sukui Lu School of Compuer Science and Technology, Hebei Universiy, Baoding, China Received Augus 215 Absrac In machine-vision-based sysems for deecing foreign fibers, due o he background of he coon layer has he absolue advanage in he whole image, while he foreign fiber only accoun for a very small par, and wha s more, he brighness and conras of he image are all poor. Using he radiional image segmenaion mehod, he segmenaion resuls are very poor. By adoping he maximum enropy and geneic algorihm, he maximum enropy funcion was used as he finess funcion of geneic algorihm. Through coninuous opimizaion, he opimal segmenaion hreshold is deermined. Experimenal resuls prove ha he image segmenaion of his paper no only fas and accurae, bu also has srong adapabiliy. Keywords Foreign Fibers, Image Segmenaion, Maximum Enropy, Geneic Algorihm 1. Inroducion The foreign fibers in coon refer o hose non-coon fibers and dyed fibers, such as polypropylene fiber silk, hemp, feahers, colored line, colored cloh, hairs and so on. Though very low conen of foreign fibers in coon, he presence of foreign fibers will seriously affec he qualiy of he final coon exile producs, as hey may debase he srengh of he yarn, hey are no easy o be dyed, and his will lead o grea economic loss for he coon exile enerprises [1]. Therefore, fas and accurae measuremen of foreign fibers in lin coon enerprises is an urgen problem. Using machine vision echnology o idenify and measure he foreign fiber is an effecive and feasible soluion. The basis and key of he measuremen of he foreign fiber conen is he foreign fiber s classificaion, and he image segmenaion is he premise and guaranee of he classificaion of he foreign fiber. Image segmenaion is one of he primary sages in image processing and machine vision sysem, and i is also he precondiion of image analysis. The objecive of image segmenaion is o pariion he image ino meaningful conneced-componens o exrac he feaures of objecs [2]. According o he means of image segmenaion, he image segmenaion mehod can be divided ino hreshold mehod, boundary deecion mehod, area mehod and so on. Among hem, he hreshold mehod is he earlies sudied and used. A presen, due o he characerisics of clear physical meaning, obviously effec, easily implemening and good real-ime, he hreshold mehod became one of he mos commonly used image segmenaion mehod in image analysis, image recogniion and machine vision sysems. How o cie his paper: Chen, L.P., Chen, X.Y., Wang, S.L., Yang, W.Z. and Lu, S.K. (215) Foreign Fiber Image Segmenaion Based on Maximum Enropy and Geneic Algorihm. Journal of Compuer and Communicaions, 3, 1-7. hp://dx.doi.org/1.4236/jcc
2 The curren hreshold segmenaion mehod, according o he hreshold selecion crierion funcion ypes, can be divided ino maximum enropy mehod [3], maximum iner-class variance (Osu) mehod, cross enropy mehod [4], minimum error mehod, fuzzy enropy mehod and so on [5]. How o deermine he opimal hreshold is he key of he hreshold segmenaion mehod. Since he maximum enropy mehod does no require a priori knowledge, i is widely used in image segmenaion. Bu he maximum enropy mehod is hrough exhausive search of global opimal soluion, i is very complex and slow. In recen years, due o he fas random search capabiliy, geneic algorihm (GA) has been successfully applied in many fields, such as image processing, machine learning, parameer opimizaion and so on [6] [7]. In his paper, hrough combine GA wih maximum enropy mehod, we realized he fas segmenaion of he foreign fibers. The remainder of his paper is organized as follows. Secion 2 presens he maximum enropy mehod and he GA briefly. Secion 3 provides he proposed algorihm in deail. Resuls and discussions are followed in Secion 4. Secion 5 declares he conclusion. 2. Mehodology 2.1. Maximum Enropy Maximum enropy algorihm is a segmenaion mehod which based on he hisogram of he image [8]. Le x be he gray level of he image (from o L), p(x) is he probabiliy of he pixel which gray level is x in he image, hen he enropy of he image is represened as: L H= px ( )lg px ( ) (1) x= 1 Le he segmenaion hreshold is, which will divide he image ino wo pars: arge A and background B. Assuming ha he gray values which less han he hreshold of he pixels belong o he arge A, he gray values which greaer han or equal o he hreshold of he pixels belong o he background B, hen he probabiliy of pixels in he image are relaed o arge A and background B respecively is: Targe A: Background B: p p b a 1 = p (2) 255 i i = p (3) The enropy of he arge region and he background region are respecively defined as: 1 H ( ) = ( p p )lg( p p ) (4) a i a i a 255 H ( ) = ( p p )lg( p p ) (5) b i b i b The enropy of he whole image is defined as: H () = H() + H() (6) a The greaer he value of funcion H(), he more informaion of he arge and background represen, he more accurae he arge and he background area. The global opimal hreshold (le i be * ) is he value which make H() ake he maximum value, ha is, * can be expressed as: b = arg max H ( ) (7) 2.2. Geneic Algorihm Geneic algorihm (GA) is a parallel random search opimizaion mehod which simulaes naural geneic mechanism and biological evoluion heory. I is sochasic raher han exhausive. I can obain he global opimal 2
