Application of Decision Tree and Support Vector Machine for Inspecting Bubble Defects on LED Sealing Glue Images

Size: px
Start display at page:

Download "Application of Decision Tree and Support Vector Machine for Inspecting Bubble Defects on LED Sealing Glue Images"

Transcription

1 66 Applicatio of Decisio Tree ad Support Vector Machie for Ispectig Bubble Defects o LED Sealig Glue Images * Chua-Yu Chag ad Yi-Feg Li Abstract Bubble defect ispectio is a importat step i light-emittig diode (LED) packagig processes. It is difficult to detect bubble defects because bubbles are trasparet ad have irregular shapes i LED sealig glue images. Traditioally, experieced egieers visually check defect regios ad exclude defective elemets. However, the ispectio processes are costly ad time-cosumig. This paper proposes a automatic bubble defect ispectio method for LED sealig glue images. The system automatic locates the sealig glue regio. A decisio tree is adopted to outlie regios of iterest (ROI), ad may textural ad geometric features are extracted from the ROIs. A support-vector-machie (SVM) is used to classify the ROIs as acceptable or defective. Experimetal results demostrate effectiveess of the proposed approach. Keywords: light-emittig diode, defect ispectio, decisio tree, support-vector-machie 1. Itroductio Sice the ivetio of the lightig equipmet, lightig has become a idispesable product. LED is a semicoductor device that emits visible light. Compared with traditioal illumiatig devices, the features of LED have smaller volume, lower power requiremets, higher efficiecy, ad a loger lifetime. Figure 1 shows a LED product ad its compoet structure. There are may types of defects i the silicoe ecapsulat, such as short shot, flash, damage, ad bubble. However, ispectig LED surface defects by huma eyes is iefficiet. I idustrial maufacturig, most defects ca be detected by usig the automatic detectio system. There have bee may methods proposed for defect ispectio [1-4]. Li et al. applied a wavelet-based algorithm for the ispectio of multicrystallie solar images [1]. They used the wavelet coefficiets to distiguish local defects ad also to ehace the discrimiat features usig the wavelet s eergy differeces i two cosecutive decompositio levels. Liu et al. proposed a defect detectio method based o two-dimesioal discrete wavelet trasformatio []. The defects were detected by comparative recostructed stadard images ad test images. This method aligmet ad structure affect the results. I additio, a icorrect stadard wafer image may result i ispectio mistakes. Li et al. proposed a level-set method for LED wafer ispectio [3]. They utilized the zero-level cotours for segmetig wafers. Defects were detected by textural ad geometric features. However, they are rather complex ad time-cosumig processes. Chiou applied the decisio tree to select a proper image segmetatio method for detectig defects [4]. However, the proposed detectio method is oly suitable i a simple image. *Correspodig Author: Chua-Yu Chag ( chuayu@yutech.edu.tw) 1 Departmet of Computer Sciece ad Iformatio Egieerig, atioal Yuli Uiversity of Sciece ad Techology, 13, Sec.3, Uiversity Rd., Douliou, Yuli, 640, Taiwa

2 67. Bubble Defect Ispectio Figure shows the flowchart of the proposed method. There are four major steps i the proposed method. Details are described as follows: LED Sealig Glue Images Preprocessig Image Segmetatio (Silicoe area) Figure 1: LED product ad Basic LED structure. Most methods are based o the aalysis of the differeces of textural ad geometric features. Sice LED sealig glue images have a large area to be ispected, a system requires a log time to calculate the textural features for each pixel. However, it is difficult to detect the limpid ad icostat bubble defects. Therefore, this paper develops a method to detect bubble defects by geometric features i LED sealig glue images. Sice the LED silicoe regio is a smooth surface, it is importat to build a sigle ad uiform light source capture eviromet to reduce oises. Before applyig the algorithm, first, the silicoe ecapsulat was segmeted, which is a trasparet layer o the LED structure. ext, decisio tree is applied to aalyze bubble, edge ad backgroud regio to obtai the potetial defect regios. The features of potetial defect regios were extracted, ad the these features are classified by the SVM. Fially, the positios of the bubble are represeted. This paper is orgaized as follows: I Sectio, the approach for LED bubble defect ispectio is described, icludig preprocessig, ROI extractio, feature extractio, ad classificatio. Sectio 3 demostrates the experimetal results. Fially, coclusios are give i Sectio 4. Potetial Defect Detectio Feature Extractio Classificatio Result Figure : The flowchart of the proposed method.1 Preprocessig As show i Figure 1, a LED sealig glue image cosists of three compoets: the backgroud, the outer package regio ad the silicoe regio. Sice bubble defects occur oly i the silicoe regio, the purpose of the preprocessig is to segmet the silicoe regio. The brightess of a LED sealig glue image ca be divided ito two parts. The darker area is backgroud; ad the lighter area is LED. Therefore, Otsu s method is used to separate the LED sealig glue images ito backgroud ad LED regios [5]. Otsu s method is capable of fidig a optimal threshold value from the distributio of a image. The algorithm fids a optimal threshold value to divide a LED sealig glue image ito two groups, while the sum of variaces of the two groups is the miimum. The optimal threshold is defied as the weighted sum of variaces of the two groups: t opt arg mi w1 ( t) 1( t) w ( t) ( t) (1) t

3 68 where w 1 ad w are the probabilities of the two groups separated by t; σ 1 ad σ are the stadard deviatios of the two groups; t [0,L], ad L is the image level. Figure 3 shows a origial LED image. Figure 3 is the thresholdig result by Otsu s method. Sice the white regios i the segmeted LED image are ot coected to the backgroud regio, it is easy to extract the complete backgroud regio by meas of coected-compoet labelig. Figure 3(c) shows the segmeted backgroud regio. Based o the segmeted LED regio, we ca obtai the cetroid of LED. Ad the extract the outer package regio. The outer package regio is a dout-like circle with radius from 10 to 160 pixels. Figure 3(d) shows the cetroid of the LED ad the outer package regio. Ada _ Th( x, m / m / im / jm / f ( x i, y j) m m t () where f(x, is the gray itesity of pixel (x,. If the pixel itesity is lower tha the threshold value, the it is set to 0, otherwise it is set to 1; that is: 1, f ( x, Ada _ Th( x, Out ( x, (3) 0, f ( x, Ada _ Th( x, Figure 4 shows the segmeted regios by adaptive thresholdig. I order to obtai completely segmetatio results, a morphological closig operatio with a 9 9 structurig elemet is applied. The the resultig image is coverted egatively as show i Figure 4. Figure 4(c) shows the outer package regio ad parts of the silicoe regio. The two regios are ot coected. Figure 4(d) is the egative of Figure 4(c), ad it excludes the backgroud regio. A complete silicoe regio is obtaied by removig the o-silicoe regio ad fillig holes. Figures 4(e) ad 4(f) show the detected silicoe regio ad the silicoe regio i the origial image. (c) (d) Figure 3: Backgroud segmetatio: the origial image; result of Otsu s method; (c) detected backgroud, ad (d) LED cetroid ad outlied outer package regio. (c) Sice the silicoe regio caot be determied by a threshold value, the adaptive thresholdig method is adopted to segmet silicoe regio. The adaptive thresholdig method ca suppress the ifluece of illumiatio [6]. The adaptive threshold value is computed as: (d) (e) (f) Figure 4: Adaptive thresholdig result the egative of ; (c) outer package regios; (d) the egative of (c); (e) the silicoe regio, ad (f) the silicoe regio i origial image.

