CHAPTER 5 PALMPRINT RECOGNITION WITH ENHANCEMENT
|
|
- Cornelia Robinson
- 5 years ago
- Views:
Transcription
1 145 CHAPTER 5 PALMPRINT RECOGNITION WITH ENHANCEMENT 5.1 INTRODUCTION This chapter discusses the application of enhancement technique in palmprint recognition system. Section 5.2 describes image sharpening methods. Advanced palmprint recognition system is discussed in Section 5.3. A palmprint recognition using Symbolic Aggregate approximation (SAX) features is discussed in Section 5.4. Palmprint recognition using multiple palmprint features with enhanced palmprint image is given in Section 5.5. The performance measures are given in Section 5.6. The results are discussed in Section 5.7.The performance of the proposed enhancement technique is compared with the HE technique. Summary of the chapter is given in Section 5.8. There exist three different categories for palmprint authentication (Zhang,2004), divided on the basis of extracted features; (i) line-based approaches (Han et al 2003, Zhang et al 1999, Han et al 2007 ) (ii) appearance-based approaches (Lu et al 2003) and (iii) texture-based approaches. Line-based methods are based on line matching, line detection, crease detection, morphological operators etc. Morphological operators (Han et al 2003) can be used in the feature extraction process in order to obtain the feature vectors. Datum point invariant and the line feature matching technique
2 146 (Zhang et al 1999) for the verification process are not appropriate for many on-line security systems, since it is difficult to extract principal lines from a low resolution palmprint image. The required recognition rates and computational efficiency are not fully achieved here. Other issues in the linebased approaches include the existence of similar line features in many palmprints, and the thickness and width of the different lines are not taken into account which is very critical for differentiating palmprints. Appearance-based approaches are based on the analysis of principal component and linear discriminate. The original training palmprints are transformed into small groups of characteristic feature images called eigenpalms (Lu et al 2003) by means of Karhunen Loeve (K L) transform. But the authentication performance of these eigenpalms is reduced when it is applied in real time applications. In texture-based approach, texture features are extracted by means of gabor filter, discrete cosine transform, ordinal filter, laws mask, discrete fourier transform, wavelets and so on. Even though the Gabor filter (Kong et al 2003) gives accurate time-frequency location and robustness against varying image s brightness and contrast, it involves high computational cost and time delay. Difficulty in setting an appropriate filter parameter causes identification performance to depend much on the training set used for parameter selection. Orthogonal line ordinal feature (Sun et al 2005) is currently the best ordinal measure for palmprint representation; still its theoretical foundation has not been well formulated. Wavelet Energy Feature technique s (Wu et al 2002) ability to distinguish palms is very strong because it can reflect the wavelet energy distribution of the principal lines, wrinkles and ridges in different directions at varying wavelet decomposition levels. Disadvantages of this method are its sensitiveness towards noise, the requirement of high resolution images, implementation cost and time
3 147 complexity. Fourier transform method (Li et al 2002) is used to ignore the abundant textural details of a palm, and the extracted features are highly influenced by the lighting situations. A huge storage of database to store image templates affects the system s simplicity. Personal verification using palmprint and hand geometry biometric (Kumar et al 2003) does verification by integrating hand geometry features. Palmprint and hand geometry features are acquired using a digital camera. These images are aligned and then used to extract palmprint and hand geometry features. These features are then examined for their individual and combined performances. The image acquisition setup used in this work is inherently simple and it does not employ any special illumination, nor does it use any pegs to cause any inconvenience to the users. Hierarchical palmprint identification via multiple feature extraction (You et al 2002) describes a new method to authenticate individuals based on palmprint identifcation and verification. A texture-based dynamic selection scheme is used to facilitate the fast search for the best matching of the sample in the database in a hierarchical fashion. The global texture energy, which is characterized with high convergence of inner-palm similarities and good dispersion of inter-palm discrimination, is used to guide the dynamic selection of a small set of similar candidates from the database at coarse level for further processing. Multiple palmprint features are used by Nanni and Lumini (2009) for accurate palmprint recognition. Combining multiple classifiers by averaging or by multiplying (Tax et al 2000) combines observations from different sources. Palmprint-based recognition system using phase difference information (Badrinath et al 2012) uses histogram equalization for enhancing the contrast of the palmprint image. Most of the works did not give any attempt to incorporate the enhancement techniques in biometric palmprint images to achieve
