Texture Defect Detection System with Image Deflection Compensation
|
|
- Barbra Owen
- 5 years ago
- Views:
Transcription
1 Texture Defect Detection System with Image Deflection Compensation CHUN-CHENG LIN CHENG-YU YEH Department of Electrical Engineering National Chin-Yi University of Technology 35, Lane 15, Sec. 1, Chungshan Roa, Taiping, Taichung, Taiwan Abstract: Image textural analysis technology has been wiely use in the esign of automate efect etection systems. Because the presence of efects may change the textural features of an image, a reference image without efects can be compare with the test image to etect whether there are any efects. However, besies efects, the eflection of the input test image coul also change its textural features. When there is any angular ifference between the reference an test images, their textural features woul also be ifferent, even if there is no efect in the test image. As a result, misjugment of the efect etection system may occur. Most of the previous stuies have focuse on the evelopment of textural analysis technology which coul ecrease the effect of test image eflection. This stuy aime to estimate the eflection angle of test images through polar Fourier transform an phase correlation analysis, an rotate the reference image by the same angle to compensate for the eflection of the test image. After the angles of the reference an test images were brought into line, the textural analysis base on the gray level co-occurrence matrix was applie to analyze an compare the textural features of the two images. The results of actual texture efect etection emonstrate that the angular ifferences between the reference an test images coul be estimate correctly, with an estimation error of only 0 to 0.5. By compensating for the eflection of the test image, the accuracy of the texture efect etection coul be effectively enhance. Key-Wors: - Texture efect etection, Image eflection compensation, Polar Fourier transform, Phase correlation analysis, Gray level co-occurrence matrix 1 Introuction In automate prouction systems, efects are likely to occur in many proucts, such as textiles, steel proucts, iscs, an glass an paper proucts, ue to the abnormality of processing tools uring processing. If the efect is too small to be ientifie by visual inspection, it woul be time-consuming an strenuous to carry out manual inspection, an thus inspection may be neglecte. Since the textural features of efects are ifferent from those of the proucts, many stuies have propose image textural analysis technology to esign an automate efect etection system. The main aim of textural analysis is to simulate human capability of istinguishing textures, an ientify appropriate textural features to escribe the image, so as to analyze textural ifferences. The main methos for textural analysis inclue the statistical metho [1-9], the structural metho [10] an the spectral metho [11-15]. The statistical metho can provie all sorts of statistical ata about the relative positions among pixels, an then ecrease the effects of textural image translation, rotation an noise, thus having inherent avantages for efect etection. It can be ivie into first orer, secon orer an higher orer levels. Julesz [16] pointe out that human s vision system is most appropriate for secon-orer statistics; thus, most researchers have aopte this kin of statistics. The secon-orer statistical metho inclues the gray level co-occurrence matrix () [1-5], the neighboring gray level epenence matrix [6-8] an the neighborhoo gray tone ifference matrix [9]. The structural metho consiers that images are forme by textural primaries arrange base on specific rules. Accoringly, it ientifies the arrangement rules by obtaining textural primaries in the image [10]. However, to analyze the images with inconspicuous textural rules, the structural metho cannot effectively obtain the textural primaries an escribe their arrangement rules. The spectral metho uses Fourier transform to analyze the obtaine spectrums an istinguish the features of perioic texture, such as main irection, spatial perio an spectral energy [11-15]. Moreover, there are some other textural analysis methos base on the Markov ranom fiel moel [17,18], the irectional Walsh-Haamar transform [19], the ranom subspace neural classifier [0], the wavelet transform [1], an the optimize filter [,3]. Chang et al. [17] observe that certain spatial an temporal features of the Markov ranom ISSN: Issue 9, Volume 8, September 009
2 fiel ensity function can be erive to moel temporal textures. They propose a texture escriptor base on spatial an temporal preiction resiual of mean filtering to stuy the ynamic nature of textures for vieo inexing. Zimeras [18] further evelope an auto-logistic moel base on Markov ranom fiels to simulate texture patterns. The metho base on the irectional Walsh- Haamar transform [19] can insert the basic avantages of multi-scale an multi-irectional texture analysis into a fast moifie Walsh- Haamar transform. The ranom subspace neural classifier [0] was evelope an use for image recognition in micromechanics, an can recognize ifferent types of metal surfaces after mechanical processing. Ngan et al [1] propose the metho base on wavelet transform an golen image subtraction for efect etection on patterne fabric or repetitive patterne texture. The golen image subtraction can effectively segment out the efective regions on patterne fabric. The optimize filters using linear finite-impulse-response filters [] an Gabor filters [3] were esigne to automatically extract the efects in texture materials. Since the presence of efects can change the textural features of an image, a reference image without efects can be use to compare with the test image to etect whether there are any efects. However, besies efects, the image eflection can also change textural features an affect the accuracy of efect etection. When there is any angular ifference between the reference image an the test image, their textural features are accoringly ifferent, even if there is no efect in the test image. As a result, misjugment of the etection system may occur. Although the current methos of textural analysis can extract various useful features in texture materials, they are all sensitive to image eflection. This stuy aime to compensate for the eflection angle of the test image, so as to enhance the accuracy of texture efect etection. It transforme the rotation relationship between the test an reference images into a isplacement relationship in the frequency omain through polar Fourier transform [4-7], an estimate the isplacement vector in the frequency omain through phase correlation analysis [8] to obtain the angular ifference between the two images. Then, the reference image was rotate by the same angle to compensate for the eflection of the test image. When the angles of the test an reference images were brought into line, the -base statistical metho was applie to analyze an compare the textural features of the two images. The remainer of this paper is organize as follows. Sections an 3 introuce the estimation methos for the eflection angle of the test image an the -base texture analysis, respectively. Section 4 establishes the texture efect etection rules, an efines the performance inexes of the texture efect etection system. Section 5 explains the etection results of the texture efect etection system for all efect images. Section 6 gives the conclusions. Estimation methos for the eflection angle of the test image Accoring to the properties of Fourier transform, spatial signal isplacement or rotation has specific corresponing relationships in the frequency omain. Therefore, the spatial isplacement vector or rotation angle can be calculate from the frequency omain. Kuglin an Hines [8] use the translation property of Fourier transform to propose a phase correlation analysis to calculate the isplacement vector between two images, an applie this analysis in image registration. Other research on image registration [4-7] combine polar Fourier transform an phase correlation analysis to further calculate the ifference of rotation angles between two images. Through polar Fourier transform, the original spatial rotation relationship of these two images before an after rotating coul be expresse as a isplacement relationship in the frequency omain. Therefore, phase correlation analysis can be further use to calculate the isplacement vector in the frequency omain, an to obtain the angle ifference of these two images. In this stuy, the estimation metho for the eflection angle of the test image is escribe in etail as follows. Suppose that f 1 an f are the images before an after a isplacement of ( x 0, y0 ), the relationship between which is as follows: f ( 1 0 y0 x, y) = f ( x x, y ) (1) Accoring to the translation property of Fourier transform, the relationship between Fourier transforms F1 ( u, an F ( u, of image f 1 an f is as follows: jπ ( ux + vy ) 0 F ( u, = e 0 F1 ( u, v ) Moreover, () ISSN: Issue 9, Volume 8, September 009