3 soluion wih large probabiliy. In addiion, GA does no require he evaluaion funcion o be monoone, so GA is very suiable for real-ime processing, which is no only easy o implemen, bu also has srong robusness. The basic idea of he algorihm is firs encoding he problem o be solved ino a sring (named chromosome). Each chromosome is a soluion o he being solved problem. Nex, GA calculaes he finess value of each individual in a group of chromosomes, hen chromosomes wih higher finess are seleced for crossover and muaion operaion and hen produce a new generaion wih higher finess. A las, he relaive opimal soluion is obained by coninuous ieraion. 3. Foreign Fiber Image Segmenaion Based on Maximum Enropy and Geneic Algorihm Through analysis he coon foreign fiber images, i is found ha he background of he coon layer has he absolue advanage in he whole image, while he arge is very small (Figures 2-5). Furhermore, he brighness and conras of he image are all poor. Using he radiional image segmenaion mehod (e.g. Osu), he segmenaion resuls are very poor. Therefore, we adop he maximum enropy hreshold mehod in his paper. However, he essence of he maximum enropy mehod is o obain he maximum value of he objecive funcion (Equaion (6)) in he gray space, he compuaion of he algorihm is very large, and i akes much more ime. In order o reduce he complexiy of he algorihm, we combine GA wih he maximum enropy in he foreign fiber image segmenaion. The maximum enropy funcion was used as he finess funcion of GA. By coninuous opimizaion, he opimal segmenaion hreshold is deermined. The flow char of he algorihm was shown as Figure Encoding and Design Finess Funcion Encoding a soluion of a problem ino a serial of genes, called chromosome, is very imporan when using GA. Various encoding mehods have been proposed for paricular problems o provide effecive implemenaion of GA, such as binary encoding, real number encoding, ineger or lieral permuaion encoding, or general daa srucure encoding [9]. In our research, we chose he binary encoding mehod. Since he gray level of he foreign fiber image has 256 gray level, so encoding he segmenaion hreshold wih 8 binary sring, and ake he enropy funcion of Equaion (6) as he finess funcion. Figure 1. Flowchar of he proposed mehod. 3
4 3.2. Populaion Iniializaion The iniial populaion for evoluion is creaed randomly. Individual in he iniial populaion is equivalen o he candidae soluion in he soluion space. If he populaion size is oo large, he compuaional complexiy is high; if he scale is oo small, he search space is limied, he search may sop a he immaure sage. Therefore, he populaion number is se o 2, he maximum number of ieraions is se o Selecion Operaion The selecion operaion, also known as he copy operaion, is o deermine which individual is geneic and which individual is eliminaed. The common mehods include roulee wheel mehod, he elie preservaion sraegy and he order selecion mehod. As he crossover and muaion operaions are performed, he opimal soluion can be easily los in an inermediae sep. So we adoped he mehod of 1% elie sraegy and 9% roulee wheel. Individuals wih he larges finess direcly ino he nex generaion, which can guaranee ha he algorihm converges o he global opimal soluion; he remaining 9% of he individuals are seleced according o he finess proporionae. The larger he finess of he individual, he greaer he probabiliy of being seleced. The probabiliy of he individual i is seleced o he nex generaion group is: n P = F F (8) i i i 1 where n is he populaion size, F i is he finess of he individual i Crossover Operaion Commonly used crossover operaions include single-poin crossover, double-poin crossover, muli-poin crossover, ec. In our research, we chose he single-poin crossover operaor, he crossover probabiliy is.8 and.6 respecively Muaion Operaion According o he muaion probabiliy, he individual's value is replaced by some oher gene values, which can increase he diversiy of he populaion, and can also improve he local search abiliy of GA. Various muaion operaions have been inroduced by researchers, such as inversion muaion, neighbor exchange muaion, ec. We chose inversion muaion in our research Probabiliy of Crossover and Muaion The probabiliies of crossover and muaion, denoed by P c and P m, affec seriously he search abiliy and convergence speed of GA [1]. For he sandard GA, P c and P m are all fixed. Bu in he early sage of evoluion, he individual difference is bigger, so we should increase P c and reduce P m in order o accelerae he evoluion process and a he same ime reducing he amoun of calculaion. In he laer sage of evoluion, he individual difference is small, so P m should be reduced and P c should be increased o avoid local opimal soluion. For he proposed algorihm, P c is.8 during he firs 5 generaions of he evoluion, so as o search he opimal soluion as soon as possible. In he second par of he evoluion, P c is.6. The muaion probabiliy P m is calculaed by: Pm log 2( g+ 1) f f Pm = Pm f f where P m is he iniial muaion probabiliy; f is he finess of he paren chromosome; f is he average finess of he chromosomes in he curren populaion [11] Terminae Crierion We se wo erminae crierions in our GA: 1) maximum generaion number. When he maximum number of ieraions is reached, he algorihm erminaes; 2) se he minimum number of ieraions is 1, when he ieraion (9) 4
5 number is larger han he value, check he difference beween he average finess of he curren populaion and he average finess of he las generaion wheher less han a minimum value ε (here ε =.1), once he condiion is saisfied, he ieraion erminaes. 4. Resuls and Discussions In order o verify he effeciveness of he paper s algorihm, we colleced 6 foreign fiber images which include 5 foreign fibers such as hair, feaher, hemp rope, polypropylene, cloh and so on. The image is size. The experimens are performed on over Malab7.1 plaform. We compared he resuls of he paper s mehod wih he resuls of he Osu s mehod. Figures 2-5 show a par of he experimenal resuls. I can be seen from Figures 2-5, for he original image, he coon layer background occupies he absolue advanage in he whole image, while he foreign fiber only accouns for a very small par, and he conras of he image is very low. Therefore, in many cases, he arge canno be separaed from he background by using he Osu mehod (e.g. Figures 2-4). For Figure 2 and Figure 3, alhough he arge was segmened, bu par of he background was divided ino he arge oo. The foreign fiber of Figure 4 was no exraced a all. So he reliabiliy of he Osu is very poor. In conras, his paper s mehod works well in mos cases. The exracion of he arge is accurae and complee. Table 1 liss he saisical segmenaion resuls of 6 foreign fiber images wih wo differen mehods. Figure 2. Color image of polypropylene fiber; The resul of he paper s mehod; The resul of Osu. Figure 3. Color image of cloh piece; The resul of he paper s mehod; The resul of Osu. 5