4 148 performance improvement. In most of the prior systems, the enhancement stage got little attention. The enhancement of the input image can deeply affect the output of the system. This work incorporates curvelet and RHE techniques for enhancement of the palmprint image. Curvelet is used for removing noise in the palmprint image, and RHE is used for improving the contrast of the palmprint image. Applying curvelet and RHE improves the overall performance of the system. 5.2 IMAGE SHARPENING Image sharpening refers to any enhancement technique that highlights edges and fine details in an image Highpass Filter The highpass filter allows high frequency data to pass through, suppressing low frequency data. Highpass filtering is useful for finding edges, for enhancing lines and for sharpening an image. Small window size will enhance small features and details. Large window size will allow large features to pass through, suppressing or eliminating smaller features. In general, image filters operate by performing a mathematical operation on each pixel using the pixels surrounding it to generate the result. For instance, a low pass filter changes the value of each pixel in the image to the average of it and the pixels in its neighborhood. This average replaces the gray level of the selected pixel gray level. The chosen window size determines how big that neighborhood is. For instance, a 3x3 size has eight pixels all round the sample pixel in the center of the window. The windows move through every pixel in the image, performing the same mathematical operation using the surrounding pixels in
5 149 its neighborhood to determine the target pixel s new value. The mask for the highpass filter is given in Figure Figure 5.1 3x3 mask for highpass filter This filter can be viewed as a kind of slope filter in which it highlights pixels that have values that are different from their neighboring pixels. The greater the difference, the higher or lower (visually brighter or darker) the output value will be Unsharp Masking The standard tool used for sharpening in order to make edges clear and distinct is known as UM filter. An UM filter cannot create additional detail, but it helps to emphasize texture and greatly enhance the appearance of detail. It performs sharpening using a procedure that subtracts an unsharp or smoothed version of an image from the original image. The unsharp filtering technique is also used in other areas such as photographic and printing industries. Unsharp masking filter produces an edge image g(x,y) from an input image f(x,y) as given in Equation(5.1) g(x,y) = f(x,y) f smooth (x,y) (5.1) where f smooth (x,y) is a smoothed version of f(x,y). The complete unsharp sharpening operator for the UM filter is shown in Figure 5.2 below.
6 150 f(x,y) Smooth - g(x,y) f sharp (x,y) Figure 5.2 The UM filtering operator The output of the UM filter is given in Equation (5.2) f sharp (x,y) = f(x,y) + k * g(x,y) (5.2) where k is a scaling constant. Reasonable values for k vary between 0.2 and 0.7, with the larger values providing higher rate of sharpening. 5.3 ADVANCED PALMPRINT RECOGNITION SYSTEM The system has two phases, namely enrollment phase and identification phase. During enrollment phase, the system will store the multiple features in the database. During the identification phase, the features are extracted from the input image using the same algorithm and are compared with the features in the database. This study proposes a highly reliable method called advanced palmprint recognition using curvelet transform and RHE to overcome the drawbacks of the existing palmprint authentication systems and ensures high accuracy and efficiency. The block diagram of the advanced palmprint recognition system is given in Figure 5.3. Various steps involved in the proposed method are palmprint acquisition, enhancement, feature extraction and palmprint matching. The noise in the input image is removed by curvelet transform and then equalized by RHE technique. The features are extracted from the enhanced image. Two sets of features are extracted in this work, (i) SAX features and (ii) multiple palmprint features.
7 151 Palmprint image Palmprint image Image enhancement Image enhancement Feature extraction Feature extraction Store in Database Palmprint matching Decision Reject Accept Figure 5.3 Block diagram of the advanced palmprint recognition system 5.4 PALMPRINT RECOGNITION USING SAX FEATURES The proposed palmprint recognition system using SAX features is shown in Figure 5.4. It composes input acquisition, enhancement, feature extraction and recognition stages. The input acquisition and enhancement steps are discussed in chapter I, II, and III. This chapter mainly focuses on the feature extraction and recognition steps. The block diagram of palmprint recognition using SAX features is shown in Figure 5.4.