3 F ( u, jπ ( ux0 + vy0 ) = e F ( u, 1 (3) Accoringly, image isplacement in frequency omain can only change the phase correlation jπ ( ux 0 ) of 0 + vy e. After Eq. (3) taken on inverse Fourier transform, δ ( x x0, y y0 ) can be obtaine. The position of maximum δ ( x x0, y y0 ) is then the isplacement vector ( x 0, y 0 ). The inverse Fourier transform of Eq. (3) is efine as a phase correlation function as follows [8]: 1 F ( u, Corr( x, y) = I ( ) F1 ( u, ( x, y ) = arg max( Corr( x, )) (4) 0 0 y ( x, y) 1 where I is the inverse Fourier transform, an x 0 an y 0 are the positions of the maximum phase correlation function. Therefore, in phase correlation analysis, two images with a isplacement relationship unergo Fourier transform first, an then their phase correlation function is calculate, an the position of the maximum phase correlation function is obtaine, in orer to fin the isplacement vector between the two images. Figures 1 an are the images of a rectangle before an after a isplacement of (30, 10). The corresponing phase correlation function is shown in Figure. As seen, the maximum value of this function appears at (30, 10). Therefore, the spatial isplacement vector of the images is (30, 10). Image rotation also has a specific corresponing relationship in the frequency omain [4-7]. Supposing that f can be obtaine through rotating f 1 by θ 0, then the relationship between f 1 an f can be escribe as follows: f ( x, y) = f1( xcosθ0 + y sinθ0, x cosθ0 + y sinθ0 ) (5) Accoring to the rotation properties of Fourier transform, the relationship between spectrums F 1( u, an F ( u, after f 1 an f unergo Fourier transform is as follows: F ( u, = F1 ( ucosθ0 + vsinθ0, u cosθ0 + vsinθ0 ) (6) Fig. 1 A rectangle image, before isplacement; after a isplacement of (30, 10). Magnitue Fig. The phase correlation function corresponing to a isplacement of (30, 10). Therefore, when the image rotates by θ 0, the spectrum also rotates by θ 0. Figures 3 an are the images of a rectangle before an after rotating by 45. Figures 3 an () show the spectrums of the image before an after rotating. The rotation angles of the spectrum in the frequency omain an the image in the spatial omain are both 45. Although the rotation angles in the frequency an spatial omains are the same, they cannot be calculate irectly in the frequency omain. The spatial rotation relationship nees to be transforme into a isplacement relationship in the frequency omain. Polar Fourier transform transforms the spectrum represente by the rectangular coorinate after Fourier transform into that represente by polar coorinate. Supposing that f is obtaine through translating f 1 by ( x0, y0 ) an rotating it by θ 0, then the relationship between f 1 an f can be escribe as follows: f x, y) = f1( xcosθ 0 + ysinθ0, xcosθ 0 + y sinθ0 y0 ) (7) ( x0 ISSN: Issue 9, Volume 8, September 009
4 Reference Image f 1 Test Image f Polar Fourier Transform Polar Fourier Transform Magnitue Spectrum Calculation Magnitue Spectrum Calculation M ( r, ) M ( r, ) 1 θ θ () Fig. 3 Image an spectrum of a rectangle: an : images before an after rotating by 45 ; an (): spectrums before an after rotating. Through Fourier transform, the following equation can be obtaine: jπ ( ux + vy ) 0 F ( u, = e 0 F1 ( ucosθ0 + vsin θ 0, u cosθ0 + vsinθ0 ) (8) If consiering the magnitue spectrum only, the relationship among them is as follows: M ( u, = M1( ucosθ0 + vsinθ0, u cosθ0 + vsinθ0 ) (9) where M 1 an M are the magnitue spectrums of images f 1 an f ; parameters r an θ that transform the rectangular coorinate into the polar coorinate system are efine as follows: r = u + v (10) tan 1 v θ = ( ) (11) u Then the relationship between magnitue spectrums can be transforme as: Deflection Angle θ 0 Fig. 4 Flow chart for estimating the eflection angle of the test image. M r, θ ) = M ( r, θ ) (1) ( 1 θ0 Phase Correlation Analysis As a result, the spatial rotation relationship between images can be transforme as the translation relationship in the frequency omain through polar Fourier transform. Then, phase correlation analysis is use to calculate the translation vector in this frequency omain. This stuy applie polar Fourier transform an phase correlation analysis to calculate the eflection angle of the test image. Figure 4 is the calculation flow chart of the eflection angle of this test image. After applying polar Fourier transform to the reference an test images, an calculating the magnitue spectrum, if there is any angular ifference between the images, the magnitue spectrums woul have a isplacement relationship. Phase correlation analysis is then applie to calculate the isplacement vector between magnitue spectrums, in orer to obtain the eflection angle of the test image. 3 -base texture analysis -base texture analysis is a secon-orer statistical metho that can be use to calculate the emergency frequency of pixels conforming to the relative angle an istance in a specific position [1- ISSN: Issue 9, Volume 8, September 009
5 5]. The corresponing is ifferent ue to the ifference of the relative position angle of the etecte pixels. Each image has four s uner ifferent angles, 0, 45, 90 an 135. I ( l) an I( m, are two pixels in the two-imension image I, then s uner ifferent angles can be escribe as follows [1]: ( l),( m, I P( i, j,,0) = # k m = 0, l n = (13) I ( l) = i, I( m, = j ( l),( m, I ( k m =, l n = ) P( i, j,,45) = # (14) or ( k m =, l n = ) I( l) = i, I ( m, = j ( l),( m, I P( i, j,,90) = # k m =, l n = 0 (15) I( l) = i, I ( m, = j ( l),( m, I ( k m =, l n = ) P( i, j,,135) = # (16) or ( k m =, l n = ) I( l) = i, I( m, = j where, is the istance between pixels, # is the quantity of collection elements, an i an j are the pixel values of I ( l) an I ( m,. Figure 5 is an 8 8 image example, the gray level values of which are j = 0,1,. Figure 6 is the schematic iagram of this 8 8 image example. Supposing that = 1, then in four irections can be calculate accoring to Eqs. (13), (14), (15) an (16), as shown in Figure 7. Figure 8 is an image example with vertical texture. Figures 9,, an () are the s at 0, 45, 90 an 135, respectively, where a larger inicates higher brightness. As shown in Figure 9, the numerical value istribution is relate to textural structure. The value of structures with fewer gray level interfaces tens to be istribute near the iagonal line, while that of structures with more gray level interfaces spreas from the iagonal line an istributes uniformly Fig. 5 An 8 8 image example. Gray level #(0,0) #(0,1) #(0,) 1 #(1,0) #(1,1) #(1,) #(,0) #(,1) #(,) Fig. 6 schematic iagram for an 8 8 image example () 135 Fig. 7 The co-occurrence matrices of an 8 8 image example. Fig. 8 An image example with vertical textures ISSN: Issue 9, Volume 8, September 009