6 Figure 4. Color image of hemp rope; The resul of he paper s mehod; The resul of Osu. Figure 5. Color image of feaher; The resul of he paper s mehod; The resul of Osu. Table 1. Caparison of he segmenaion resuls by wo differen mehods. Image name Image number The proposed mehod Segmenaion accuracy Hair 1 9% 2% Feaher 15 1% 1% Polypropylene 1 1% 5% Cloh 15 1% 6% Hemp rope 1 1% 2% Osu The resuls shown in Table 1 indicaed ha for differen foreign fiber images, he segmenaion accuracy of he proposed mehod is very high, i has srong adapabiliy. While for he Osu mehod, he segmenaion accuracy is higher when he area of he arge is larger (such as he feaher images, he segmenaion accuracy is 1%). When he foreign fiber s area is small, he segmenaion accuracy is very low (such as hair and wine images, he accuracy rae is only 2%). So, for low conras images, he mehod of combining he maximum enropy and geneic algorihm can effecively improve he image segmenaion accuracy. 6
7 5. Conclusions Due o he low brighness, low conras and small proporion of he arge of he foreign fiber images, we adoped he image segmenaion based on maximum enropy and geneic algorihm. Experimenal resuls show ha he adoped algorihm is more accurae han he radiional Osu mehod, and he speed is fas and adapable, which mees he real-ime requiremens of he foreign fiber deecion sysem. Nex work: for he deecion of whie foreign fibers (such as plasic sheeing, plasic film, ec.), he accuracy of he segmenaion algorihm is poor, here is sill o be furher improved. Acknowledgemens The auhors hank Hebei Naural Science Foundaion (F ), he Minisry of Science and Technology of he People s Republic of China (213DFA1132), for heir financial suppor. References [1] Yang, M.H. (214) Hazards and Prevenion of Foreign Fiber in Coon. Jiangsu Texile, 4, (In Chinese wih English Absrac) [2] Zhang, Y.J. (213) Image Engineering (II) Image Analysis. Tsinghua Universiy Press, Beijing. [3] He, Z.J. and Wang, H.F. (21) Chinese Word Sense Disambiguaion Based on Maximum Enropy Model wih Feaure Selecion. Journal of Sofware, 21, hp://dx.doi.org/1.3724/sp.j [4] Wu, Y.Q. and Zhang, X.J. (211) Two-Dimensional Symmeric Cross-Enropy Image Thresholding. Journal of Image and Graphics, 16, [5] Wu, Y.Q., Meng, T.L. and Wu, S.H. (215) Research Progress of Image Threshold Mehods in Recen 2 Years ( ). Journal of Daa Acquisiion and Processing, 3, [6] Ou, P. and He, D. (211) 2-D Maximum Enropy Mehod of Image Segmenaion Based on Geneic Algorihm. Journal of Compuer Simulaion, 1, [7] Guo, M.S. and Liu, B.H. (28) 2-D Maximum Enropy Mehod in Image Segmenaion Based on Chaos Geneic Algorihm. Compuer Technology and Developmen, 18, [8] Cao, J.N. (212) Review on Image Segmenaion Based on Enropy. Paern Recogniion and Arificial Inelligence, 25, [9] Zhang, C.Q., Zheng, J.G. and Qian, J. (211) Comparison of Coding Schemes for Geneic Algorihms. Applicaion Research of Compuers, 28, [1] Cao, D.Y. and Cheng, J.X. (21) A Geneic Algorihm Based on Modified Selecion Operaor and Crossover Operaor. Compuer Technology and Developmen, 2, [11] Yang, W.Z., Li, D.L. and Zhu, L. (21) An Improved Geneic Algorihm for Opimal Feaure Subse Selecion from Muli-Characer Feaure Se. Journal of Agriculural Machinery, 38,
A Segmentation Method for Uneven Illumination Particle Images
Research Journal of Applied Sciences, Engineering and Technology 5(4): 1284-1289, 2013 ISSN: 2040-7459; e-issn: 2040-7467 Maxwell Scienific Organizaion, 2013 Submied: July 17, 2012 Acceped: Augus 15, 2012
More informationPointwise Image Operations
Poinwise Image Operaions Binary Image Analysis Jana Kosecka hp://cs.gmu.edu/~kosecka/cs482.hml - Lookup able mach image inensiy o he displayed brighness values Manipulaion of he lookup able differen Visual
More informationP. Bruschi: Project guidelines PSM Project guidelines.
Projec guidelines. 1. Rules for he execuion of he projecs Projecs are opional. Their aim is o improve he sudens knowledge of he basic full-cusom design flow. The final score of he exam is no affeced by
More informationEvaluation of the Digital images of Penaeid Prawns Species Using Canny Edge Detection and Otsu Thresholding Segmentation
Inernaional Associaion of Scienific Innovaion and Research (IASIR) (An Associaion Unifying he Sciences, Engineering, and Applied Research) Inernaional Journal of Emerging Technologies in Compuaional and
More informationComparing image compression predictors using fractal dimension
Comparing image compression predicors using fracal dimension RADU DOBRESCU, MAEI DOBRESCU, SEFA MOCAU, SEBASIA ARALUGA Faculy of Conrol & Compuers POLIEHICA Universiy of Buchares Splaiul Independenei 313
More informationPulse Train Controlled PCCM Buck-Boost Converter Ming Qina, Fangfang Lib
5h Inernaional Conference on Environmen, Maerials, Chemisry and Power Elecronics (EMCPE 016 Pulse Train Conrolled PCCM Buck-Boos Converer Ming Qina, Fangfang ib School of Elecrical Engineering, Zhengzhou