4 69. Subjective Characteristics of Elderly Speech The bubble defects are circular ad trasparet with differet sizes. Accordig to the property of bubbles, we ca use the decisio tree to classify them ito three classes: 1) edge, ) iterior of bubble ad 3) backgroud. A decisio tree is a method to represet iformatio by a machie learig algorithm [7]. All the traiig patters are outlied maually by experieced egieers. Four features are the extracted by usig a slidig widow from each traiig patter: 1). M(x, : the mea of pixel itesity i the widow. ). Std(x, : the stadard deviatio of pixel itesity i the widow. 3). R(x, : the raked positio of the ceter pixel i the widow. 4). FR(x, : the red compoet of the ceter pixel i the widow. I the traiig phase, each class selected 900 patters for traiig ad 300 patters for testig. After the traiig process, the decisio tree model was obtaied as show i Figure 5. Figure 6 shows the classificatio results of Figure 4(f) by decisio tree. Figure 5: Result of decisio tree (c) Figure 6: Classificatio of the silicoe regio: the edge regios; the iterior of bubble regios ad (c) the LED backgroud regios. By observig the iterior of bubbles, we could exclude o-bubble defect regios. The miimum boudig rectagle (MBR) is the smallest rectagle which ecloses potetial defect regios completely. Yag proposed a fast calculatio of a miimum area exterior rectagle method [8]. The method is used to determie the spidle, which is the iertia accordig to the rotary iertia of a object. MBR ca be obtaied by usig image rotatio with the edge ad spidle of the object. Therefore, we elimiated the regios i which the MBR aspect ratio is greater tha.5, ad the legth of a loger side is greater tha 55 pixels.

5 70 Figure 7 shows the locatios of potetial defects, which had excluded o-bubble defect regio. Therefore, the potetial defect regios extracted correspod to these iteral of bubble regios, as the gree rectagles show i Figure 7. The potetial defect regios will be processed i ext step. Sice bubble defects are cocetrated i a small rage of the vertical projectio. A factor P is calculated to evaluate the cocetratio of the vertical projectio P R i1 50 ( P V(i) P V(i) ) r (7) I geeral, the bubble defects have small value of P. Figure 7: Potetial defects ad potetial defect regios (a1).3 Feature Extractio The purpose of feature extractio is to obtai features to discrimiate betwee defects ad o-defects. I order to ehace performace of the idetificatio, the potetial defect regios are trasformed to the polar coordiate system. The polar coordiates (r, θ) ca be calculated from the Cartesia coordiates by: r (Yp Y ) 1 o (X p X o ) (Yp Yo ), θ ta (4) (X X ) where (X o, Y o ) is the origi, (X p, Y p ) is the positio i the Cartesia coordiates. Figures 8 -(d) show the trasformatio results. The horizotal axis is the agle [0, π], ad the vertical axis is the radius distace. Obviously, the bubble defects ad ormal regios i a polar coordiates system are differet.. I geeral, bubble defects have a similar appearace. Let P H ad P V deote the horizotal projectio ratio ad vertical projectio ratio, respectively. The P H ad P V are defied as 1 P H ( ) R r i1 B( i, ) p,for 0,1,..,359 (5) o (b1) (c1) (d1) (c) (d) Figure 8: (a1)-(d1) Potetial defect regios, ad -(d) Potetial defect regios at the polar coordiate..4 Ispectio Algorithm The similarity measuremet was applied to compare the feature of horizotal projectio ratio betwee two histograms. Three similarity measuremets described below are calculated. Chi-square distace, d (H,H ) C i0 Bhattacharyya distace, d (H,H ) B (H(i) H (i)) H(i) H (i) i0 1 (8) 1 (H(i) H(i)) (9) 1 PV ( i) 359 r 0 B( i, ),for i 1,..., R (6) where B i, is the itesity at the polar coordiate i,, R is the legth of radius, ad r is the umber of o-zero value i the trasformed image B. Itersectio ratio, d (H,H ) I i0 Mi(H(i),H (i)) (10)

6 71 where H ad H deote the horizotal projectio histogram of bubble template ad potetial defect regio, respectively. The three distaces ad factor P are aggregated as a feature vector as v [ d, d, d, P] (11) C B I The SVM has bee widely used i may patter recogitio problems [9,10]. It fids a hyperplae to classify patters ito two classes. Assume that a set of vectors D belogs to two separable classes, D {( v1, d1),( v, d ),...,( v, d )}, di { 1, 1} (1) The hyperplae ca be represeted as l v vi g( v ) sg idi exp b (13) i1 where is the weight parameter, i v is support i vector, l is the umber of support vectors, σ is badwidth ad b is a bias. I the traiig phase, 60 traiig patters, icludig 30 defect patters ad 30 o-defect patters, are selected. The o-defect patters were selected from potetial defect regios. Ad the best model was selected by two-fold cross-validatio. After the traiig phase, the SVM model ca be obtaied ad processed. Figure 9 shows the structure of the SVM classifier for bubble defects classificatio. SVM 3. Experimetal Results The proposed method was implemeted by Microsoft Visual Studio 008 C# o a Itel Core i7 3.4GHz processor with 4GB RAMs. There are two LED sealig glue image databases captured from differet light sources (white ad red) with the same LEDs. Each database cotais 10 LED images icludig 75 images with bubble defects ad 45 images without bubble defect. Figure 10 shows examples of the two databases. The average ispectio time of the proposed method was 1.s per image. Three experimets were coducted i this paper. 3.1 Potetial Defect Detectio Uder Various Widow Sizes I the proposed method, potetial defect regios were detected by decisio tree. To fid the best settig for widow size, four sizes of widow (3 3, 5 5, 7 7 ad 9 9) were used for feature extractio. I this experimet, there exist 148 bubble defects i the 5 LED sealig glue images. Table 1 presets the experimetal results uder differet widow sizes. The result shows that the widow with size of 7 7 ca detect the most bubble defects. Four bubble defects were missed. These udetected bubble defects are usually blurred ad isigificat with sizes less tha pixels. Therefore, the widow with a size of 7 7 was selected i the subsequet experimets o-defect Defect Figure 9: The structure of the SVM classifier.