6 upper right or lower left corners, the contrast is larger. A smaller contrast inicates closer gray-level values among pixels, while a larger contrast inicates larger ifferences of gray-level values among pixels. ) Angular secon moment ASM = [ P ( i j) ] i j, (19) () Fig. 9 s of an image example with vertical textures at 0, 45, 90 an () 135. Since the image texture in Figure 8 presents a vertical tren, at 90 istributes significantly near the iagonal line, as shown in Figure 9. At the same time, s in the other irections istribute uniformly, as shown in Figures 9,, an (). Conventional textural features in texture analysis inclue contrast, angular secon moment (ASM), homogeneity, entropy an correlation, which are efine as follows [-5]: 1) Contrast = i j ( i j) P ( i j) CON, (17) where P is the normalize, efine as follows: P = i= o j= 0 P ( i, j) P (18) Contrast is use to measure the sharp egree of the contrast an reflect the situation of co-occurrence matrices elements near the main iagonal line. When larger values center on the main iagonal line of co-occurrence matrices, the image contrast is smaller. Otherwise, when larger values centre at the The ASM value is equal to the quaratic sum of all elements in an also the energy of. ASM is use to measure the consistency an uniformity of image gray level istribution, which means the repeate emergence probability of a certain pixel: higher probability inicates higher consistency. When an image has consistent texture, few values of normalize off the iagonal line are approximate to 1, while others are approximate to 0. Therefore, when the image texture is more consistent an uniform, values ten to centre on the few elements, thus making the ASM value larger. Otherwise, when values istribute more uniformly, the ASM value is smaller. 3) Homogeneity 1 HOM = P ( i, j), i j (0) i j i j When larger values are concentrate aroun the main iagonal line, homogeneity woul be larger. Opposite to contrast, homogeneity is use to analyze the homogeneous egree of the image: the more homogeneous the image (contrast less sharp), the larger the homogeneity. An image with a sharper contrast is etaile, while one with higher homogeneity is coarse. 4) Entropy = i j ( i j) log P ( i j) EN P,, (1) Entropy is mainly use to measure textural complexity. When the texture of a textural image is unorerly, gray level values istribute uniformly, making the values of all elements in the cooccurrence matrix smaller. Therefore, larger entropy inicates higher textural complexity. Entropy is in inverse proportion to energy. The co-occurrence matrix values of an image with higher entropy istribute uniformly. ISSN: Issue 9, Volume 8, September 009
7 5) Correlation i j P ( i, j) μ xμ y i j COR = σ xσ y () where, μ μ σ x y = i i P ( i, j) j = j i i P ( j, i) ( x = i j ( y = i j i μ ) P ( i, j) x y σ j μ ) P ( i, j) (3) where μ x, μ y, σ x an σ y are the mean values of rows an stanar eviations of columns. Correlation values can reflect image irectivity. When images arrange along a certain irection, the correlation of textural features in this irection is higher than that in other irections. A feature vector is then efine combining Eqs. (17), (19), (0), (1) an () as follows: [ ASM HOM EN COR] CON (4) The feature vector can be use to calculate the Euler istance between the reference image an the test image, which is efine as follows: xy = m i= 1 ( x y ) (5) i i where xi an yi are the feature vectors of the reference an test images, respectively. The Euler istance can be use to calculate the istances among vectors in orthogonal space. However, in this stuy, it is use to estimate the nearness of feature vectors. When the Euler istance is lower than the efault critical value, there is no efect in the test image. Otherwise, when the Euler istance is higher than the efault critical value, there are some efects in the image. The texture efect etection algorithm propose in this stuy is as follows: Step 1: Reference image an test image with pixels are input. Step : Polar Fourier transform an phase correlation analysis are applie to calculate angular ifference θ 0 between the reference an test images. Step 3: The reference image with pixels is rotate by θ 0. After the angles of the reference an test images are consistent, a block of 3 3 pixels in a central position is extracte as a reference. Step 4: The test image of pixels is ivie into 64 test blocks of 3 3 pixels. Step 5: Feature matrixes an the Euler Distance of the reference block an all test blocks are calculate. Step 6: When the Euler Distance is larger than the efault threshol value, the value is set accoring to actual texture kins. In this stuy, performance inexes such as specificity, sensitivity, positive preictive accuracy (PPA), negative estimative accuracy (NPA), an total estimative accuracy (TPA) [9] were applie to estimate the performance of the efect etection system. Specificity is use to estimate the correctness of etecting zero efects in perfect images. Sensitivity is use to estimate the correctness of etecting the existence efects in actually efective images. PPA is use to estimate the etection correctness of the existence of efects. NPA is use to estimate the etection correctness of zero efects. TPA is use to estimate the total etection correctness. Supposing that the efect etection results are as in Table 1, all performance inexes are efine as follows: Specificity = 100% ( b + ) a Sensitivity = 100% ( a + c) a PPA = 100% ( a + b) NPA = 100% ( c + ) (6) (7) (8) (9) 4 Texture efect etection algorithm a + TPA = 100% ( a + b + c + ) (30) ISSN: Issue 9, Volume 8, September 009
8 5 Experiment results In this stuy, four kins of test images with bifilar efects, panel efects, greasy efects an scratch efects uner ifferent eflection angles were applie to evaluate the performance of the texture efect etection system. As seen from Figure 10, when there is no eflection in the test image, applying -base texture analysis only can etect the efective blocks correctly. However, given any eflection in the test image angle, the etection correctness of applying -base texture analysis only ecreases greatly. Figures 11, 1, 13 an 14 show the efect etection results of -base texture analysis without an with image eflection compensation when the efective test images eflect ifferent angles. Because the ifferences between the perfect an efective blocks for greasy an scratch efects are less conspicuous than those for bifilar an panel efects, the Euler istances an the threshol value of ientifying efective blocks for greasy an scratch efects are also lower than those for bifilar an panel efects. The threshol values for ientifying bifilar, panel, greasy an scratch efects are 300, 300, 15 an 5, respectively. The smaller Euler istances also cause more misjugments in the etection of greasy an scratch efects when the input test image eflects, if only applying -base texture analysis without image eflection compensation. Moreover, the larger the eflection angle, the lower the accuracy of the efect etection. After aing phase correlation analysis an compensating for the eflection angle of the test image, the etection accuracy of the efective blocks can revert to that when the test image has no angular eflection. This stuy further analyze the performance inexes of the texture efect etection system for ifferent eflection angles an test images with various efects. Tables, 3, 4 an 5 list the performance inexes for bifilar efects, panel efects, greasy efects an scratch efects, respectively, using -base texture analysis without an with image eflection compensation uner ifferent eflection angles of the input test image. The quantity of actual perfect an efective blocks is epenent on the eflecte test image. The results emonstrate that image eflection compensation can increase TPA by 11% (97%-86%), 1% (100%-99%), 5% (97%-45%) an 37% (98%- 61%) in the etection of bifilar efects, panel efects, greasy efects an scratch efects, respectively. As seen, the eflection of the test image has the smallest effect on the textural features of the test image with panel efects, an the largest effect on the test image with greasy efects. Table 1 Distribution of efect etection results Detecte efective blocks Detecte perfect blocks Actual efective blocks Actual perfect blocks Total a b a+b c c+ Total a+c b+ () Fig. 10 Defect etection results of texture analysis when there is no eflection in the test image bifilar efects panel efects, greasy efects an () scratch efects. Tables, 3, 4 an 5 also inicate the actual eflection angles of the test image an the estimate eflection angles by polar Fourier transform an phase correlation analysis. The estimation error of the eflection angle is only from 0 to 0.5. Hence the eflection angle of the test image can be compensate for quite correctly. ISSN: Issue 9, Volume 8, September 009