More informationDevelopment of Temporary Ground Wire Detection Device
Inernaional Journal of Smar Grid and Clean Energy Developmen of Temporary Ground Wire Deecion Device Jing Jiang* and Tao Yu a Elecric Power College, Souh China Universiy of Technology, Guangzhou 5164,
More informationAn Automated Fish Counting Algorithm in Aquaculture Based on Image Processing
Inernaional Forum on Mechanical, Conrol and Auomaion (IFMCA 06) An Auomaed Fish Couning Algorihm in Aquaculure Based on Image Processing Jiuyi Le,a, Lihong Xu,b College of Elecronics and Informaion Engineering,
More informationSocial-aware Dynamic Router Node Placement in Wireless Mesh Networks
Social-aware Dynamic Rouer Node Placemen in Wireless Mesh Neworks Chun-Cheng Lin Pei-Tsung Tseng Ting-Yu Wu Der-Jiunn Deng ** Absrac The problem of dynamic rouer node placemen (dynrnp) in wireless mesh
More informationMotion-blurred star image acquisition and restoration method based on the separable kernel Honglin Yuana, Fan Lib and Tao Yuc
5h Inernaional Conference on Advanced Maerials and Compuer Science (ICAMCS 206) Moion-blurred sar image acquisiion and resoraion mehod based on he separable kernel Honglin Yuana, Fan Lib and Tao Yuc Beihang
More informationEvaluation of Instantaneous Reliability Measures for a Gradual Deteriorating System
General Leers in Mahemaic, Vol. 3, No.3, Dec 27, pp. 77-85 e-issn 259-9277, p-issn 259-9269 Available online a hp:\\ www.refaad.com Evaluaion of Insananeous Reliabiliy Measures for a Gradual Deerioraing
More informationComparitive Analysis of Image Segmentation Techniques
ISSN: 78 33 Volume, Issue 9, Sepember 3 Compariive Analysis of Image Segmenaion echniques Rohi Sardana Pursuing Maser of echnology (Compuer Science and Engineering) GJU S& Hissar, Haryana Absrac Image
More informationRobot Control using Genetic Algorithms
Robo Conrol using Geneic Algorihms Summary Inroducion Robo Conrol Khepera Simulaor Geneic Model for Pah Planning Chromosome Represenaion Evaluaion Funcion Case Sudies Conclusions The Robo Conroller Problem
More informationDouble Tangent Sampling Method for Sinusoidal Pulse Width Modulation
Compuaional and Applied Mahemaics Journal 2018; 4(1): 8-14 hp://www.aasci.org/journal/camj ISS: 2381-1218 (Prin); ISS: 2381-1226 (Online) Double Tangen Sampling Mehod for Sinusoidal Pulse Widh Modulaion
More informationOptimization of PID Parameter for Position Control of DC-Motor using Multi-Objective Genetic Algorithm
ISSN (Online) 2321 24 Vol. 2, Issue 6, June 214 Opimizaion of PID Parameer for Posiion Conrol of DC-Moor using Muli-Objecive Geneic Algorihm MD Amanullah 1, Mohi Jain 2, Praibha Tiwari 3, Sidharh Gupa
More informationDirect Analysis of Wave Digital Network of Microstrip Structure with Step Discontinuities
Direc Analysis of Wave Digial Nework of Microsrip Srucure wih Sep Disconinuiies BILJANA P. SOŠIĆ Faculy of Elecronic Engineering Universiy of Niš Aleksandra Medvedeva 4, Niš SERBIA MIODRAG V. GMIROVIĆ
More informationBounded Iterative Thresholding for Lumen Region Detection in Endoscopic Images
Bounded Ieraive Thresholding for Lumen Region Deecion in Endoscopic Images Pon Nidhya Elango School of Compuer Science and Engineering Nanyang Technological Universiy Nanyang Avenue, Singapore Email: ponnihya88@gmail.com
More informationAn Emergence of Game Strategy in Multiagent Systems
An Emergence of Game Sraegy in Muliagen Sysems Peer LACKO Slovak Universiy of Technology Faculy of Informaics and Informaion Technologies Ilkovičova 3, 842 16 Braislava, Slovakia lacko@fii.suba.sk Absrac.
More informationKnowledge Transfer in Semi-automatic Image Interpretation
Knowledge Transfer in Semi-auomaic Image Inerpreaion Jun Zhou 1, Li Cheng 2, Terry Caelli 23, and Waler F. Bischof 1 1 Deparmen of Compuing Science, Universiy of Albera, Edmonon, Albera, Canada T6G 2E8
More informationA new image security system based on cellular automata and chaotic systems
A new image securiy sysem based on cellular auomaa and chaoic sysems Weinan Wang Jan 2013 Absrac A novel image encrypion scheme based on Cellular Auomaa and chaoic sysem is proposed in his paper. The suggesed
More informationLecture 4. EITN Chapter 12, 13 Modulation and diversity. Antenna noise is usually given as a noise temperature!
Lecure 4 EITN75 2018 Chaper 12, 13 Modulaion and diversiy Receiver noise: repeiion Anenna noise is usually given as a noise emperaure! Noise facors or noise figures of differen sysem componens are deermined
More informationMobile Robot Localization Using Fusion of Object Recognition and Range Information
007 IEEE Inernaional Conference on Roboics and Auomaion Roma, Ialy, 10-14 April 007 FrB1.3 Mobile Robo Localizaion Using Fusion of Objec Recogniion and Range Informaion Byung-Doo Yim, Yong-Ju Lee, Jae-Bok
More informationA New and Robust Segmentation Technique Based on Pixel Gradient and Nearest Neighbors for Efficient Classification of MRI Images
A New and Robus Segmenaion Technique Based on Pixel Gradien and Neares Neighbors for Efficien Classificaion of MRI Images Sanchi Kumar, Sahil Dalal Absrac This paper proposes a new fully auomaed mehod
More information4 20mA Interface-IC AM462 for industrial µ-processor applications
Because of he grea number of indusrial buses now available he majoriy of indusrial measuremen echnology applicaions sill calls for he sandard analog curren nework. The reason for his lies in he fac ha
More informationA neurofuzzy color image segmentation method for wood surface defect detection
neurofuzzy color image segmenaion mehod for wood surface defec deecion Gonzalo. Ruz Pablo. Esévez Claudio. Perez bsrac crucial sep in developing auomaed visual inspecion sysems for wood boards is image