7 7 Specificit y t tp t Accuracy p (15) (16) (c) (d) Figure 10: Example of LED sealig glue images: ormal LED image captured from red light source; Defective LED image captured from red light source; (c) ormal LED captured from white light source, ad (d) Defective LED image captured from white light source. Table 1: Potetial defect detectio result Widow size # of potetial bubble defects # of udetected bubble defects Bubble Defect Detectio I order to evaluate the performace of the proposed method, the sesitivity, specificity ad accuracy were calculated. Assume p is the actual umber of bubble defects. The is the actual umber of ormal regios. tp is the umber of actual defective regios that the system detects. Ad the t is the umber of actual ormal regios that the system detects. The sesitivity, specificity ad accuracy are defied as follows. tp Sesitivit y (14) p 80 LED images captured from white ad red light sources were used for testig. Table shows the bubble defect detectio results uder differet lightig sources. The system detects more potetial defect regios from the LED images captured from white light source. This factor causes the experimet to have high false positives ad take loger time to detect defects. Table 3 presets the performace. These values demostrate that the proposed method ca detect bubble defects with high sesitivity. The result shows that the whole classificatio accuracy i red light is better tha that i white light. Figure 11 shows the bubble defect detectio results. Bubbles are outlied by rectagles, ad the gree rectagles outlie the real bubbles; the blue rectagles are over detected defects. These false positive regios are usually located o the edge or shadow regios, as the blue rectagles show i Figure 11. Figure 11 shows the results are more robust ad accurate with red light sources. Table : Cofusio matrix of bubble defect detectio. Predicted Actual Defect ormal Red light source Defect ormal White light source Defect 1 18 ormal Table 3: Performace of defect detectio. Light source Sesitivity Specificity Accuracy Red 90.00% 84.58% 84.7% White 87.14% 73.34% 73.55%

8 Compared with other methods I the image, the bubble ca extract shape features for idetificatio. Sice images use differet segmetatio methods to segmet the bubble, the results of segmetatio image are ot the same. That could affect the efficiecy of the idetificatio results. This experimet used differet segmetatio algorithms to compare defect ispectio. The popular edge detectors icludig Sobel ad Cay edge detectors ad Otsu s method were selected for compariso with the proposed approach. Table 4 shows the performace compariso of four segmetatio methods. There are 140 bubble defects ad 4630 ormal regios which are the potetial defect regios i 40 LED sealig glue images. I the proposed method, the sesitivity ad specificity is 0.9 ad 0.85, respectively. Although Cay s method has a higher accuracy, its sesitivity is less tha the proposed method, which meas Cay s method caot detect bubble defects accurately. As show i Table 4, these values demostrate that the effectiveess of the proposed method ca efficietly ispect the bubble defects i the LED sealig glue images. Figure 11: the detected bubble defects from the white light source, ad the detected bubble defects from the red light source. Table 4: Performace compariso of the four segmetatio methods. Propose Cay Sobel Otsu d Defect regio Defect ormal ormal regio Defect ormal Sesitivity Specificity Accuracy Coclusios LED ca be produced quickly with automatic maufacturig systems. Automatic visual defect ispectio plays a importat role with the beefits of low-cost ad high accuracy. This paper proposed a bubble defects detectio scheme for LED sealig glue images. The silicoe regio was extracted so that the regio eeded to be ispected was reduced, ad thus the defect regios were determied. The positios of potetial bubble defects ca be obtaied by usig decisio tree. The SVM is applied to classify the potetial defects ito defect ad o-defect. The experimetal data show that LED sealig glue image i red light source has higher accuracy tha i white source. The results show that the proposed method is effective to detect bubble defects o LED sealig glue images.

9 74 Ackowledgmets This work was supported by the atioal Sciece Coucil Taiwa, R.O.C, uder the grats SC E Refereces [1]. W.-C. Li, D.-M. Tsai, Wavelet-based defect detectio i solar wafer images with ihomogeeous texture, Patter Recogitio, vol. 45, pp , 011. []. H. Liu, W. Zhou, Q. Kuag, L. Cao, B. Gao, Defect detectio of IC wafer based o two-dimesio wavelet trasform, Microelectroics Joural, vol. 41, pp , 010. [3]. C.-H. Li, C.-Y. Chag, M.-D. Jeg, Applyig regioal level-set formulatio to post-sawig four-elemet LED wafer ispectio, IEEE Trasactios o Systems, Ma, ad Cyberetics--Part C: Applicatios ad Reviews, vol. 41, o. 6, pp , ov [4]. Y.-C. Chiou, Itelliget segmetatio method for real-time defect ispectio system, Computers i Idustry, vol. 61, o. 7, pp , 010. [5].. Otsu, A threshold selectio method from gray-level histograms, IEEE Trasactios o Systems, Ma ad Cyberetics, vol. 9, o. 1, pp. 6 66, Ja [6]. D. Bradley ad G. Roth, Adaptive thresholdig usig the itegral image, Joural of Graphics Tools, vol. 1, o., pp. 13-1, 007. [7]. Quila, J. R., C4.5: Programs for Machie Learig, Morga Kaufma Publishers, [8]. C. Yag, R. Lu,. Che, A fast method for large aperture optical elemets surface defects detectio, Advaces i MSEC, Vol., pp , 011. [9]. C. C. Chag ad C. J. Li, LIBSVM: a library for support vector machies, 001. Available: [10]. C. Cortes ad V. Vapik, Support-vector etwork, Machie Learig, Vol. 0, pp , Chua-Yu Chag received the Ph.D. degree i electrical egieerig from atioal Cheg Kug Uiversity, Taia, Taiwa, i 000. He is curretly a Distiguished Professor ad Dea of Research & Developmet, atioal Yuli Uiversity of Sciece ad Techology, Taiwa. He is the chair of IEEE Sigal Processig Society Taia Chapter, ad a Associate Editor of the Iteratioal Joural of Cotrol Theory ad Applicatios. His curret research iterests iclude eural etworks ad their applicatio to medical image processig, wafer defect ispectio, digital watermarkig, ad patter recogitio. I the above areas, he has more tha 150 publicatios i jourals ad coferece proceedigs. He was a member of the orgaizatio ad program committees for more tha 50 times, orgaized ad chaired for more tha 30 techical sessios for may iteratioal cofereces. He is a Life Member of IPPR ad the Taiwaese Associatio for Artificial Itelligece (TAAI), seior Member of IEEE, ad is listed i Who s Who i the World, Who s Who i Sciece ad Egieerig, Who s Who i Asia, ad Who s Who of Emergig Leaders. Yi-Feg Li received the B.S. ad M.S. degree i 009 ad 01, respectively, from the Departmet of Computer Sciece ad Iformatio Egieerig, atioal Yuli Uiversity, Yuli, Taiwa. His research iterests iclude eural etworks, digital image processig ad their applicatios.

RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE

RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE Z.G. Zhou, S. Zhao, ad Z.G. A School of Mechaical Egieerig ad Automatio, Beijig Uiversity of Aeroautics ad Astroautics,

More information

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process Vol.133 (Iformatio Techology ad Computer Sciece 016), pp.85-89 http://dx.doi.org/10.1457/astl.016. Euclidea Distace Based Feature Selectio for Fault Detectio Predictio Model i Semicoductor Maufacturig

More information

A New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method

A New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method A ew Morphological 3D Shape Decompositio: Grayscale Iterframe Iterpolatio Method D.. Vizireau Politehica Uiversity Bucharest, Romaia ae@comm.pub.ro R. M. Udrea Politehica Uiversity Bucharest, Romaia mihea@comm.pub.ro

More information

A Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System

A Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System A Novel Feature Extractio Algorithm for Haar Local Biary Patter Texture Based o Huma Visio System Liu Tao 1,* 1 Departmet of Electroic Egieerig Shaaxi Eergy Istitute Xiayag, Shaaxi, Chia Abstract The locality

More information

Harris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c

Harris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c Iteratioal Coferece o Computatioal Sciece ad Egieerig (ICCSE 015) Harris Corer Detectio Algorithm at Sub-pixel Level ad Its Applicatio Yuafeg Ha a, Peijiag Che b * ad Tia Meg c School of Automobile, Liyi

More information

Image Segmentation EEE 508

Image Segmentation EEE 508 Image Segmetatio Objective: to determie (etract) object boudaries. It is a process of partitioig a image ito distict regios by groupig together eighborig piels based o some predefied similarity criterio.