9 () () Fig. 11 Bifilar efects etection results when the input test image eflects 45 ( an ) an 150 ( an ()) using -base texture analysis without ( an ) an with ( an ()) image eflection compensations. Fig. 13 Greasy efects etection results when the input test image eflects 45 ( an ) an 150 ( an ()) using -base texture analysis without ( an ) an with ( an ()) image eflection compensations. () () Fig. 1 Panel efects etection results when the input test image eflects 45 ( an ) an 150 ( an ()) using -base texture analysis without ( an ) an with ( an ()) image eflection compensations. Fig. 14 Scratch efects etection results when the input test image eflects 45 ( an ) an 150 ( an ()) using -base texture analysis without ( an ) an with ( an ()) image eflection compensations. ISSN: Issue 9, Volume 8, September 009
10 Table Performance inexes for the etection of bifilar efects. Specificity Sensitivity PPA NPA TPA + Image Deflection Compensation Actual eflection angles are 30, 45, 60 an 150, while estimate eflection angles are 9.5, 45, 60.5 an The threshol value is 300. Table 4 Performance inexes for the etection of greasy efects. Specificity Sensitivity PPA NPA TPA + Image Deflection Compensation Actual eflection angles are 11, 19, 9 an 36, while estimate eflection angles are 11.3, 19.5, 9.5 an The threshol value is 15. Table 3 Performance inexes for the etection of panel efects. Specificity Sensitivity PPA NPA TPA + Image Deflection Compensation Actual eflection angles are 9, 14, an 33, while estimate eflection angles are 8.5, 14.1,.5 an 3.5. The threshol value is 300. Table 5 Performance inexes for the etection of scratch efects. Specificity Sensitivity PPA NPA TPA + Image Deflection Compensation Actual eflection angles are 5, 11, 7 an 38, while estimate eflection angles are 5.4, 11., 6.7 an The threshol value is 5. 6 Conclusions This stuy estimate angular ifferences between the reference an test images using polar Fourier transform an phase correlation analysis, an rotate the reference image by the same angle to compensate for the eflection of the test image. The estimation error of the image eflection angle was only from 0 to 0.5. Hence the estimate eflection angle can be further applie to compensate for eflection effects. The experimental results of the texture efect etection showe that, when there is some eflection in the test image, the ISSN: Issue 9, Volume 8, September 009
11 efect etection accuracy of using -base texture analysis only ecreases greatly, while that of compensating for the angular eflection of the test image can be effectively enhance. In conclusion, the texture efect etection system with image eflection compensation propose in this stuy can effectively solve the problem of test image eflection an enhance the performance of the texture efect etection system. 7 Acknowlegement This research was financially supporte by the National Science Council uner Grant No B References: [1] R.M. Haralic K. Shanmugan, I.H. Dinstein, Textural features for image classification, IEEE Transaction on Systems, Man, an Cybernetics, Vol.SMC-3, 1973, pp [] L.K. Soh, C. Tsatsoulis, Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co- Occurrence Matrices, IEEE Transactions on Geoscience an Remote Sensing, Vol.37, 1999, pp [3] D. Mery, M.A. Berti, Automatic Detection of Weling Defects Using Texture Features, Insight, Vol.45, 003, pp [4] U. Kanaswamy, D.A. Ajeroh, M.C. Lee, Efficient Texture Analysis of SAR Imagery, IEEE Transactions on Geoscience an Remote Sensing, Vol.43, 005,pp [5] C.E. Honeycutt, R. Plotnic Image analysis techniques an gray-level co-occurrence matrices () for calculating bioturbation inices an characterizing biogenic seimentary structures, Computers an Geosciences, Vol.34, 008, pp [6] C. Sun, W.G. Wee, Neighboring Gray Level Depenence Matrix for Texture Classification, Computer Vision, Graphics an Image Processing, Vol.3, 198, pp [7] L.H. Siew, R.M. Hogson, E.J. Woo, Texture Measures for Carpet Wear Assessment, IEEE Transaction on Pattern Analysis an Machine Intelligence, Vol.10, 1988, pp [8] A. Murali, W.V. Stoecker, R.H. Moss, Detection of Soli Pigment in Dermatoscopy Images Using Texture Analysis, Skin Research an Technology, Vol.6, 000, pp [9] C.I. Christooulou, S.C. Michaelies, C.S. Pattichis, Multifeature Texture Analysis for the Classification of Clous in Satellite Imagery, IEEE Transactions on Geoscience an Remote Sensing, Vol.41, 003, pp [10] C.D. Ruberto, G. Roriguez, S. Vitulano, Image Segmentation by Texture Analysis, Proceeings of International Conference on Image Analysis an Processing, 1999, pp [11] C.H. Chen, G.K.H. Pang, Fabric Defect Detection by Fourier Analysis, IEEE Transactions on Inustry Application, Vol.36, 000, pp [1] Z. Peng, T.B. Kir Two-imensional Fast Fourier Transform an Power Spectrum for Wear Particle Analysis, Tribology International, Vol.30,1997, pp [13] D. Zhang, G. Lu, Stuy an Evaluation of Different Fourier Methos for Image Retrieval, Image an Vision Computing, Vol.3, 005, pp [14] D.M. Tsai, C.Y. Hsieh, Automate Surface Inspection for Directional Textures, Image an Vision Computing, Vol.18, 1999, pp [15] D.M. Tsai, T.Y. Huang, Automate Surface Inspection for Statistical Textures, Image an Vision Computing, Vol.1, 003, pp [16] T. Caelli, B. Julesz, Psychophysical Evience for Global Feature Processing in Visual Texture Discrimination, Journal of the Optical Society of America, Vol.69, 1979, pp [17] W.H. Chang, N.C. Yang, C.M. Kuo, Y.J. Chen, A Novel Temporal Texture Descriptor Using Spatial-Temporal Local Distribution for Vieo Retrieving, WSEAS Transactions on Information Science an Applications, Vol. 3, 006, pp [18] S. Zimeras, Simulating texture patterns using auto-logistic moels, WSEAS Transactions on Systems, Vol. 5, 006, pp [19] S.A. Monajemi, P. Moallem, A fast multiscale/multi-irectional texture feature extraction scheme, WSEAS Transactions on Computers, Vol. 5, 006, pp [0] T. Baiy E. Kussul, O. Makeyev, Texture recognition with ranom subspace neural classifier, WSEAS Transactions on Circuits an Systems, Vol. 4, 005, pp [1] H.Y.T. Ngan, G.K.H. Pang, S.P. Yung, M.K. Ng, Wavelet base methos on patterne fabric efect etection, Pattern Recognition, Vol.38, 005, pp [] A. Kumar, G.K.H. Pang, Defect Detection in Texture Materials Using Optimize Filters, IEEE Transaction on Systems, Man, an Cybernetics, Vol.3, 00, pp ISSN: Issue 9, Volume 8, September 009
12 [3] A. Kumar, G.K.H. Pang, Defect Detection in Texture Materials Using Gabor Filters, IEEE Transactions on Inustry Applications, Vol.38, 00, pp [4] B.S. Rey, B.N. Chatterji, An FFT-Base Technique for Translation, Rotation, an Scale-Invariant Image Registration, IEEE Transactions on Image Processing, Vol.5, 1991, pp [5] A. Averbuch, Y. Keller, FFT Base Image Registration, Proceeings of IEEE International Conference on Acoustics, Speech an Signal Processing, Vol.4, 00, pp.iv/3608-iv/3611. [6] Y. Keller, A. Averbuch, M. Israeli, Pseuopolar-Base Estimation of Large Translations, Rotations, an Scalings in Images, IEEE Transactions on Image Processing, Vol.14, 005, pp.1-. [7] Y. Keller, Y. Shkolnisky, A. Averbuch, The Angular Difference Function an Its Application to Image Registration, IEEE Transactions on Pattern Analysis an Machine Intelligence, Vol.7, 005, pp [8] C.D. Kuglin, D.C. Hines, The phase correlation image alignment metho, Proceeings of IEEE International Conference on Cybernetics an Society, 1975pp [9] P.F. Griner, R.J. Mayewski, A.I. Mushlin, P. Greenlan, Selection an interpretation of iagnostic tests an proceures. Principles an applications, Annals of internal meicine, Vol.94, 1981, pp ISSN: Issue 9, Volume 8, September 009