More informationVariation Aware Cross-Talk Aggressor Alignment by Mixed Integer Linear Programming
ariaion Aware Cross-alk Aggressor Alignmen by Mixed Ineger Linear Programming ladimir Zoloov IBM. J. Wason Research Cener, Yorkown Heighs, NY zoloov@us.ibm.com Peer Feldmann D. E. Shaw Research, New York,
More informationDeblurring Images via Partial Differential Equations
Deblurring Images via Parial Dierenial Equaions Sirisha L. Kala Mississippi Sae Universiy slk3@mssae.edu Advisor: Seh F. Oppenheimer Absrac: Image deblurring is one o he undamenal problems in he ield o
More informationDiscrete Word Speech Recognition Using Hybrid Self-adaptive HMM/SVM Classifier
Journal of Technical Engineering Islamic Azad Universiy of Mashhad Discree Word Speech Recogniion Using Hybrid Self-adapive HMM/SVM Classifier Saeid Rahai Quchani (1) Kambiz Rahbar (2) (1)Assissan professor,
More informationAutomatic Power Factor Control Using Pic Microcontroller
IDL - Inernaional Digial Library Of Available a:www.dbpublicaions.org 8 h Naional Conference on Advanced Techniques in Elecrical and Elecronics Engineering Inernaional e-journal For Technology And Research-2017
More informationFault Diagnosis System Identification Based on Impedance Matching Balance Transformer
Inernaional Conference on Advanced Maerial Science and Environmenal Engineering (AMSEE 06) Faul Diagnosis Sysem Idenificaion Based on Impedance Maching Balance ransformer Yanjun Ren* and Xinli Deng Chongqing
More informationSketch-based Image Retrieval Using Contour Segments
Skech-based Image Rerieval Using Conour Segmens Yuing Zhang #1, Xueming Qian *2, Xianglong Tan #3 # SMLESLAB of Xi an Jiaoong Universiy, Xi an CN710049, China 1 zhangyuing@su.xju.edu.cn 2 qianxm@mail.xju.edu.cn
More informationMemorandum on Impulse Winding Tester
Memorandum on Impulse Winding Teser. Esimaion of Inducance by Impulse Response When he volage response is observed afer connecing an elecric charge sored up in he capaciy C o he coil L (including he inside
More informationRecognition and Tracing Scheme Study of Moving Objects by Video Monitoring System
www.ijcsi.org 85 Recogniion and Tracing Scheme Sudy of Moving Ojecs y Video Monioring Sysem Peilong XU 1 1 The Growing Base for Sae Key Laoraory, Qingdao Universiy, No. 308, Ningxia Road, Qingdao 266071,
More informationAn off-line multiprocessor real-time scheduling algorithm to reduce static energy consumption
An off-line muliprocessor real-ime scheduling algorihm o reduce saic energy consumpion Firs Workshop on Highly-Reliable Power-Efficien Embedded Designs Shenzhen, China Vincen Legou, Mahieu Jan, Lauren
More informationSignal Characteristics
Signal Characerisics Analog Signals Analog signals are always coninuous (here are no ime gaps). The signal is of infinie resoluion. Discree Time Signals SignalCharacerisics.docx 8/28/08 10:41 AM Page 1
More informationLab 3 Acceleration. What You Need To Know: Physics 211 Lab
b Lab 3 Acceleraion Wha You Need To Know: The Physics In he previous lab you learned ha he velociy of an objec can be deermined by finding he slope of he objec s posiion vs. ime graph. x v ave. = v ave.
More informationA NEW DUAL-POLARIZED HORN ANTENNA EXCITED BY A GAP-FED SQUARE PATCH
Progress In Elecromagneics Research Leers, Vol. 21, 129 137, 2011 A NEW DUAL-POLARIZED HORN ANTENNA EXCITED BY A GAP-FED SQUARE PATCH S. Ononchimeg, G. Ogonbaaar, J.-H. Bang, and B.-C. Ahn Applied Elecromagneics
More informationNegative frequency communication
Negaive frequency communicaion Fanping DU Email: dufanping@homail.com Qing Huo Liu arxiv:2.43v5 [cs.it] 26 Sep 2 Deparmen of Elecrical and Compuer Engineering Duke Universiy Email: Qing.Liu@duke.edu Absrac
More informationImproving the Sound Recording Quality of Wireless Sensors Using Automatic Gain Control Methods
BULETINUL ŞTIINŢIFIC al Universiăţii POLITEHNICA din Timişoara, România, Seria AUTOMATICĂ ŞI CALCULATOARE SCIENTIFIC BULLETIN of The POLITEHNICA Universiy of Timişoara, Romania, Transacions on AUTOMATIC
More informationFuzzy Inference Model for Learning from Experiences and Its Application to Robot Navigation
Fuzzy Inference Model for Learning from Experiences and Is Applicaion o Robo Navigaion Manabu Gouko, Yoshihiro Sugaya and Hiroomo Aso Deparmen of Elecrical and Communicaion Engineering, Graduae School
More informationHardware Design of Moving Object Detection on Reconfigurable System
Journal of Compuer and Communicaions, 206, 4, 30-43 Published Online Augus 206 in SciRes. hp://www.scirp.org/journal/jcc hp://dx.doi.org/0.4236/jcc.206.40004 Hardware Design of Moving Objec Deecion on
More informationECMA st Edition / June Near Field Communication Wired Interface (NFC-WI)
ECMA-373 1 s Ediion / June 2006 Near Field Communicaion Wired Inerface (NFC-WI) Sandard ECMA-373 1 s Ediion / June 2006 Near Field Communicaion Wired Inerface (NFC-WI) Ecma Inernaional Rue du Rhône 114
More informationGP Algorithm versus Hybrid and Mixed Neural Networks
CENTRE FOR EMEA BANKING, FINANCE & ECONOMICS GP Algorihm versus Hybrid and Mixed Neural Neworks Andreas Karahanasopoulos Working Paper Series No 16/11 GP Algorihm versus Hybrid and Mixed Neural Neworks
More informationTwo-area Load Frequency Control using IP Controller Tuned Based on Harmony Search
Research Journal of Applied Sciences, Engineering and Technology 3(12): 1391-1395, 211 ISSN: 24-7467 Maxwell Scienific Organizaion, 211 Submied: July 22, 211 Acceped: Sepember 18, 211 Published: December
More informationNotes on the Fourier Transform
Noes on he Fourier Transform The Fourier ransform is a mahemaical mehod for describing a coninuous funcion as a series of sine and cosine funcions. The Fourier Transform is produced by applying a series