More information

Auto-recognition Method for Pointer-type Meter Based on Binocular Vision

Auto-recognition Method for Pointer-type Meter Based on Binocular Vision JOURNAL OF COMPUTERS, VOL. 9, NO. 4, APRIL 204 787 Auto-recogitio Method for Poiter-type Meter Based o Biocular Visio Biao Yag School of Istrumet Sciece ad Egieerig, Southeast Uiversity, Najig 20096, Chia

More information

3D Model Retrieval Method Based on Sample Prediction

3D Model Retrieval Method Based on Sample Prediction 20 Iteratioal Coferece o Computer Commuicatio ad Maagemet Proc.of CSIT vol.5 (20) (20) IACSIT Press, Sigapore 3D Model Retrieval Method Based o Sample Predictio Qigche Zhag, Ya Tag* School of Computer

More information

Pattern Recognition Systems Lab 1 Least Mean Squares

Pattern Recognition Systems Lab 1 Least Mean Squares Patter Recogitio Systems Lab 1 Least Mea Squares 1. Objectives This laboratory work itroduces the OpeCV-based framework used throughout the course. I this assigmet a lie is fitted to a set of poits usig

More information

Stone Images Retrieval Based on Color Histogram

Stone Images Retrieval Based on Color Histogram Stoe Images Retrieval Based o Color Histogram Qiag Zhao, Jie Yag, Jigyi Yag, Hogxig Liu School of Iformatio Egieerig, Wuha Uiversity of Techology Wuha, Chia Abstract Stoe images color features are chose

More information

New HSL Distance Based Colour Clustering Algorithm

New HSL Distance Based Colour Clustering Algorithm The 4th Midwest Artificial Itelligece ad Cogitive Scieces Coferece (MAICS 03 pp 85-9 New Albay Idiaa USA April 3-4 03 New HSL Distace Based Colour Clusterig Algorithm Vasile Patrascu Departemet of Iformatics

More information

Mobile terminal 3D image reconstruction program development based on Android Lin Qinhua

Mobile terminal 3D image reconstruction program development based on Android Lin Qinhua Iteratioal Coferece o Automatio, Mechaical Cotrol ad Computatioal Egieerig (AMCCE 05) Mobile termial 3D image recostructio program developmet based o Adroid Li Qihua Sichua Iformatio Techology College

More information

An Image Retrieval Method Based on Hu Invariant Moment and Improved Annular Histogram

An Image Retrieval Method Based on Hu Invariant Moment and Improved Annular Histogram http://dx.doi.org/10.5755/j01.eee.0.4.6888 ELEKTROIKA IR ELEKTROTECHIKA ISS 139 115 VOL. 0 O. 4 014 A Image Retrieval Method Based o Hu Ivariat Momet ad Improved Aular Histogram F. Xiag 1 H. Yog 1 S. Dada

More information

Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1

Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1 Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces

More information

Optimization for framework design of new product introduction management system Ma Ying, Wu Hongcui

Optimization for framework design of new product introduction management system Ma Ying, Wu Hongcui 2d Iteratioal Coferece o Electrical, Computer Egieerig ad Electroics (ICECEE 2015) Optimizatio for framework desig of ew product itroductio maagemet system Ma Yig, Wu Hogcui Tiaji Electroic Iformatio Vocatioal

More information

Accuracy Improvement in Camera Calibration

Accuracy Improvement in Camera Calibration Accuracy Improvemet i Camera Calibratio FaJie L Qi Zag ad Reihard Klette CITR, Computer Sciece Departmet The Uiversity of Aucklad Tamaki Campus, Aucklad, New Zealad fli006, qza001@ec.aucklad.ac.z r.klette@aucklad.ac.z

More information

Performance Plus Software Parameter Definitions

Performance Plus Software Parameter Definitions Performace Plus+ Software Parameter Defiitios/ Performace Plus Software Parameter Defiitios Chapma Techical Note-TG-5 paramete.doc ev-0-03 Performace Plus+ Software Parameter Defiitios/2 Backgroud ad Defiitios

More information

Eigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1

Eigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1 Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces

More information

CHAPTER 3 A STUDY ON BREAST ABNORMALITY DETECTION

CHAPTER 3 A STUDY ON BREAST ABNORMALITY DETECTION 46 CHAPTER 3 A STUDY ON BREAST ABNORMALITY DETECTION 3.1 INTRODUCTION A Computer-Aided Detectio (CAD) system is used to aid radiologists i detectig mammographic lesios that may idicate the presece of breast

More information

Fast algorithm for skew detection. Adnan Amin, Stephen Fischer, Tony Parkinson, and Ricky Shiu

Fast algorithm for skew detection. Adnan Amin, Stephen Fischer, Tony Parkinson, and Ricky Shiu Fast algorithm for skew detectio Ada Ami, Stephe Fischer, Toy Parkiso, ad Ricky Shiu School of Computer Sciece ad Egieerig Uiversity of New South Wales, Sydey NSW, 2052 Australia ABSTRACT Documet image

More information

Lip Contour Extraction Based on Support Vector Machine

Lip Contour Extraction Based on Support Vector Machine Lip Cotour Extractio Based o Support Vector Machie Author Pa, Xiaosheg, Kog, Jiagpig, Liew, Ala Wee-Chug Published 008 Coferece Title CISP 008 : Proceedigs, First Iteratioal Cogress o Image ad Sigal Processig

More information

Dynamic Programming and Curve Fitting Based Road Boundary Detection

Dynamic Programming and Curve Fitting Based Road Boundary Detection Dyamic Programmig ad Curve Fittig Based Road Boudary Detectio SHYAM PRASAD ADHIKARI, HYONGSUK KIM, Divisio of Electroics ad Iformatio Egieerig Chobuk Natioal Uiversity 664-4 Ga Deokji-Dog Jeoju-City Jeobuk

More information

Text Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree

Text Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree Available olie at www.ijpe-olie.com vol. 13, o. 7, November 017, pp. 1159-1164 DOI: 10.3940/ijpe.17.07.p19.11591164 Text Feature Selectio based o Feature Dispersio Degree ad Feature Cocetratio Degree Zhifeg

More information

Neuro Fuzzy Model for Human Face Expression Recognition

Neuro Fuzzy Model for Human Face Expression Recognition IOSR Joural of Computer Egieerig (IOSRJCE) ISSN : 2278-0661 Volume 1, Issue 2 (May-Jue 2012), PP 01-06 Neuro Fuzzy Model for Huma Face Expressio Recogitio Mr. Mayur S. Burage 1, Prof. S. V. Dhopte 2 1

More information

Improving Template Based Spike Detection

Improving Template Based Spike Detection Improvig Template Based Spike Detectio Kirk Smith, Member - IEEE Portlad State Uiversity petra@ee.pdx.edu Abstract Template matchig algorithms like SSE, Covolutio ad Maximum Likelihood are well kow for