Image Segmentation using K-means clustering and Thresholding
Image Segmentation using Kmeans clustering an Thresholing Preeti Panwar 1, Girhar Gopal 2, Rakesh Kumar 3 1M.Tech Stuent, Department of Computer Science & Applications, Kurukshetra University, Kurukshetra,
More informationAN INVESTIGATION OF FOCUSING AND ANGULAR TECHNIQUES FOR VOLUMETRIC IMAGES BY USING THE 2D CIRCULAR ULTRASONIC PHASED ARRAY
AN INVESTIGATION OF FOCUSING AND ANGULAR TECHNIQUES FOR VOLUMETRIC IMAGES BY USING THE D CIRCULAR ULTRASONIC PHASED ARRAY S. Monal Lonon South Bank University; Engineering an Design 103 Borough Roa, Lonon
More informationA multiple wavelength unwrapping algorithm for digital fringe profilometry based on spatial shift estimation
University of Wollongong Research Online Faculty of Engineering an Information Sciences - Papers: Part A Faculty of Engineering an Information Sciences 214 A multiple wavelength unwrapping algorithm for
More informationClassifying Facial Expression with Radial Basis Function Networks, using Gradient Descent and K-means
Classifying Facial Expression with Raial Basis Function Networks, using Graient Descent an K-means Neil Allrin Department of Computer Science University of California, San Diego La Jolla, CA 9237 nallrin@cs.ucs.eu
More informationTexture Recognition with combined GLCM, Wavelet and Rotated Wavelet Features
International Journal of Computer an Electrical Engineering, Vol.3, No., February, 793-863 Texture Recognition with combine GLCM, Wavelet an Rotate Wavelet Features Dipankar Hazra Abstract Aim of this
More informationRough Set Approach for Classification of Breast Cancer Mammogram Images
Rough Set Approach for Classification of Breast Cancer Mammogram Images Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative Methos an Information Systems
More informationTransient analysis of wave propagation in 3D soil by using the scaled boundary finite element method
Southern Cross University epublications@scu 23r Australasian Conference on the Mechanics of Structures an Materials 214 Transient analysis of wave propagation in 3D soil by using the scale bounary finite
More informationFeature Extraction and Rule Classification Algorithm of Digital Mammography based on Rough Set Theory
Feature Extraction an Rule Classification Algorithm of Digital Mammography base on Rough Set Theory Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative
More informationClassical Mechanics Examples (Lagrange Multipliers)
Classical Mechanics Examples (Lagrange Multipliers) Dipan Kumar Ghosh Physics Department, Inian Institute of Technology Bombay Powai, Mumbai 400076 September 3, 015 1 Introuction We have seen that the
More informationTexture Analysis and Applications
Texture Analysis and Applications Chaur-Chin Chen Department of Computer Science National Tsing Hua University Hsinchu 30043, Taiwan E-mail: cchen@cs.nthu.edu.tw Tel/Fax: (03) 573-1078/572-3694 Outline
More informationMulti-camera tracking algorithm study based on information fusion
International Conference on Avance Electronic Science an Technolog (AEST 016) Multi-camera tracking algorithm stu base on information fusion a Guoqiang Wang, Shangfu Li an Xue Wen School of Electronic
More informationThe Journal of Systems and Software
The Journal of Systems an Software 83 (010) 1864 187 Contents lists available at ScienceDirect The Journal of Systems an Software journal homepage: www.elsevier.com/locate/jss Embeing capacity raising
More informationTHE BAYESIAN RECEIVER OPERATING CHARACTERISTIC CURVE AN EFFECTIVE APPROACH TO EVALUATE THE IDS PERFORMANCE
БСУ Международна конференция - 2 THE BAYESIAN RECEIVER OPERATING CHARACTERISTIC CURVE AN EFFECTIVE APPROACH TO EVALUATE THE IDS PERFORMANCE Evgeniya Nikolova, Veselina Jecheva Burgas Free University Abstract:
More informationDEVELOPMENT OF DamageCALC APPLICATION FOR AUTOMATIC CALCULATION OF THE DAMAGE INDICATOR
Mechanical Testing an Diagnosis ISSN 2247 9635, 2012 (II), Volume 4, 28-36 DEVELOPMENT OF DamageCALC APPLICATION FOR AUTOMATIC CALCULATION OF THE DAMAGE INDICATOR Valentina GOLUBOVIĆ-BUGARSKI, Branislav
More informationFast Fractal Image Compression using PSO Based Optimization Techniques
Fast Fractal Compression using PSO Base Optimization Techniques A.Krishnamoorthy Visiting faculty Department Of ECE University College of Engineering panruti rishpci89@gmail.com S.Buvaneswari Visiting
More informationSTATISTICAL TEXTURE ANALYSIS OF ROAD FOR MOVING OBJECTIVES
U.P.B. Sci. Bull., Series C, Vol. 70, Iss. 4, 008 ISSN 454-34x STATISTICA TEXTURE ANAYSIS OF ROAD FOR MOVING OBJECTIVES Dan POPESCU, Rau DOBRESCU, Nicoleta ANGEESCU 3 Obiectivul articolului este acela
More informationCONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen
Proceeings of ACIVS 2002 (Avance Concepts for Intelligent Vision Systems), Ghent, Belgium, September 9-11, 2002 CONTENT-BASED RETRIEVAL OF DEFECT IMAGES Jukka Iivarinen an Jussi Pakkanen jukka.iivarinen@hut.fi,
More informationUNIT 9 INTERFEROMETRY
UNIT 9 INTERFEROMETRY Structure 9.1 Introuction Objectives 9. Interference of Light 9.3 Light Sources for 9.4 Applie to Flatness Testing 9.5 in Testing of Surface Contour an Measurement of Height 9.6 Interferometers
More informationOpen Access Adaptive Image Enhancement Algorithm with Complex Background
Sen Orers for Reprints to reprints@benthamscience.ae 594 The Open Cybernetics & Systemics Journal, 205, 9, 594-600 Open Access Aaptive Image Enhancement Algorithm with Complex Bacgroun Zhang Pai * epartment
More information6 Gradient Descent. 6.1 Functions
6 Graient Descent In this topic we will iscuss optimizing over general functions f. Typically the function is efine f : R! R; that is its omain is multi-imensional (in this case -imensional) an output
More informationCalculation on diffraction aperture of cube corner retroreflector
November 10, 008 / Vol., No. 11 / CHINESE OPTICS LETTERS 8 Calculation on iffraction aperture of cube corner retroreflector Song Li (Ó Ø, Bei Tang (», an Hui Zhou ( ï School of Electronic Information,
More informationRefinement of scene depth from stereo camera ego-motion parameters
Refinement of scene epth from stereo camera ego-motion parameters Piotr Skulimowski, Pawel Strumillo An algorithm for refinement of isparity (epth) map from stereoscopic sequences is propose. The metho
More information5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015)
5th International Conference on Avance Design an Manufacturing Engineering (ICADME 25) Research on motion characteristics an application of multi egree of freeom mechanism base on R-W metho Xiao-guang
More informationParticle Swarm Optimization Based on Smoothing Approach for Solving a Class of Bi-Level Multiobjective Programming Problem
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 17, No 3 Sofia 017 Print ISSN: 1311-970; Online ISSN: 1314-4081 DOI: 10.1515/cait-017-0030 Particle Swarm Optimization Base
More informationExercises of PIV. incomplete draft, version 0.0. October 2009
Exercises of PIV incomplete raft, version 0.0 October 2009 1 Images Images are signals efine in 2D or 3D omains. They can be vector value (e.g., color images), real (monocromatic images), complex or binary
More informationOnline Appendix to: Generalizing Database Forensics
Online Appenix to: Generalizing Database Forensics KYRIACOS E. PAVLOU an RICHARD T. SNODGRASS, University of Arizona This appenix presents a step-by-step iscussion of the forensic analysis protocol that