8 152 Input image Gray scale conversion Curvelet transform RHE Division of image into blocks 2D decomposition into 1D sequence Convert the values into symbols Calculate threshold to determine breakpoints Find mean for each block MINDIST calculation Database Matching Result Accept Reject Figure 5.4 Block diagram of palmprint recognition using SAX features Here, an extension of the SAX is used which represents the 2D data using a 2D matrix of symbols. The method uses the gray scale information of captured images in order to reduce the complexity of execution Introduction to SAX The symbolic demonstration of time series is called SAX. It transforms the original time-series data into symbolic strings where Piecewise Aggregate Approximation (PAA)-based algorithm is used that provides simplicity and low computational complexity. Since SAX requires less
9 153 storage space, it is used for solving many challenges associated with the present data mining tasks. In addition, the symbolic representation allows researchers go further to the available wealth of data structures and string manipulation algorithms in computer science, and also for many applications in bioinformatics and data mining (Wang et al 2004). SAX algorithm transforms a time-series X of length n into the string of arbitrary length w, where w < n, using a table that contains the breakpoints. Each value in the table corresponds to each level in the time series graph which is further represented by symbols in the alphabet array of size >2 which finally forms the string of length w. Dimensionality reduction is based on two parameters named sax length (w) and number of symbols used in the alphabet array. The algorithm consists of two steps. In the first step, it transforms the original time-series into a PAA representation ( C ) and this intermediate representation is further converted into alphabetic string ( Ĉ ) in the second step. Usage of PAA approach in the first step gives the advantage of being simple and efficient in dimensionality reduction and provides lower bounding property. The second step, where the actual conversion of PAA coefficients into alphabets is also computationally efficient, shows the contractive property of symbolic distance. Generating SAX from PAA representation of a time series is implemented in a way which produces symbols that correspond to the varying magnitude of time-series data (Lin et al 2003). Figure 5.5 shows the conversion of times series into SAX representation. Figure 5.5 (a) is the original time series data. Figure 5.5 (b) shows the corresponding PAA representation and Figure 5.5(c) shows the SAX representation.
10 154 (a) (b) (c) Figure 5.5 Times series to SAX representation (a) Time series (b) PAA representation (c) SAX representation D SAX Representation for the Proposed System The size of the gray scale image matrix Q, is m x n. It is then divided into equal size blocks of size w 1 x w 2 and the mean value of the data inside each block is calculated to form the dimensionality reduced representation. The newly formed mean value matrix is named as Q of size w 1 x w 2. The (i th, j th ) element of Q or the mean value of each block in Q can be calculated by using the Equation (5.3) Q(i, j) 1 w w 1 2 x m i w1 m i 1 w1 1 y n j w 2 n j 1 w 2 1 Q x, y (5.3) Breakpoints have to be applied to convert Q into a symbol matrix S or the 2D SAX representation. For this, a threshold value is used so that breakpoints can be calculated easily. Threshold value is calculated using the Equation (5.4)
11 155 T max min SAX level (5.4) where max is the maximum value in the Q matrix, min is the minimum value in the Q matrix, and SAX level is equal to number of symbols to be used. For example, if four SAX level are chosen, five breakpoints have to be calculated. The breakpoints are min, min+t, min+2t, min+3t and max. Then, one symbol is used to represent the values between min and min+t, and another symbol is used for the values between min+t and min+2t and so on. In this manner, the symbol matrix S, the 2D SAX representation can be obtained. Then, this two dimensional data is decomposed into one dimensional (1D) sequences using a progressive scan (Chen et al 2010). These 2D SAX representations as strings are stored in the database as palmprint template Palmprint Matching The MINDIST between two corresponding strings is measured and this is adopted as the similarity measurement of the corresponding two palmprints. Given two SAX strings Qˆ qˆ 11,qˆ 12,... qˆ w 1 w and Ĉ ĉ 2 11,ĉ12,... ĉw 1 w, 2 their MINDIST can be calculated using the Equation (5.5) where dist() can be implemented using lookup table as given in Figure 5.1. If the MINDIST is smaller, then the two palmprints are more similar. w w mn 1 2 MINDIST( Qˆ,Ĉ) dist(qˆ,ĉ ) 2 (5.5) w w i 1 j 1 ij ij 1 2 where m x n is the size of the image and w 1 x w 2 is the SAX length.