More information

Text Line Segmentation Based on Morphology and Histogram Projection

Text Line Segmentation Based on Morphology and Histogram Projection 2009 10th Iteratioal Coferece o Documet Aalsis ad Recogitio Tet Lie Segmetatio Based o Morpholog ad Histogram Projectio Rodolfo P. dos Satos, Gabriela S. Clemete, Tsag Ig Re ad George D.C. Calvalcati Ceter

More information

x x 2 x Iput layer = quatity of classificatio mode X T = traspositio matrix The core of such coditioal probability estimatig method is calculatig the

x x 2 x Iput layer = quatity of classificatio mode X T = traspositio matrix The core of such coditioal probability estimatig method is calculatig the COMPARATIVE RESEARCHES ON PROBABILISTIC NEURAL NETWORKS AND MULTI-LAYER PERCEPTRON NETWORKS FOR REMOTE SENSING IMAGE SEGMENTATION Liu Gag a, b, * a School of Electroic Iformatio, Wuha Uiversity, 430079,

More information

New Fuzzy Color Clustering Algorithm Based on hsl Similarity

New Fuzzy Color Clustering Algorithm Based on hsl Similarity IFSA-EUSFLAT 009 New Fuzzy Color Clusterig Algorithm Based o hsl Similarity Vasile Ptracu Departmet of Iformatics Techology Tarom Compay Bucharest Romaia Email: patrascu.v@gmail.com Abstract I this paper

More information

Study on effective detection method for specific data of large database LI Jin-feng

Study on effective detection method for specific data of large database LI Jin-feng Iteratioal Coferece o Automatio, Mechaical Cotrol ad Computatioal Egieerig (AMCCE 205) Study o effective detectio method for specific data of large database LI Ji-feg (Vocatioal College of DogYig, Shadog

More information

Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme

Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme 828 Iteratioal Joural of Cotrol, Automatio, ad Systems, vol. 6, o. 6, pp. 828-835, December 2008 Efficiet Eye Locatio for Biomedical Imagig usig Two-level Classifier Scheme Mi Youg Nam, Xi Wag, ad Phill

More information

The identification of key quality characteristics based on FAHP

The identification of key quality characteristics based on FAHP Iteratioal Joural of Research i Egieerig ad Sciece (IJRES ISSN (Olie: 2320-9364, ISSN (Prit: 2320-9356 Volume 3 Issue 6 ǁ Jue 2015 ǁ PP.01-07 The idetificatio of ey quality characteristics based o FAHP

More information

Analysis of Server Resource Consumption of Meteorological Satellite Application System Based on Contour Curve

Analysis of Server Resource Consumption of Meteorological Satellite Application System Based on Contour Curve Advaces i Computer, Sigals ad Systems (2018) 2: 19-25 Clausius Scietific Press, Caada Aalysis of Server Resource Cosumptio of Meteorological Satellite Applicatio System Based o Cotour Curve Xiagag Zhao

More information

Fundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le

Fundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le Fudametals of Media Processig Shi'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dih Le Today's topics Noparametric Methods Parze Widow k-nearest Neighbor Estimatio Clusterig Techiques k-meas Agglomerative Hierarchical

More information

Low Complexity H.265/HEVC Coding Unit Size Decision for a Videoconferencing System

Low Complexity H.265/HEVC Coding Unit Size Decision for a Videoconferencing System BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 15, No 6 Special Issue o Logistics, Iformatics ad Service Sciece Sofia 2015 Prit ISSN: 1311-9702; Olie ISSN: 1314-4081 DOI:

More information

USING PHASE AND MAGNITUDE INFORMATION OF THE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION

USING PHASE AND MAGNITUDE INFORMATION OF THE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION 6th Europea Sigal Processig Coferece EUSIPCO 008, Lausae, Switzerlad, August 5-9, 008, copyright by EURASIP USING PASE AND MAGNITUDE INFORMATION OF TE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION

More information

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb Chapter 3 Descriptive Measures Measures of Ceter (Cetral Tedecy) These measures will tell us where is the ceter of our data or where most typical value of a data set lies Mode the value that occurs most

More information

Improvement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation

Improvement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation Improvemet of the Orthogoal Code Covolutio Capabilities Usig FPGA Implemetatio Naima Kaabouch, Member, IEEE, Apara Dhirde, Member, IEEE, Saleh Faruque, Member, IEEE Departmet of Electrical Egieerig, Uiversity

More information

Diego Nehab. n A Transformation For Extracting New Descriptors of Shape. n Locus of points equidistant from contour

Diego Nehab. n A Transformation For Extracting New Descriptors of Shape. n Locus of points equidistant from contour Diego Nehab A Trasformatio For Extractig New Descriptors of Shape Locus of poits equidistat from cotour Medial Axis Symmetric Axis Skeleto Shock Graph Shaked 96 1 Shape matchig Aimatio Dimesio reductio

More information

IMP: Superposer Integrated Morphometrics Package Superposition Tool

IMP: Superposer Integrated Morphometrics Package Superposition Tool IMP: Superposer Itegrated Morphometrics Package Superpositio Tool Programmig by: David Lieber ( 03) Caisius College 200 Mai St. Buffalo, NY 4208 Cocept by: H. David Sheets, Dept. of Physics, Caisius College

More information

ANN WHICH COVERS MLP AND RBF

ANN WHICH COVERS MLP AND RBF ANN WHICH COVERS MLP AND RBF Josef Boští, Jaromír Kual Faculty of Nuclear Scieces ad Physical Egieerig, CTU i Prague Departmet of Software Egieerig Abstract Two basic types of artificial eural etwors Multi

More information

Using a Dynamic Interval Type-2 Fuzzy Interpolation Method to Improve Modeless Robots Calibrations

Using a Dynamic Interval Type-2 Fuzzy Interpolation Method to Improve Modeless Robots Calibrations Joural of Cotrol Sciece ad Egieerig 3 (25) 9-7 doi:.7265/2328-223/25.3. D DAVID PUBLISHING Usig a Dyamic Iterval Type-2 Fuzzy Iterpolatio Method to Improve Modeless Robots Calibratios Yig Bai ad Dali Wag

More information

Automated Extraction of Urban Trees from Mobile LiDAR Point Clouds

Automated Extraction of Urban Trees from Mobile LiDAR Point Clouds Automated Extractio of Urba Trees from Mobile LiDAR Poit Clouds Fa W. a, Cheglu W. a*, ad Joatha L. ab a Fujia Key Laboratory of Sesig ad Computig for Smart City ad the School of Iformatio Sciece ad Egieerig,

More information

Designing a learning system

Designing a learning system CS 75 Machie Learig Lecture Desigig a learig system Milos Hauskrecht milos@cs.pitt.edu 539 Seott Square, x-5 people.cs.pitt.edu/~milos/courses/cs75/ Admiistrivia No homework assigmet this week Please try

More information

Vision & Perception. Simple model: simple reflectance/illumination model. image: x(n 1,n 2 )=i(n 1,n 2 )r(n 1,n 2 ) 0 < r(n 1,n 2 ) < 1