More informationSoftware Reliability Modeling and Cost Estimation Incorporating Testing-Effort and Efficiency
Software Reliability Moeling an Cost Estimation Incorporating esting-effort an Efficiency Chin-Yu Huang, Jung-Hua Lo, Sy-Yen Kuo, an Michael R. Lyu -+ Department of Electrical Engineering Computer Science
More informationA Framework for Dialogue Detection in Movies
A Framework for Dialogue Detection in Movies Margarita Kotti, Constantine Kotropoulos, Bartosz Ziólko, Ioannis Pitas, an Vassiliki Moschou Department of Informatics, Aristotle University of Thessaloniki
More informationModifying ROC Curves to Incorporate Predicted Probabilities
Moifying ROC Curves to Incorporate Preicte Probabilities Cèsar Ferri DSIC, Universitat Politècnica e València Peter Flach Department of Computer Science, University of Bristol José Hernánez-Orallo DSIC,
More informationStudy of Network Optimization Method Based on ACL
Available online at www.scienceirect.com Proceia Engineering 5 (20) 3959 3963 Avance in Control Engineering an Information Science Stuy of Network Optimization Metho Base on ACL Liu Zhian * Department
More informationQueueing Model and Optimization of Packet Dropping in Real-Time Wireless Sensor Networks
Queueing Moel an Optimization of Packet Dropping in Real-Time Wireless Sensor Networks Marc Aoun, Antonios Argyriou, Philips Research, Einhoven, 66AE, The Netherlans Department of Computer an Communication
More informationEstimating Velocity Fields on a Freeway from Low Resolution Video
Estimating Velocity Fiels on a Freeway from Low Resolution Vieo Young Cho Department of Statistics University of California, Berkeley Berkeley, CA 94720-3860 Email: young@stat.berkeley.eu John Rice Department
More informationSMART IMAGE PROCESSING OF FLOW VISUALIZATION
SMAR IMAGE PROCESSING OF FLOW VISUALIZAION H Li (A Rinoshika) 1, M akei, M Nakano 1, Y Saito 3 an K Horii 4 1 Department of Mechanical Systems Engineering, Yamagata University, Yamagata 99-851, JAPAN Department
More informationGeneralized Edge Coloring for Channel Assignment in Wireless Networks
Generalize Ege Coloring for Channel Assignment in Wireless Networks Chun-Chen Hsu Institute of Information Science Acaemia Sinica Taipei, Taiwan Da-wei Wang Jan-Jan Wu Institute of Information Science
More informationA Plane Tracker for AEC-automation Applications
A Plane Tracker for AEC-automation Applications Chen Feng *, an Vineet R. Kamat Department of Civil an Environmental Engineering, University of Michigan, Ann Arbor, USA * Corresponing author (cforrest@umich.eu)
More informationA Neural Network Model Based on Graph Matching and Annealing :Application to Hand-Written Digits Recognition
ITERATIOAL JOURAL OF MATHEMATICS AD COMPUTERS I SIMULATIO A eural etwork Moel Base on Graph Matching an Annealing :Application to Han-Written Digits Recognition Kyunghee Lee Abstract We present a neural
More informationFrequency Domain Parameter Estimation of a Synchronous Generator Using Bi-objective Genetic Algorithms
Proceeings of the 7th WSEAS International Conference on Simulation, Moelling an Optimization, Beijing, China, September 15-17, 2007 429 Frequenc Domain Parameter Estimation of a Snchronous Generator Using
More informationFigure 1: 2D arm. Figure 2: 2D arm with labelled angles
2D Kinematics Consier a robotic arm. We can sen it commans like, move that joint so it bens at an angle θ. Once we ve set each joint, that s all well an goo. More interesting, though, is the question of
More informationA Duality Based Approach for Realtime TV-L 1 Optical Flow
A Duality Base Approach for Realtime TV-L 1 Optical Flow C. Zach 1, T. Pock 2, an H. Bischof 2 1 VRVis Research Center 2 Institute for Computer Graphics an Vision, TU Graz Abstract. Variational methos
More informationCluster Center Initialization Method for K-means Algorithm Over Data Sets with Two Clusters
Available online at www.scienceirect.com Proceia Engineering 4 (011 ) 34 38 011 International Conference on Avances in Engineering Cluster Center Initialization Metho for K-means Algorithm Over Data Sets
More informationFast Window Based Stereo Matching for 3D Scene Reconstruction
The International Arab Journal of Information Technology, Vol. 0, No. 3, May 203 209 Fast Winow Base Stereo Matching for 3D Scene Reconstruction Mohamma Mozammel Chowhury an Mohamma AL-Amin Bhuiyan Department
More informationText Particles Multi-band Fusion for Robust Text Detection
Text Particles Multi-ban Fusion for Robust Text Detection Pengfei Xu, Rongrong Ji, Hongxun Yao, Xiaoshuai Sun, Tianqiang Liu, an Xianming Liu School of Computer Science an Engineering Harbin Institute
More informationMultiresolution Texture Analysis of Surface Reflection Images
Multiresolution Texture Analysis of Surface Reflection Images Leena Lepistö, Iivari Kunttu, Jorma Autio, and Ari Visa Tampere University of Technology, Institute of Signal Processing P.O. Box 553, FIN-330
More informationRobust Camera Calibration for an Autonomous Underwater Vehicle
obust Camera Calibration for an Autonomous Unerwater Vehicle Matthew Bryant, Davi Wettergreen *, Samer Aballah, Alexaner Zelinsky obotic Systems Laboratory Department of Engineering, FEIT Department of
More informationResearch Article Research on Law s Mask Texture Analysis System Reliability
Research Journal of Applie Sciences, Engineering an Technology 7(19): 4002-4007, 2014 DOI:10.19026/rjaset.7.761 ISSN: 2040-7459; e-issn: 2040-7467 2014 Maxwell Scientific Publication Corp. Submitte: November
More informationBayesian localization microscopy reveals nanoscale podosome dynamics
Nature Methos Bayesian localization microscopy reveals nanoscale poosome ynamics Susan Cox, Ewar Rosten, James Monypenny, Tijana Jovanovic-Talisman, Dylan T Burnette, Jennifer Lippincott-Schwartz, Gareth
More informationState Indexed Policy Search by Dynamic Programming. Abstract. 1. Introduction. 2. System parameterization. Charles DuHadway
State Inexe Policy Search by Dynamic Programming Charles DuHaway Yi Gu 5435537 503372 December 4, 2007 Abstract We consier the reinforcement learning problem of simultaneous trajectory-following an obstacle
More informationA FUZZY FRAMEWORK FOR SEGMENTATION, FEATURE MATCHING AND RETRIEVAL OF BRAIN MR IMAGES
A FUZZY FRAMEWORK FOR SEGMENTATION, FEATURE MATCHING AND RETRIEVAL OF BRAIN MR IMAGES Archana.S 1 an Srihar.S 2 1 Department of Information Science an Technology, College of Engineering, Guiny archana.santhira@gmail.com
More informationDepth Sizing of Surface Breaking Flaw on Its Open Side by Short Path of Diffraction Technique
17th Worl Conference on Nonestructive Testing, 5-8 Oct 008, Shanghai, China Depth Sizing of Surface Breaking Flaw on Its Open Sie by Short Path of Diffraction Technique Hiroyuki FUKUTOMI, Shan LIN an Takashi
More informationUsing Vector and Raster-Based Techniques in Categorical Map Generalization
Thir ICA Workshop on Progress in Automate Map Generalization, Ottawa, 12-14 August 1999 1 Using Vector an Raster-Base Techniques in Categorical Map Generalization Beat Peter an Robert Weibel Department
More informationSkyline Community Search in Multi-valued Networks
Syline Community Search in Multi-value Networs Rong-Hua Li Beijing Institute of Technology Beijing, China lironghuascut@gmail.com Jeffrey Xu Yu Chinese University of Hong Kong Hong Kong, China yu@se.cuh.eu.h
More informationTight Wavelet Frame Decomposition and Its Application in Image Processing
ITB J. Sci. Vol. 40 A, No., 008, 151-165 151 Tight Wavelet Frame Decomposition an Its Application in Image Processing Mahmu Yunus 1, & Henra Gunawan 1 1 Analysis an Geometry Group, FMIPA ITB, Banung Department
More informationDefect Detection of Regular Patterned Fabric by Spectral Estimation Technique and Rough Set Classifier
Defect Detection of Regular Patterned Fabric by Spectral Estimation Technique and Rough Set Classifier Mr..Sudarshan Deshmukh. Department of E&TC Siddhant College of Engg, Sudumbare, Pune Prof. S. S. Raut.