More informationSimulation Analysis of DC-DC Circuit Based on Simulink in Intelligent Vehicle Terminal
Open Access Library Journal 218, Volume 5, e4682 ISSN Online: 2333-9721 ISSN Prin: 2333-975 Simulai Analysis of DC-DC Circui Based Simulink in Inelligen Vehicle erminal Weiran Li, Guoping Yang College
More informationStudy on the Wide Gap Dielectric Barrier Discharge Device Gaofeng Wang
Sudy on he Wide Gap Dielecric Barrier Discharge Device Gaofeng Wang School of Informaion Engineering, Zhengzhou Universiy, Zhengzhou 450001, China 932167312@qq.com Keywords: DBD; Wide air gap; Plasma body;
More informationPerformance Analysis of High-Rate Full-Diversity Space Time Frequency/Space Frequency Codes for Multiuser MIMO-OFDM
Performance Analysis of High-Rae Full-Diversiy Space Time Frequency/Space Frequency Codes for Muliuser MIMO-OFDM R. SHELIM, M.A. MATIN AND A.U.ALAM Deparmen of Elecrical Engineering and Compuer Science
More informationECE-517 Reinforcement Learning in Artificial Intelligence
ECE-517 Reinforcemen Learning in Arificial Inelligence Lecure 11: Temporal Difference Learning (con.), Eligibiliy Traces Ocober 8, 2015 Dr. Iamar Arel College of Engineering Deparmen of Elecrical Engineering
More informationEE 330 Lecture 24. Amplification with Transistor Circuits Small Signal Modelling
EE 330 Lecure 24 Amplificaion wih Transisor Circuis Small Signal Modelling Review from las ime Area Comparison beween BJT and MOSFET BJT Area = 3600 l 2 n-channel MOSFET Area = 168 l 2 Area Raio = 21:1
More informationA WIDEBAND RADIO CHANNEL MODEL FOR SIMULATION OF CHAOTIC COMMUNICATION SYSTEMS
A WIDEBAND RADIO CHANNEL MODEL FOR SIMULATION OF CHAOTIC COMMUNICATION SYSTEMS Kalle Rui, Mauri Honanen, Michael Hall, Timo Korhonen, Veio Porra Insiue of Radio Communicaions, Helsini Universiy of Technology
More informationMATLAB/SIMULINK TECHNOLOGY OF THE SYGNAL MODULATION
J Modern Technology & Engineering Vol2, No1, 217, pp76-81 MATLAB/SIMULINK TECHNOLOGY OF THE SYGNAL MODULATION GA Rusamov 1*, RJ Gasimov 1, VG Farhadov 1 1 Azerbaijan Technical Universiy, Baku, Azerbaijan
More informationAUTOMATED TECHNIQUES FOR SATELLITE IMAGE SEGMENTATION
IPR IPT IGU UCI CIG ACG Table of conens Table des maières Auhors index Index des aueurs earch Recherches xi orir AUTOMATD TCHIQU FOR ATLLIT IMAG GMTATIO A. Guarnieri*, A. Veore* *CIRGO (Inerdeparmen Research
More informationSEGMENTATION USING ADAPTIVE THRESHOLDING OF THE IMAGE HISTOGRAM ACCORDING TO THE INCREMENTAL RATES OF THE SEGMENT LIKELIHOOD FUNCTIONS.
SEGMENTATION USING ADAPTIVE THRESHOLDING OF THE IMAGE HISTOGRAM ACCORDING TO THE INCREMENTAL RATES OF THE SEGMENT LIELIHOOD FUNCTIONS Ioannis M. Sephanais and George C. Anasassopoulos Hellenic Telecommunicaions
More informationThe design of an improved matched filter in DSSS-GMSK system
Journal of Physics: Conference Series PAPER OPEN ACCESS The design of an improved mached filer in DSSS-GMSK sysem To cie his aricle: Mao Wei-ong e al 16 J. Phys.: Conf. Ser. 679 1 View he aricle online
More informationFamily of Single-Inductor Multi-Output DC-DC Converters
PEDS009 Family of Single-Inducor Muli-Oupu DC-DC Converers Ray-ee in Naional Cheng Kung Universiy No., a-hseuh Road ainan Ciy, aiwan rayleelin@ee.ncku.edu.w Chi-Rung Pan Naional Cheng Kung Universiy No.,
More informationA FMCW-FSK Combined Waveform for Multi-Target Detection in FMCW Radar
217 2 n Inernaional Conerence on Compuer Engineering, Inormaion Science an Inerne Technology (CII 217) ISBN: 978-1-6595-54-9 A FMCW-FSK Combine Waveorm or Muli-Targe Deecion in FMCW Raar TAO SHEN, WENQUAN
More informationEXPERIMENT #9 FIBER OPTIC COMMUNICATIONS LINK
EXPERIMENT #9 FIBER OPTIC COMMUNICATIONS LINK INTRODUCTION: Much of daa communicaions is concerned wih sending digial informaion hrough sysems ha normally only pass analog signals. A elephone line is such
More informationImproving Driver Alertness through Music Selection Using a Mobile EEG to Detect Brainwaves
Sensors 2013 13 8199-8221; doi:10.3390/s130708199 Aricle OPN ACCSS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Improving Driver Alerness hrough Music Selecion Using a Mobile G o Deec Brainwaves
More informationSLAM Algorithm for 2D Object Trajectory Tracking based on RFID Passive Tags
2008 IEEE Inernaional Conference on RFID The Veneian, Las Vegas, Nevada, USA April 16-17, 2008 1C2.2 SLAM Algorihm for 2D Objec Trajecory Tracking based on RFID Passive Tags Po Yang, Wenyan Wu, Mansour
More informationChannel Estimation for Wired MIMO Communication Systems
Channel Esimaion for Wired MIMO Communicaion Sysems Final Repor Mulidimensional DSP Projec, Spring 2005 Daifeng Wang Absrac This repor addresses raining-based channel modeling and esimaion for a wired
More informationTransformer of tgδ on MSP430F1331 single chip microcomputer WANG Han 1 CAI Xinjing 1,XiaoJieping 2,Liu weiqing 2
2nd Inernaional Workshop on Maerials Engineering and ompuer Sciences (IWMES 205 Transformer of gδ on MSP430F33 single chip microcompuer WANG Han AI Xinjing,XiaoJieping 2,Liu weiqing 2 School of elecrical
More informationInvestigation and Simulation Model Results of High Density Wireless Power Harvesting and Transfer Method
Invesigaion and Simulaion Model Resuls of High Densiy Wireless Power Harvesing and Transfer Mehod Jaber A. Abu Qahouq, Senior Member, IEEE, and Zhigang Dang The Universiy of Alabama Deparmen of Elecrical
More informationLaplacian Mixture Modeling for Overcomplete Mixing Matrix in Wavelet Packet Domain by Adaptive EM-type Algorithm and Comparisons
Proceedings of he 5h WSEAS Inernaional Conference on Signal Processing, Isanbul, urey, May 7-9, 6 (pp45-5) Laplacian Mixure Modeling for Overcomplee Mixing Marix in Wavele Pace Domain by Adapive EM-ype