Vision & Perception. Simple model: simple reflectance/illumination model. image: x(n 1,n 2 )=i(n 1,n 2 )r(n 1,n 2 ) 0 < r(n 1,n 2 ) < 1 Visio & Perceptio Simple model: simple reflectace/illumiatio model Eye illumiatio source i( 1, 2 ) image: x( 1, 2 )=i( 1, 2 )r( 1, 2 ) reflectace term r( 1, 2 ) where 0 < i( 1, 2 ) < 0 < r( 1, 2 ) < 1

More information

Automatic Road Extraction from Satellite Image

Automatic Road Extraction from Satellite Image Automatic Road Extractio from Satellite Image B.Sowmya Dept. of Electroics & Cotrol Egg., Sathyabama Istitute of Sciece & Techology, Deemed Uiversity, Cheai bsowya@yahoo.com Abstract This paper explais

More information

Neural Networks A Model of Boolean Functions

Neural Networks A Model of Boolean Functions Neural Networks A Model of Boolea Fuctios Berd Steibach, Roma Kohut Freiberg Uiversity of Miig ad Techology Istitute of Computer Sciece D-09596 Freiberg, Germay e-mails: steib@iformatik.tu-freiberg.de

More information

Adaptive Resource Allocation for Electric Environmental Pollution through the Control Network

Adaptive Resource Allocation for Electric Environmental Pollution through the Control Network Available olie at www.sciecedirect.com Eergy Procedia 6 (202) 60 64 202 Iteratioal Coferece o Future Eergy, Eviromet, ad Materials Adaptive Resource Allocatio for Electric Evirometal Pollutio through the

More information

Road Boundary Detection in Complex Urban Environment based on Low- Resolution Vision

Road Boundary Detection in Complex Urban Environment based on Low- Resolution Vision Road Boudary Detectio i Complex Urba Eviromet based o Low- Resolutio Visio Qighua We, Zehog Yag, Yixu Sog, Peifa Jia State Key Laboratory o Itelliget Techology ad Systems, Tsighua Natioal Laboratory for

More information

Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment

Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment Turkish Figerspellig ecogitio System Usig Axis of Least Iertia Based Fast Aligmet Oğuz Altu, Sogül Albayrak, Ali Ekici, ad Behzat Bükü Yıldız Techical Uiversity, Computer Egieerig Departmet, Yıldız, İstabul,

More information

COMPLEMENTARY SIMILARITY MEASURE

COMPLEMENTARY SIMILARITY MEASURE IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 20, NO. 0, OCTOBER 998 03 Text-Lie Extractio ad Character Recogitio of Documet Headlies With Graphical Desigs Usig Complemetary Similarity

More information

The measurement of overhead conductor s sag with DLT method

The measurement of overhead conductor s sag with DLT method Advaces i Egieerig Research (AER), volume 7 2d Aual Iteratioal Coferece o Electroics, Electrical Egieerig ad Iformatio Sciece (EEEIS 206) he measuremet of overhead coductor s sag with DL method Fag Ye,

More information

Multiresolution Image Fusion Based on the Wavelet-based Contourlet Transform

Multiresolution Image Fusion Based on the Wavelet-based Contourlet Transform Multiresolutio Image Fusio Based o the Wavelet-based Cotourlet Trasform Lei Tag Istitute of utomated Commad PL Uiversit of Sciece ad Techolog Najig rm Commad College Najig, Chia tttaglei@gmail.com bstract

More information

Mining from Quantitative Data with Linguistic Minimum Supports and Confidences

Mining from Quantitative Data with Linguistic Minimum Supports and Confidences Miig from Quatitative Data with Liguistic Miimum Supports ad Cofideces Tzug-Pei Hog, Mig-Jer Chiag ad Shyue-Liag Wag Departmet of Electrical Egieerig Natioal Uiversity of Kaohsiug Kaohsiug, 8, Taiwa, R.O.C.

More information

An Efficient Image Rectification Method for Parallel Multi-Camera Arrangement

An Efficient Image Rectification Method for Parallel Multi-Camera Arrangement Y.-S. Kag ad Y.-S. Ho: A Efficiet Image Rectificatio Method for Parallel Multi-Camera Arragemet 141 A Efficiet Image Rectificatio Method for Parallel Multi-Camera Arragemet Yu-Suk Kag ad Yo-Sug Ho, Seior

More information

Empirical Validate C&K Suite for Predict Fault-Proneness of Object-Oriented Classes Developed Using Fuzzy Logic.

Empirical Validate C&K Suite for Predict Fault-Proneness of Object-Oriented Classes Developed Using Fuzzy Logic. Empirical Validate C&K Suite for Predict Fault-Proeess of Object-Orieted Classes Developed Usig Fuzzy Logic. Mohammad Amro 1, Moataz Ahmed 1, Kaaa Faisal 2 1 Iformatio ad Computer Sciece Departmet, Kig

More information

Criterion in selecting the clustering algorithm in Radial Basis Functional Link Nets

Criterion in selecting the clustering algorithm in Radial Basis Functional Link Nets WSEAS TRANSACTIONS o SYSTEMS Ag Sau Loog, Og Hog Choo, Low Heg Chi Criterio i selectig the clusterig algorithm i Radial Basis Fuctioal Lik Nets ANG SAU LOONG 1, ONG HONG CHOON 2 & LOW HENG CHIN 3 Departmet

More information

An improved support vector machine based on particle swarm optimization in laser ultrasonic defect detection

An improved support vector machine based on particle swarm optimization in laser ultrasonic defect detection A improved support vector machie based o particle swarm optimizatio i laser ultrasoic defect detectio School of Sciece, North Uiversity of Chia, aiyua, Shaxi 35, Chia xut98@63.com,hhp9@63.com,xywag@6.com,43497@qq.com

More information

Image based Cats and Possums Identification for Intelligent Trapping Systems

Image based Cats and Possums Identification for Intelligent Trapping Systems Volume 159 No, February 017 Image based Cats ad Possums Idetificatio for Itelliget Trappig Systems T. A. S. Achala Perera School of Egieerig Aucklad Uiversity of Techology New Zealad Joh Collis School

More information

Masking based Segmentation of Diseased MRI Images

Masking based Segmentation of Diseased MRI Images Maskig based Segmetatio of Diseased MRI Images Aruava De Dept. of Electroics ad Commuicatio Egg. Dr. B.C. Roy Egg College Durgapur,Idia aruavade@yahoo.com Raib Locha Das Dept. Of Electroics ad Commuicatio

More information

ISSN (Print) Research Article. *Corresponding author Nengfa Hu

ISSN (Print) Research Article. *Corresponding author Nengfa Hu Scholars Joural of Egieerig ad Techology (SJET) Sch. J. Eg. Tech., 2016; 4(5):249-253 Scholars Academic ad Scietific Publisher (A Iteratioal Publisher for Academic ad Scietific Resources) www.saspublisher.com

More information

Hand Gesture Recognition for Human-Machine Interaction

Hand Gesture Recognition for Human-Machine Interaction Had Gesture Recogitio for Huma-Machie Iteractio Elea Sáchez-Nielse Departmet of Statistic, O.R. ad Computer Sciece, Uiversity of La Lagua Edificio de Física y Matemáticas 38271, La Lagua, Spai eielse@ull.es

More information

An Efficient Algorithm for Graph Bisection of Triangularizations

An Efficient Algorithm for Graph Bisection of Triangularizations A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045 Oe Brookigs Drive St. Louis, Missouri 63130-4899, USA jaegerg@cse.wustl.edu