12 156 Table 5.1 Lookup table for calculating dist() function with four SAX level a b c d a b c d subjects from IIT Database are used for recognition. Four samples are taken for each subject. The features of the palmprint image to be recognized are checked with the features of the palmprint images stored in the system s database. If a match is found, then the person is authenticated, otherwise the person is unauthenticated. Verification is done with HE,curvelet,RHE and curvelet & RHE methods. It is proceeded with two phases in which in the first phase, 117 random palmprint images from the IIT database that are also contained in the system s database were tested. In the second phase, 117 palmprint images were taken for testing from the IIT database that is not in the system s database. Figure 5.6 Sample palmprints Few samples of palmprints are shown in Figure 5. 6, in which palmprints in the same column are from the same palm, and the palmprints in
13 157 the first and second rows are from session one and session two respectively. Figure 5. 7 shows the output of the palmprint enhancement and feature extraction process where block size (w1 w2) is set as 8 8 and the SAX level as 4. The SAX string is used as palmprint templates for experiment-matching process. Figure 5.8 shows the four samples of a palmprint from an individual and their corresponding SAX representation. (a) (b) (c) (d) ddbbdddccccbbbbbddbbcddbbcbbccccddbcddcccccbccccdcbbc ccbbbcbcbcccbbbbbbbbbbbbbbccbbcccabbbbbbbbbdbccccbbb bbbbabbcbccdbccbbbaaabacbcdcbccccbaaaaacccdbcccccbbaab cbcdcbcccdcbbbbbcccdbdddccbbbbbccdddbddcbccbabbcccdcc dcbcccabcccbccbcdbccbbaaccccccbcbccccbaacccc (e) Figure 5.7 Palmprint enhancement and feature extraction. (a) The input image. (b) image after applying curvelet (c) RHE equalized image (d) SAX representation (e) SAX string (a) (b) (c) (d) (e) (f) (g) (h) Figure 5.8 (a),(b),(c) and(d) palmprints from the same palm, (e),(f),(g) and (h) corresponding SAX representation
14 PALMPRINT RECOGNITION USING MULTIPLE PALMPRINT FEATURES This system uses a combination of four major representations of the palmprint. i.e Discrete Cosine Transform (DCT), Local Binary Pattern (LBP), GB (Gabor features) and line features. The sum rule is used for fusing multiple features of the palmprint. Decision will be taken based on the distance between the input image features and features of the images in the database. Here, the first stage of the system is to perform the enhancement of the palmprint image. Curvelet, RHE and highpass filter are used for enhancement of the palmprint image. The second stage of the system is feature extraction. The system extracts multiple features from palmprint image. The output of the feature extraction process is the feature vector with variance. These feature vectors can be used for the unique representation of a palmprint image. Figure 5.9 shows the block diagram of feature extraction process. Enhanced image Feature extraction GB LBP DCT Line features Store the feature vectors Figure 5.9 Block diagram of feature extraction stage
15 Extraction of Gabor Features Gabor filter is a linear filter used for edge detection. Frequency and orientation representations of Gabor filters are similar to those of the human visual system, and they have been found to be particularly appropriate for texture representation and discrimination. In the spatial domain, a 2D Gabor filter is a Gaussian kernel function modulated by a sinusoidal plane wave. The Gabor filters are self-similar. Figure 5.10 shows the Gabor Filters used for feature extraction. By using Gabor filter, system extracts texture features which can be employed for palmprint verification. Palmprint image is filtered with a bank of 36 Gabor filters to generate 36 filtered images. Here, the orientation is varied from 0 to 2 with 10 degree increments. Kong et al (2003) described that filters with frequency and standard deviation achieved high recognition rate. Hence, the frequency is chosen as and sigma is chosen as Each of the filtered images are overlaid one over the other so that line features in all directions get enhanced. The components of palmprint crease and lines in different directions are captured by each of these filters. The extracted prominent texture features can be used for unique representation of a palmprint image. Figure 5.11 shows the extracted Gabor feature by superimposing all the Gabor-filtered images. Figure 5.10 Gabor filters
16 160 Figure 5.11 Gabor features Figure 5.12 Gabor feature vector Gabor feature vector template is created using the technique of dimensionality reduction. The dimension of the image gets reduced in such a way that nine pixels (one pixel surrounded by eight pixels) get reduced to a single pixel and its value will be the average of the surrounding pixel. This is the simple technique which uses the mean of the block for dimensionality reduction. The technique of dimensionality reduction helps us to rectify the rotational invariance of the input palmprint images and reduces the complexity. Thus the system can accurately identify the input palmprint image. Gabor feature vector after dimension reduction is given Figure Extraction of DCT Features A DCT expresses a sequence of finitely many data points in terms of a sum of cosine functions oscillating at different frequencies. DCT is a separable linear transformation. The two-dimensional DCT is equivalent to a one-dimensional DCT in single dimension followed by a one-dimensional DCT in the other dimension. The salient information of the DCT exists in the coefficients with low frequencies. Because of this property of the DCT, most