More informationParameters Affecting Lightning Backflash Over Pattern at 132kV Double Circuit Transmission Lines
Parameers Affecing Lighning Backflash Over Paern a 132kV Double Circui Transmission Lines Dian Najihah Abu Talib 1,a, Ab. Halim Abu Bakar 2,b, Hazlie Mokhlis 1 1 Deparmen of Elecrical Engineering, Faculy
More informationUsing Box-Jenkins Models to Forecast Mobile Cellular Subscription
Open Journal of Saisics, 26, 6, 33-39 Published Online April 26 in SciRes. hp://www.scirp.org/journal/ojs hp://dx.doi.org/.4236/ojs.26.6226 Using Box-Jenkins Models o Forecas Mobile Cellular Subscripion
More informationDimensions. Transmitter Receiver ø2.6. Electrical connection. Transmitter +UB 0 V. Emitter selection. = Light on = Dark on
OBE-R-SE Dimensions Transmier.. 7.5 9..5.8 4.9 4 5 M 8.9 7.5 9..5.8 4 5 M 8.9 ø.6 ø.6 Model Number OBE-R-SE Thru-beam sensor wih m fixed cable Elecrical connecion Transmier Feaures BN +UB WH IN Ulra-small
More informationDimensions. Transmitter Receiver ø2.6. Electrical connection. Transmitter +UB 0 V. Emitter selection. = Light on = Dark on
OBE-R-SE Dimensions Transmier.. 7.5 9..5.8 4.9 4 5 M 8.9 7.5 9..5.8 4 5 M 8.9 ø.6 ø.6 Model Number OBE-R-SE Thru-beam sensor wih m fixed cable Elecrical connecion Transmier Feaures BN +UB WH IN Ulra-small
More informationInstalling remote sites using TCP/IP
v dc Keypad from nework Whie/ 3 Whie/ 4 v dc Keypad from nework Whie/ 3 Whie/ 4 v dc Keypad from nework Whie/ 3 Whie/ 4 +v pu +v pu +v pu v dc Keypad from nework Whie/ 3 Whie/ 4 v dc Keypad from nework
More information4.5 Biasing in BJT Amplifier Circuits
4/5/011 secion 4_5 Biasing in MOS Amplifier Circuis 1/ 4.5 Biasing in BJT Amplifier Circuis eading Assignmen: 8086 Now le s examine how we C bias MOSFETs amplifiers! f we don bias properly, disorion can
More informationDynamic Difficulty Adjustment in a Whac-A-Mole like Game
Dynamic Difficuly Adjusmen in a Whac-A-Mole like Game Bruno E. R. Garcia and Marcio K. Crocomo Deparmen of Informaics IFSP - PRC Piracicaba, SP, Brazil brunoely.gc@gmail.com, marciokc@ifsp.edu.br Kleber
More informationDead Zone Compensation Method of H-Bridge Inverter Series Structure
nd Inernaional Conference on Elecrical, Auomaion and Mechanical Engineering (EAME 7) Dead Zone Compensaion Mehod of H-Bridge Inverer Series Srucure Wei Li Insiue of Elecrical Engineering and Informaion
More informationThe student will create simulations of vertical components of circular and harmonic motion on GX.
Learning Objecives Circular and Harmonic Moion (Verical Transformaions: Sine curve) Algebra ; Pre-Calculus Time required: 10 150 min. The sudens will apply combined verical ranslaions and dilaions in he
More informationEstimation of Automotive Target Trajectories by Kalman Filtering
Buleinul Şiinţific al Universiăţii "Poliehnica" din imişoara Seria ELECRONICĂ şi ELECOMUNICAŢII RANSACIONS on ELECRONICS and COMMUNICAIONS om 58(72), Fascicola 1, 2013 Esimaion of Auomoive arge rajecories
More informationA Novel Routing Algorithm for Power Line Communication over a Low-voltage Distribution Network in a Smart Grid
Energies 0, 6, 4-48; doi:0.90/en604 Aricle OPEN ACCESS energies ISSN 996-07 www.mdpi.com/journal/energies A Novel Rouing Algorihm for Power Line Communicaion over a Low-volage Disribuion Nework in a Smar
More informationEE368/CS232 Digital Image Processing Winter Homework #1 Released: Monday, January 8 Due: Wednesday, January 17, 1:30pm
EE368/CS232 Digial Image Processing Winer 207-208 Lecure Review and Quizzes (Due: Wednesday, January 7, :30pm) Please review wha you have learned in class and hen complee he online quiz quesions for he
More informationMAP-AIDED POSITIONING SYSTEM
Paper Code: F02I131 MAP-AIDED POSITIONING SYSTEM Forssell, Urban 1 Hall, Peer 1 Ahlqvis, Sefan 1 Gusafsson, Fredrik 2 1 NIRA Dynamics AB, Sweden; 2 Linköpings universie, Sweden Keywords Posiioning; Navigaion;
More informationNEURAL NETWORK APPROACH TO BAYESIAN BACKGROUND MODELING FOR VIDEO OBJECT SEGMENTATION
NEURAL NETWORK APPROACH TO BAYESIAN BACKGROUND MODELING FOR VIDEO OBJECT SEGMENTATION Dubravko Ćulibrk, Oge Marques, Daniel Socek, Hari Kalva and Borko Furh Deparmen of Compuer Science and Engineering
More informationShip Target Detection Algorithm for Maritime Surveillance Video Based on Gaussian Mixture Model
Journal of Physics: Conference Series PAPER OPEN ACCESS Ship Targe Deecion Algorihm for Mariime Surveillance Video Based on Gaussian Mixure Model To cie his aricle: Zuohuan Chen e al 08 J. Phys.: Conf.
More informationComparison of ATP Simulation and Microprocessor
Elecrical Engineering Research (EER), Volume 3, 15 Comparison of ATP Simulaion and Microprocessor Based Faul ocaion Using DFT H Nouri *1, F Jalili, T Boxshall 3 Power Sysems, Elecronics and Conrol Research
More informationOpen Access Analysis of Monitoring System Reliability for Wind Turbine Based on Wireless Sensor Network
Send Orders for Reprins o reprins@benhamscience.ae 21 The Open Auomaion and Conrol Sysems Journal, 214, 6, 21-217 Open Access Analysis of Monioring Sysem Reliabiliy for Wind Turbine Based on Wireless Sensor
More informationBOUNCER CIRCUIT FOR A 120 MW/370 KV SOLID STATE MODULATOR
BOUNCER CIRCUIT FOR A 120 MW/370 KV SOLID STATE MODULATOR D. Gerber, J. Biela Laboraory for High Power Elecronic Sysems ETH Zurich, Physiksrasse 3, CH-8092 Zurich, Swizerland Email: gerberdo@ehz.ch This
More informationAnnouncement. Allowed
9//05 nnouncemen Firs es: Sep. 8, Chap. -4 llowed wriing insrumen poce calculaor ruler One 8.5" " paper conaining consans, formulas, and any oher informaion ha you migh find useful (NOT any inds of soluions).