More information

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base Compariso of classificatio algorithms i the task of object recogitio o radar images of the MSTAR base A.A. Borodiov 1, V.V. Myasikov 1,2 1 Samara Natioal Research Uiversity, 34 Moskovskoe Shosse, 443086,

More information

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c Advaces i Egieerig Research (AER), volume 131 3rd Aual Iteratioal Coferece o Electroics, Electrical Egieerig ad Iformatio Sciece (EEEIS 2017) Pruig ad Summarizig the Discovered Time Series Associatio Rules

More information

Biometric System Design for Iris Recognition Using Intelligent Algorithms

Biometric System Design for Iris Recognition Using Intelligent Algorithms I.J. Moder Educatio ad Computer Sciece, 8, 3, 9-6 Published Olie March 8 i MECS (http://www.mecs-press.org/) DOI:.585/ijmecs.8.3. Biometric System Desig for Iris Recogitio Usig Itelliget Algorithms Muthaa

More information

SAML-QC: a Stochastic Assessment and Machine Learning based QC technique for Industrial Printing

SAML-QC: a Stochastic Assessment and Machine Learning based QC technique for Industrial Printing SAML-QC: a Stochastic Assessmet ad Machie Learig based QC techique for Idustrial Pritig Azhar ussai College of Iformatio ad Commuicatio Egieerig, arbi Egieerig Uiversity, 5000, arbi, Chia egrazr@hrbeu.edu.c

More information

Alpha Individual Solutions MAΘ National Convention 2013

Alpha Individual Solutions MAΘ National Convention 2013 Alpha Idividual Solutios MAΘ Natioal Covetio 0 Aswers:. D. A. C 4. D 5. C 6. B 7. A 8. C 9. D 0. B. B. A. D 4. C 5. A 6. C 7. B 8. A 9. A 0. C. E. B. D 4. C 5. A 6. D 7. B 8. C 9. D 0. B TB. 570 TB. 5

More information

GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT

GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT 6th Iteratioal DAAAM Baltic Coferece INDUSTRIAL ENGINEERING 24-26 April 2008, Talli, Estoia GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT Rahayem, M.; Kjellader,

More information

FEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING

FEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING FEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING Christoph Busch, Ralf Dörer, Christia Freytag, Heike Ziegler Frauhofer Istitute for Computer Graphics, Computer Graphics Ceter

More information

An Entropy Maximization based technique for Progressive Transmission of MRI Images

An Entropy Maximization based technique for Progressive Transmission of MRI Images IJCSNS Iteratioal Joural of Computer Sciece ad Network Security, VOL.11 No.4, April 2011 159 A Etropy Maximizatio based techique for Progressive Trasmissio of MRI Images Aruava De, Dr. Aup Kumar Bhattacharee,

More information

An Efficient Algorithm for Graph Bisection of Triangularizations

An Efficient Algorithm for Graph Bisection of Triangularizations Applied Mathematical Scieces, Vol. 1, 2007, o. 25, 1203-1215 A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045, Oe

More information

Handwriting Stroke Extraction Using a New XYTC Transform

Handwriting Stroke Extraction Using a New XYTC Transform Hadwritig Stroke Etractio Usig a New XYTC Trasform Gilles F. Houle 1, Kateria Bliova 1 ad M. Shridhar 1 Computer Scieces Corporatio Uiversity Michiga-Dearbor Abstract: The fudametal represetatio of hadwritig

More information

VALIDATING DIRECTIONAL EDGE-BASED IMAGE FEATURE REPRESENTATIONS IN FACE RECOGNITION BY SPATIAL CORRELATION-BASED CLUSTERING

VALIDATING DIRECTIONAL EDGE-BASED IMAGE FEATURE REPRESENTATIONS IN FACE RECOGNITION BY SPATIAL CORRELATION-BASED CLUSTERING VALIDATING DIRECTIONAL EDGE-BASED IMAGE FEATURE REPRESENTATIONS IN FACE RECOGNITION BY SPATIAL CORRELATION-BASED CLUSTERING Yasufumi Suzuki ad Tadashi Shibata Departmet of Frotier Iformatics, School of

More information

Ones Assignment Method for Solving Traveling Salesman Problem

Ones Assignment Method for Solving Traveling Salesman Problem Joural of mathematics ad computer sciece 0 (0), 58-65 Oes Assigmet Method for Solvig Travelig Salesma Problem Hadi Basirzadeh Departmet of Mathematics, Shahid Chamra Uiversity, Ahvaz, Ira Article history:

More information

Review of Data Preprocessing Methods for Sign Language Recognition Systems based on Artificial Neural Networks

Review of Data Preprocessing Methods for Sign Language Recognition Systems based on Artificial Neural Networks ISS 2255-9094 (olie) ISS 2255-9086 (prit) December 2016, vol. 19, pp. 98 103 doi: 10.1515/itms-2016-0018 https://www.degruyter.com/view/j/itms Review of Data Preprocessig Methods for Sig Laguage Recogitio

More information

Fragments based tracking with adaptive multi-cue integration

Fragments based tracking with adaptive multi-cue integration Fragmets based tracig with adaptive multi-cue itegratio Abstract Lichua Gu *, Jiaxiao Liu, Chegi Wag School of Computer ad Iformatio, Ahui Agriculture Uiversity, Hefei Ahui, No.130 West Chagiag Road Chia,

More information

MRI Abdominal Organ Tissue Identification using Statistical Distance in Color Space

MRI Abdominal Organ Tissue Identification using Statistical Distance in Color Space MRI Abdomial Orga Tissue Idetificatio usig Statistical Distace i Color Space Ared Castelei, Terrace Weede, Xiupig Tao 3, H. Keith Brow, Yog Wei. Departmet of Computer Sciece, Uiversity of North Georgia,

More information

On the Accuracy of Vector Metrics for Quality Assessment in Image Filtering

On the Accuracy of Vector Metrics for Quality Assessment in Image Filtering 0th IMEKO TC4 Iteratioal Symposium ad 8th Iteratioal Workshop o ADC Modellig ad Testig Research o Electric ad Electroic Measuremet for the Ecoomic Uptur Beeveto, Italy, September 5-7, 04 O the Accuracy

More information

Descriptive Statistics Summary Lists

Descriptive Statistics Summary Lists Chapter 209 Descriptive Statistics Summary Lists Itroductio This procedure is used to summarize cotiuous data. Large volumes of such data may be easily summarized i statistical lists of meas, couts, stadard

More information

DATA MINING II - 1DL460

DATA MINING II - 1DL460 DATA MINING II - 1DL460 Sprig 2017 A secod course i data miig http://www.it.uu.se/edu/course/homepage/ifoutv2/vt17/ Kjell Orsbor Uppsala Database Laboratory Departmet of Iformatio Techology, Uppsala Uiversity,

More information

Performance Comparisons of PSO based Clustering

Performance Comparisons of PSO based Clustering Performace Comparisos of PSO based Clusterig Suresh Chadra Satapathy, 2 Guaidhi Pradha, 3 Sabyasachi Pattai, 4 JVR Murthy, 5 PVGD Prasad Reddy Ail Neeruoda Istitute of Techology ad Scieces, Sagivalas,Vishaapatam