17 161 DCT components are typically very small in magnitude. Discarding the small coefficients from the DCT representation, only a small error is resulted. Figure 5.13 (a) is a sample image and the enhanced image is given in Figure 5.13(b). Figure 5.13 (c) shows the DCT features. DCT coefficients with higher variance are retained, and remaining small coefficients which introduce a small error in the reconstructed image from the DCT representations are discarded. For dimensionality reduction, the first N co-efficients are retained. (a) (b) (c) Figure 5.13 (a) Original image (b) Enhanced image (c) DCT features Extraction of LBP Features LBP is a simple yet very efficient texture operator which labels the pixels of an image by thresholding the neighborhood of each pixel and considers the result as a binary number. Due to its discriminative power and computational simplicity, LBP texture operator has become a popular approach in various applications. The most important property of the LBP operator in real-world applications is its robustness to monotonic gray-scale changes. Another important property is its computational simplicity, which makes it possible to analyze images in challenging real-time settings. Figure 5.14 shows LBP feature and its histogram.
18 162 (a) (b) Figure 5.14(a) LBP features (b) LBP histogram Extraction of Lines and Ridges The lines and ridges are unique for each palmprint image. The palmprint image will contain mainly three principal lines, namely heart line, head line and life line. In addition to that it has wrinkles and ridges. The principal lines will be more prominent in palmprint images. The enhanced image is sharpened to highlight the line features. Palmprint image is sharpened using unsharp masking. By creating the binary image from the sharpened image, the lines and ridges are extracted. Figure 5.15 shows the extracted line features. Dimensionality reduction is done as in Section Figure 5.15 Line features Creating Template from Feature Vectors The proposed system extracts four types of feature vectors. They are Gabor feature vector, DCT feature vector, LBP feature vector and line feature vector. The system stores these four templates in the database. The sum rule is applied on the feature vectors before the distance calculation takes
19 163 place. The feature vector of the input palmprint image is verified against feature vector of the palmprint image in the database. If X x 1, x2,... xn is one feature vector and Y y, y2,... yn 1 is another feature vector, then fusion of these vectors Z using sum rule is represented as in Equation (5.6) Z x1 y1, x2 y2,... xn y n (5.6) Palmprint Matching This system uses Euclidian distance for distance vector calculation for palmprint matching. The distance calculation is one of the important things in authentication. Distance between two palmprint images shows the similarity of those two palmprint images. The palmprint images from the same person with negligible transposition will be of minimal distance mean, while the distance between two palmprint images from two different people will be high. Euclidean distance is used for distance calculation. Euclidean distance between vector X and Y is calculated as in Equation (5.7) n 2 d X,Y) x i y i (5.7) i 1 Experimental results show that the extracted features from the enhanced image is more accurate than that of the direct input image. Here, the proposed system shows the effect of the enhancement stage to obtain more recognition rate.
20 PERFORMANCE MEASURES The performance of a palmprint authentication system can be measured by three metrics, namely FAR, FRR and TSR. False Acceptance (FA) is the number of times the system accepts an unauthorized user (imposter) and FAR is the ratio of number of false acceptances to the total number of imposter accesses. FAR is measured as in Equation (5.8) Number of false acceptances FAR 100 % (5.8) Total number of imposter accesses False Rejection (FR) is the number of times the system rejects an authorized user (genuine) and FRR is the ratio of number of false rejections to the total number of genuine accesses. FRR is measured using Equation (5.9) Number of false rejections FRR 100 % (5.9) Total number of genuine accesses TSR (Connie et al 2005) represents the recognition rate of the system and it is measured using Equation (5.10) FA FR TSR % (5.10) Total number of accesses 5.7 RESULTS AND DISCUSSION Performance of Palmprint Recognition Using SAX Features The comparison of FAR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the lowest FAR.