More informationShift-map Image Registration
Shift-map Image Registration Svärm, Linus; Stranmark, Petter Unpublishe: 2010-01-01 Link to publication Citation for publishe version (APA): Svärm, L., & Stranmark, P. (2010). Shift-map Image Registration.
More informationFigure 1: Schematic of an SEM [source: ]
EECI Course: -9 May 1 by R. Sanfelice Hybri Control Systems Eelco van Horssen E.P.v.Horssen@tue.nl Project: Scanning Electron Microscopy Introuction In Scanning Electron Microscopy (SEM) a (bunle) beam
More informationA New Search Algorithm for Solving Symmetric Traveling Salesman Problem Based on Gravity
Worl Applie Sciences Journal 16 (10): 1387-1392, 2012 ISSN 1818-4952 IDOSI Publications, 2012 A New Search Algorithm for Solving Symmetric Traveling Salesman Problem Base on Gravity Aliasghar Rahmani Hosseinabai,
More informationParticle Swarm Optimization with Time-Varying Acceleration Coefficients Based on Cellular Neural Network for Color Image Noise Cancellation
Particle Swarm Optimization with Time-Varying Acceleration Coefficients Base on Cellular Neural Network for Color Image Noise Cancellation Te-Jen Su Jui-Chuan Cheng Yang-De Sun 3 College of Information
More information1 Surprises in high dimensions
1 Surprises in high imensions Our intuition about space is base on two an three imensions an can often be misleaing in high imensions. It is instructive to analyze the shape an properties of some basic
More informationYet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama and Hayato Ohwada Faculty of Sci. and Tech. Tokyo University of Scien
Yet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama an Hayato Ohwaa Faculty of Sci. an Tech. Tokyo University of Science, 2641 Yamazaki, Noa-shi, CHIBA, 278-8510, Japan hiroyuki@rs.noa.tus.ac.jp,
More informationEFFICIENT STEREO MATCHING BASED ON A NEW CONFIDENCE METRIC. Won-Hee Lee, Yumi Kim, and Jong Beom Ra
th European Signal Processing Conference (EUSIPCO ) Bucharest, omania, August 7-3, EFFICIENT STEEO MATCHING BASED ON A NEW CONFIDENCE METIC Won-Hee Lee, Yumi Kim, an Jong Beom a Department of Electrical
More informationNET Institute*
NET Institute* www.netinst.org Working Paper #08-24 October 2008 Computer Virus Propagation in a Network Organization: The Interplay between Social an Technological Networks Hsing Kenny Cheng an Hong Guo
More information4.2 Implicit Differentiation
6 Chapter 4 More Derivatives 4. Implicit Differentiation What ou will learn about... Implicitl Define Functions Lenses, Tangents, an Normal Lines Derivatives of Higher Orer Rational Powers of Differentiable
More informationDivide-and-Conquer Algorithms
Supplment to A Practical Guie to Data Structures an Algorithms Using Java Divie-an-Conquer Algorithms Sally A Golman an Kenneth J Golman Hanout Divie-an-conquer algorithms use the following three phases:
More informationSection 19. Thin Prisms
Section 9 Thin Prisms 9- OPTI-50 Optical Design an Instrumentation I opyright 08 John E. Greivenkamp Thin Prism Deviation Thin prisms introuce small angular beam eviations an are useful as alignment evices.
More informationLakshmish Ramanna University of Texas at Dallas Dept. of Electrical Engineering Richardson, TX
Boy Sensor Networks to Evaluate Staning Balance: Interpreting Muscular Activities Base on Inertial Sensors Rohith Ramachanran Richarson, TX 75083 rxr057100@utallas.eu Gaurav Prahan Dept. of Computer Science
More informationCHAPTER 2 TEXTURE CLASSIFICATION METHODS GRAY LEVEL CO-OCCURRENCE MATRIX AND TEXTURE UNIT
CHAPTER 2 TEXTURE CLASSIFICATION METHODS GRAY LEVEL CO-OCCURRENCE MATRIX AND TEXTURE UNIT 2.1 BRIEF OUTLINE The classification of digital imagery is to extract useful thematic information which is one
More informationSection 20. Thin Prisms
OPTI-0/0 Geometrical an Instrumental Optics opyright 08 John E. Greivenkamp 0- Section 0 Thin Prisms Thin Prism Deviation Thin prisms introuce small angular beam eviations an are useful as alignment evices.
More informationVision-based Multi-Robot Simultaneous Localization and Mapping
Vision-base Multi-Robot Simultaneous Localization an Mapping Hassan Hajjiab an Robert Laganière VIVA Research Lab School of Information Technology an Engineering University of Ottawa, Ottawa, Canaa, K1N
More informationMORA: a Movement-Based Routing Algorithm for Vehicle Ad Hoc Networks
: a Movement-Base Routing Algorithm for Vehicle A Hoc Networks Fabrizio Granelli, Senior Member, Giulia Boato, Member, an Dzmitry Kliazovich, Stuent Member Abstract Recent interest in car-to-car communications
More informationParts Assembly by Throwing Manipulation with a One-Joint Arm
21 IEEE/RSJ International Conference on Intelligent Robots an Systems, Taipei, Taiwan, October, 21. Parts Assembly by Throwing Manipulation with a One-Joint Arm Hieyuki Miyashita, Tasuku Yamawaki an Masahito
More informationDigital fringe profilometry based on triangular fringe patterns and spatial shift estimation
University of Wollongong Research Online Faculty of Engineering an Information Sciences - Papers: Part A Faculty of Engineering an Information Sciences 4 Digital fringe profilometry base on triangular
More informationAnyTraffic Labeled Routing
AnyTraffic Labele Routing Dimitri Papaimitriou 1, Pero Peroso 2, Davie Careglio 2 1 Alcatel-Lucent Bell, Antwerp, Belgium Email: imitri.papaimitriou@alcatel-lucent.com 2 Universitat Politècnica e Catalunya,
More informationThreshold Based Data Aggregation Algorithm To Detect Rainfall Induced Landslides
Threshol Base Data Aggregation Algorithm To Detect Rainfall Inuce Lanslies Maneesha V. Ramesh P. V. Ushakumari Department of Computer Science Department of Mathematics Amrita School of Engineering Amrita
More informationComparative Study of Projection/Back-projection Schemes in Cryo-EM Tomography
Comparative Stuy of Projection/Back-projection Schemes in Cryo-EM Tomography Yu Liu an Jong Chul Ye Department of BioSystems Korea Avance Institute of Science an Technology, Daejeon, Korea ABSTRACT In
More informationInverse Model to Determine the Optimal Number of Drops of RDC Column Using Fuzzy Approach
Inverse Moel to Determine the Optimal Number of Drops of RDC Column Using Fuzzy Approach 1 HAFEZ IBRAHIM, 2 JAMALLUDIN TALIB, 3 NORMAH MAAN Department of Mathematics Universiti Teknologi Malaysia 81310
More informationNeural Network based textural labeling of images in multimedia applications
Neural Network based textural labeling of images in multimedia applications S.A. Karkanis +, G.D. Magoulas +, and D.A. Karras ++ + University of Athens, Dept. of Informatics, Typa Build., Panepistimiopolis,
More informationLecture 6: Multimedia Information Retrieval Dr. Jian Zhang
Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang NICTA & CSE UNSW COMP9314 Advanced Database S1 2007 jzhang@cse.unsw.edu.au Reference Papers and Resources Papers: Colour spaces-perceptual, historical