More informationSurveillance System with Object-Aware Video Transcoder
MITSUBISHI ELECTRIC RESEARCH LABORATORIES hp://www.merl.com Surveillance Sysem wih Objec-Aware Video Transcoder Toshihiko Haa, Naoki Kuwahara, Toshiharu Nozawa, Derek Schwenke, Anhony Vero TR2005-115 April
More informationA Smart Sensor with Hyperspectral/Range Fovea and Panoramic Peripheral View
A Smar Sensor wih Hyperspecral/Range Fovea and Panoramic Peripheral View Tao Wang,2, Zhigang Zhu,2 and Harvey Rhody 3 Deparmen of Compuer Science, The Ciy College of New York 38 h Sree and Conven Avenue,
More informationEE 40 Final Project Basic Circuit
EE 0 Spring 2006 Final Projec EE 0 Final Projec Basic Circui Par I: General insrucion 1. The final projec will coun 0% of he lab grading, since i s going o ake lab sessions. All oher individual labs will
More informationOptimization of Overcurrent Relay Operation with Genetic Algorithm
Opimizaion of Overcurren Relay Operaion wih Geneic Algorihm Arulnahan Gynasegaran College of Engineering, Universiy Tenaga Nasional, Malaysia, Email: ArulnahanGyna@gmail.com Aidil Azwin bin Zainul Abidin
More information(This lesson plan assumes the students are using an air-powered rocket as described in the Materials section.)
The Mah Projecs Journal Page 1 PROJECT MISSION o MArs inroducion Many sae mah sandards and mos curricula involving quadraic equaions require sudens o solve "falling objec" or "projecile" problems, which
More informationDetailing a Quantitative Method for Assessing Algorithms to Remove Back-to-Front Interference in Documents
Journal of Universal Compuer Science, vol. 14, no. 2 (2008), 266-283 submied: 15/6/06, acceped: 17/11/07, appeared: 28/1/08 J.UCS Deailing a Quaniaive Mehod for Assessing Algorihms o Remove Back-o-Fron
More informationDimensions. Model Number. Electrical connection emitter. Features. Electrical connection receiver. Product information. Indicators/operating means
OBE-R-SE Dimensions.8.8 ø..75 7.5 6. 5 6.7 4.9 4. 5.9 ø.6 Model Number OBE-R-SE Elecrical connecion emier Thru-beam sensor wih m fixed cable Feaures 45 cable oule for maximum mouning freedom under exremely
More informationThe Relationship Between Creation and Innovation
The Relaionship Beween Creaion and DONG Zhenyu, ZHAO Jingsong Inner Mongolia Universiy of Science and Technology, Baoou, Inner Mongolia, P.R.China, 014010 Absrac:Based on he compleion of Difference and
More informationIncreasing multi-trackers robustness with a segmentation algorithm
Increasing muli-rackers robusness wih a segmenaion algorihm MARTA MARRÓN, MIGUEL ÁNGEL SOTELO, JUAN CARLOS GARCÍA Elecronics Deparmen Universiy of Alcala Campus Universiario. 28871, Alcalá de Henares.
More informationA new method for classification and characterization of voltage sags
Elecric Power Sysems Research 58 (2001) 27 35 www.elsevier.com/locae/epsr A new mehod for classificaion and characerizaion of volage sags Mladen Kezunovic *, Yuan Liao Deparmen of Elecrical Engineering,
More informationTeacher Supplement to Operation Comics, Issue #5
eacher Supplemen o Operaion Comics, Issue #5 he purpose of his supplemen is o provide conen suppor for he mahemaics embedded ino he fifh issue of Operaion Comics, and o show how he mahemaics addresses
More informationLECTURE 1 CMOS PHASE LOCKED LOOPS
Lecure 01 (8/9/18) Page 1-1 Objecive LECTURE 1 CMOS PHASE LOCKED LOOPS OVERVIEW Undersand he principles and applicaions of phase locked loops using inegraed circui echnology wih emphasis on CMOS echnology.
More informationChapter 2 Summary: Continuous-Wave Modulation. Belkacem Derras
ECEN 44 Communicaion Theory Chaper Summary: Coninuous-Wave Modulaion.1 Modulaion Modulaion is a process in which a parameer of a carrier waveform is varied in accordance wih a given message (baseband)
More informationGaN-HEMT Dynamic ON-state Resistance characterisation and Modelling
GaN-HEMT Dynamic ON-sae Resisance characerisaion and Modelling Ke Li, Paul Evans, Mark Johnson Power Elecronics, Machine and Conrol group Universiy of Noingham, UK Email: ke.li@noingham.ac.uk, paul.evans@noingham.ac.uk,
More informationQ-learning Based Adaptive Zone Partition for Load Balancing in Multi-Sink Wireless Sensor Networks
Q-learning Based Adapive Zone Pariion for Load Balancing in Muli-Sink Wireless Sensor Neworks Sheng-Tzong Cheng and Tun-Yu Chang Deparmen of Compuer Science and Informaion Engineering, Naional Cheng Kung
More informationA Complexity Reliability Model
20h Inernaional Symposium on Sofware Reliabiliy Engineering A Complexiy Reliabiliy Model orm Schneidewind 1 and Mike Hinchey 2 1 aval Posgraduae School, Monerey, CA, USA 2 Lero he Irish Sofware Engineering
More informationMarch 13, 2009 CHAPTER 3: PARTIAL DERIVATIVES AND DIFFERENTIATION
March 13, 2009 CHAPTER 3: PARTIAL DERIVATIVES AND DIFFERENTIATION 1. Parial Derivaives and Differeniable funcions In all his chaper, D will denoe an open subse of R n. Definiion 1.1. Consider a funcion
More information