More information

Web Text Feature Extraction with Particle Swarm Optimization

Web Text Feature Extraction with Particle Swarm Optimization 32 IJCSNS Iteratioal Joural of Computer Sciece ad Network Security, VOL.7 No.6, Jue 2007 Web Text Feature Extractio with Particle Swarm Optimizatio Sog Liagtu,, Zhag Xiaomig Istitute of Itelliget Machies,

More information

Sectio 4, a prototype project of settig field weight with AHP method is developed ad the experimetal results are aalyzed. Fially, we coclude our work

Sectio 4, a prototype project of settig field weight with AHP method is developed ad the experimetal results are aalyzed. Fially, we coclude our work 200 2d Iteratioal Coferece o Iformatio ad Multimedia Techology (ICIMT 200) IPCSIT vol. 42 (202) (202) IACSIT Press, Sigapore DOI: 0.7763/IPCSIT.202.V42.0 Idex Weight Decisio Based o AHP for Iformatio Retrieval

More information

A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON

A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON Roberto Lopez ad Eugeio Oñate Iteratioal Ceter for Numerical Methods i Egieerig (CIMNE) Edificio C1, Gra Capitá s/, 08034 Barceloa, Spai ABSTRACT I this work

More information

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article Available olie www.jocpr.com Joural of Chemical ad Pharmaceutical Research, 2013, 5(12):745-749 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 K-meas algorithm i the optimal iitial cetroids based

More information

Real-Time Secure System for Detection and Recognition the Face of Criminals

Real-Time Secure System for Detection and Recognition the Face of Criminals Available Olie at www.ijcsmc.com Iteratioal Joural of Computer Sciece ad Mobile Computig A Mothly Joural of Computer Sciece ad Iformatio Techology IJCSMC, Vol. 4, Issue. 9, September 2015, pg.58 83 RESEARCH

More information

Exponential intuitionistic fuzzy entropy measure based image edge detection.

Exponential intuitionistic fuzzy entropy measure based image edge detection. Expoetial ituitioistic fuzzy etropy measure based image edge detectio. Abdulmajeed Alsufyai 1, Hassa Badry M. El-Owy 2 1 Departmet of Computer Sciece, College of Computers ad Iformatio Techology, Taif

More information

Size and Shape Parameters

Size and Shape Parameters Defied i the At the momet there is miimal stadardizatio for defiig particle size shape whe usig automated image aalsis. Although particle size distributio calculatios are defied i several stadards (1,

More information

Assignment Problems with fuzzy costs using Ones Assignment Method

Assignment Problems with fuzzy costs using Ones Assignment Method IOSR Joural of Mathematics (IOSR-JM) e-issn: 8-8, p-issn: 9-6. Volume, Issue Ver. V (Sep. - Oct.06), PP 8-89 www.iosrjourals.org Assigmet Problems with fuzzy costs usig Oes Assigmet Method S.Vimala, S.Krisha

More information

Computerized classification of microcalcifications on mammograms using fuzzy logic and genetic algorithm

Computerized classification of microcalcifications on mammograms using fuzzy logic and genetic algorithm Computerized classificatio of microcalcificatios o mammograms usig fuzzy logic ad geetic algorithm Yogbum Lee *a ad Du-Yih Tsai a a Dept. of Radiology, School of Health Scieces, Faculty of Medicie, Niigata

More information

Bayesian approach to reliability modelling for a probability of failure on demand parameter

Bayesian approach to reliability modelling for a probability of failure on demand parameter Bayesia approach to reliability modellig for a probability of failure o demad parameter BÖRCSÖK J., SCHAEFER S. Departmet of Computer Architecture ad System Programmig Uiversity Kassel, Wilhelmshöher Allee

More information

Soft Computing Based Range Facial Recognition Using Eigenface

Soft Computing Based Range Facial Recognition Using Eigenface Soft Computig Based Rage Facial Recogitio Usig Eigeface Yeug-Hak Lee, Chag-Wook Ha, ad Tae-Su Kim School of Electrical Egieerig ad Computer Sciece, Yeugam Uiversity, 4- Dae-dog, Gyogsa, Gyogbuk, 7-749

More information

Real-Time Crop Row Image Reconstruction for Automatic Emerged Corn Plant Spacing Measurement

Real-Time Crop Row Image Reconstruction for Automatic Emerged Corn Plant Spacing Measurement Agricultural ad Biosystems Egieerig Publicatios Agricultural ad Biosystems Egieerig 2008 Real-Time Crop Row Image Recostructio for Automatic Emerged Cor Plat Spacig Measuremet Lie Tag Iowa State Uiversity,

More information

The isoperimetric problem on the hypercube

The isoperimetric problem on the hypercube The isoperimetric problem o the hypercube Prepared by: Steve Butler November 2, 2005 1 The isoperimetric problem We will cosider the -dimesioal hypercube Q Recall that the hypercube Q is a graph whose

More information

Ontology-based Decision Support System with Analytic Hierarchy Process for Tour Package Selection

Ontology-based Decision Support System with Analytic Hierarchy Process for Tour Package Selection 2017 Asia-Pacific Egieerig ad Techology Coferece (APETC 2017) ISBN: 978-1-60595-443-1 Otology-based Decisio Support System with Aalytic Hierarchy Process for Tour Pacage Selectio Tie-We Sug, Chia-Jug Lee,

More information

EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS

EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS Iteratioal Joural o Natural Laguage Computig (IJNLC) Vol. 2, No., February 203 EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS Raj Kishor Bisht ad Ila Pat Bisht 2 Departmet of Computer Sciece &

More information

Title: Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity.

Title: Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity. 7 IEEE. Persoal use of this material is permitted. Permissio from IEEE must be obtaied for all other uses, i ay curret or future media, icludig repritig/republishig this material for advertisig or promotioal

More information

Feature classification for multi-focus image fusion

Feature classification for multi-focus image fusion Iteratioal Joural of the Physical Scieces Vol. 6(0), pp. 4838-4847, 3 September, 0 Available olie at http://www.academicjourals.org/ijps DOI: 0.5897/IJPS.73 ISSN 99-950 0 Academic Jourals Full Legth Research

More information

FEATURE RECOGNITION OF ROTATIONAL PARTS USING BIQUADRATIC BEZIER PATCHES

FEATURE RECOGNITION OF ROTATIONAL PARTS USING BIQUADRATIC BEZIER PATCHES roceedigs of the Iteratioal Coferece o Mechaical Egieerig 7 (ICME7) 9-31 December 7, Dhaka, Bagladesh ICME7- FEATURE RECOGNITION OF ROTATIONAL ARTS USING BIQUADRATIC BEZIER ATCHES J. Kumar 1 ad N. Roy

More information

Position and Velocity Estimation by Ultrasonic Sensor

Position and Velocity Estimation by Ultrasonic Sensor Positio ad Velocity Estimatio by Ultrasoic Sesor N Ramarao 1, A R Subramayam 2, J Chara Raj 2, Lalith B V 2, Varu K R 2 1 (Faculty of EEE, BMSIT & M, INDIA) 2 (Studets of EEE, BMSIT & M, INDIA) Abstract:

More information