More informationA fast embedded selection approach for color texture classification using degraded LBP
A fast embee selection approach for color texture classification using egrae A. Porebski, N. Vanenbroucke an D. Hama Laboratoire LISIC - EA 4491 - Université u Littoral Côte Opale - 50, rue Ferinan Buisson
More informationA Cost Model For Nearest Neighbor Search. High-Dimensional Data Space
A Cost Moel For Nearest Neighbor Search in High-Dimensional Data Space Stefan Berchtol University of Munich Germany berchtol@informatikuni-muenchene Daniel A Keim University of Munich Germany keim@informatikuni-muenchene
More informationCorrelation-based color mosaic interpolation using a connectionist approach
Correlation-base color mosaic interpolation using a connectionist approach Gary L. Embler * Agilent Technologies, Inc. 75 Bowers Avenue, MS 87H Santa Clara, California 9554 USA ABSTRACT This paper presents
More informationA fringe period unwrapping technique for digital fringe profilometry based on spatial shift estimation
University of Wollongong Research Online Faculty of Informatics - Papers (Archive Faculty of Engineering an Information Sciences 29 A fringe perio unrapping technique for igital fringe profilometry base
More informationBends, Jogs, And Wiggles for Railroad Tracks and Vehicle Guide Ways
Ben, Jogs, An Wiggles for Railroa Tracks an Vehicle Guie Ways Louis T. Klauer Jr., PhD, PE. Work Soft 833 Galer Dr. Newtown Square, PA 19073 lklauer@wsof.com Preprint, June 4, 00 Copyright 00 by Louis
More informationShort-term prediction of photovoltaic power based on GWPA - BP neural network model
Short-term preiction of photovoltaic power base on GWPA - BP neural networ moel Jian Di an Shanshan Meng School of orth China Electric Power University, Baoing. China Abstract In recent years, ue to China's
More informationA Comparative Evaluation of Iris and Ocular Recognition Methods on Challenging Ocular Images
A Comparative Evaluation of Iris an Ocular Recognition Methos on Challenging Ocular Images Vishnu Naresh Boeti Carnegie Mellon University Pittsburgh, PA 523 naresh@cmu.eu Jonathon M Smereka Carnegie Mellon
More informationA Convex Clustering-based Regularizer for Image Segmentation
Vision, Moeling, an Visualization (2015) D. Bommes, T. Ritschel an T. Schultz (Es.) A Convex Clustering-base Regularizer for Image Segmentation Benjamin Hell (TU Braunschweig), Marcus Magnor (TU Braunschweig)
More informationA half-scan error reduction based algorithm for cone-beam CT
Journal of X-Ray Science an Technology 12 (2004) 73 82 73 IOS Press A half-scan error reuction base algorithm for cone-beam CT Kai Zeng a, Zhiqiang Chen a, Li Zhang a an Ge Wang a,b a Department of Engineering
More informationA PSO Optimized Layered Approach for Parametric Clustering on Weather Dataset
Vol.3, Issue.1, Jan-Feb. 013 pp-504-508 ISSN: 49-6645 A PSO Optimize Layere Approach for Parametric Clustering on Weather Dataset Shikha Verma, 1 Kiran Jyoti 1 Stuent, Guru Nanak Dev Engineering College
More informationDetecting Overlapping Communities from Local Spectral Subspaces
Detecting Overlapping Communities from Local Spectral Subspaces Kun He, Yiwei Sun Huazhong University of Science an Technology Wuhan 430074, China Email: {brooklet60, yiweisun}@hust.eu.cn Davi Binel, John
More informationReal Time On Board Stereo Camera Pose through Image Registration*
28 IEEE Intelligent Vehicles Symposium Einhoven University of Technology Einhoven, The Netherlans, June 4-6, 28 Real Time On Boar Stereo Camera Pose through Image Registration* Fai Dornaika French National
More informationMultilevel Linear Dimensionality Reduction using Hypergraphs for Data Analysis
Multilevel Linear Dimensionality Reuction using Hypergraphs for Data Analysis Haw-ren Fang Department of Computer Science an Engineering University of Minnesota; Minneapolis, MN 55455 hrfang@csumneu ABSTRACT
More informationLinear First-Order PDEs
MODULE 2: FIRST-ORDER PARTIAL DIFFERENTIAL EQUATIONS 9 Lecture 2 Linear First-Orer PDEs The most general first-orer linear PDE has the form a(x, y)z x + b(x, y)z y + c(x, y)z = (x, y), (1) where a, b,
More informationArchitecture Design of Mobile Access Coordinated Wireless Sensor Networks
Architecture Design of Mobile Access Coorinate Wireless Sensor Networks Mai Abelhakim 1 Leonar E. Lightfoot Jian Ren 1 Tongtong Li 1 1 Department of Electrical & Computer Engineering, Michigan State University,
More informationA Modified Immune Network Optimization Algorithm
IAENG International Journal of Computer Science, 4:4, IJCS_4_4_3 A Moifie Immune Network Optimization Algorithm Lu Hong, Joarer Kamruzzaman Abstract This stuy proposes a moifie artificial immune network
More informationInvestigation into a new incremental forming process using an adjustable punch set for the manufacture of a doubly curved sheet metal
991 Investigation into a new incremental forming process using an ajustable punch set for the manufacture of a oubly curve sheet metal S J Yoon an D Y Yang* Department of Mechanical Engineering, Korea
More informationA Versatile Model-Based Visibility Measure for Geometric Primitives
A Versatile Moel-Base Visibility Measure for Geometric Primitives Marc M. Ellenrieer 1,LarsKrüger 1, Dirk Stößel 2, an Marc Hanheie 2 1 DaimlerChrysler AG, Research & Technology, 89013 Ulm, Germany 2 Faculty
More informationCoupling the User Interfaces of a Multiuser Program
Coupling the User Interfaces of a Multiuser Program PRASUN DEWAN University of North Carolina at Chapel Hill RAJIV CHOUDHARY Intel Corporation We have evelope a new moel for coupling the user-interfaces
More informationI. Introuction With the evolution of imaging technology, an increasing number of image moalities becomes available. In remote sensing, sensors are use
A multivalue image wavelet representation base on multiscale funamental forms P. Scheuners Vision Lab, Department ofphysics, University ofantwerp, Groenenborgerlaan 7, 00 Antwerpen, Belgium Tel.: +3/3/8
More informationA Classification of 3R Orthogonal Manipulators by the Topology of their Workspace
A Classification of R Orthogonal Manipulators by the Topology of their Workspace Maher aili, Philippe Wenger an Damien Chablat Institut e Recherche en Communications et Cybernétique e Nantes, UMR C.N.R.S.
More informationDiscriminative Filters for Depth from Defocus
Discriminative Filters for Depth from Defocus Fahim Mannan an Michael S. Langer School of Computer Science, McGill University Montreal, Quebec HA 0E9, Canaa. {fmannan, langer}@cim.mcgill.ca Abstract Depth
More informationFuzzy Clustering in Parallel Universes
Fuzzy Clustering in Parallel Universes Bern Wisweel an Michael R. Berthol ALTANA-Chair for Bioinformatics an Information Mining Department of Computer an Information Science, University of Konstanz 78457
More information