21 HE RHE Curvelet RHE and Curvelet Figure 5.16 Comparison of FAR of RHE & curvelet method with HE, RHE and curvelet The comparison of FRR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the least FRR. The comparison of TSR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the highest TSR. Here, the proposed technique provides TSR of 98.29% HE RHE Curvelet RHE and Curvelet Figure 5.17 Comparison of FRR of RHE & curvelet method with HE, RHE and curvelet
22 HE RHE Curvelet RHE and Curvelet Figure 5.18 Comparison of TSR of RHE & curvelet method with HE, RHE and curvelet The optimum result is obtained when both curvelet and RHE are used. The FAR, FRR and TSR values are measured as %, %, %. Michael et al (2008) used contrast adjustment and smoothing as enhancement technique in contactless palmprint and recognition system. They obtained a recognition rate of % without image enhancement and recognition rate of 98.68% with image enhancement. An improvement of 0.58 % is obtained using enhancement. The proposed system provides an improvement of 8% than the HE method using RHE and curvelet Performance of Palmprint Recognition Using Multiple Palmprint Features In this work, the performance of the system is analyzed by using the FAR, FRR and TSR. For the best performance of the system, the metric FAR and FRR should be minimum and TSR should be maximum. The experimental results show that the performance of the system increased, while the system incorporates enhancement before feature extraction. This system improves the performance of the system by
23 167 enhancement and the effective utilization of multiple features palmprint image HE RHE Curvelet RHE and Curvelet Figure 5.19 Comparison of FAR of RHE & curvelet method with HE, RHE and curvelet with multiple palmprint features The comparison of FAR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the lowest FAR. FAR value is The comparison of FRR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the least FRR. The FRR value is HE RHE Curvelet RHE and Curvelet Figure 5.20 Comparison of FRR of RHE & curvelet method with HE, RHE and curvelet with multiple palmprint features
24 HE RHE Curvelet RHE and Curvelet Figure 5.21 Comparison of TSR of RHE & curvelet method with HE, RHE and curvelet with multiple palmprint features The comparison of TSR of the RHE & curvelet method with other methods is given in Figure RHE& curvelet method has the highest TSR. The TSR of the proposed method is The optimum result is obtained when both curvelet and RHE are used. Michael et al (2010) used homomorphic filtering technique as enhancement technique in touchless palmprint and knuckle print recognition system. Here, without image enhancement % of Genuine Acceptance Rate (GAR) and with image enhancement 98.02% of GAR is obtained. An improvement of 1.5 % is obtained using enhancement. The proposed system provides an improvement of 8% than the HE method using RHE & curvelet. 5.8 SUMMARY To improve the accuracy of palmprint authentication system, curvelet and RHE are applied prior to the 2D SAX conversion. As these procedures remove the noise and enhance the contrast, the proposed system ensures high performance with competitive accuracy. Since it is a texturebased approach, the computational complexity of the feature extraction
25 169 process is much lower and thus can be efficiently implemented for even slow mobile embedded platforms. Also, the proposed approach does not rely on any parameter training process. A palmprint authentication system using multiple palmprint features with enhancement is proposed in this work. It uses four different features from the palmprint image, namely GB, DCT, LBP and line feature. RHE and curvelet are used for enhancement. The experimental results demonstrated that the RHE & curvelet method achieves optimum performance comparison with the other ones.
Advanced Palm Print Recognition Using Curve Let And Recursive Histogram Equalization
African Journal of Basic & Applied Sciences 9 (4): 09-15, 017 ISSN 079-034 IDOSI Publications, 017 DOI: 10.589/idosi.ajbas.017.09.15 Advanced Palm Print Recognition Using Curve Let And Recursive Histogram
More informationBiometric Security System Using Palm print
ISSN (Online) : 2319-8753 ISSN (Print) : 2347-6710 International Journal of Innovative Research in Science, Engineering and Technology Volume 3, Special Issue 3, March 2014 2014 International Conference
More informationBiometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)
Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html
More informationA Comparative Study of Palm Print Recognition Systems
A Comparative Study of Palm Print Recognition Systems Akash Patel akash.patel@somaiya.edu Chinmayi Tidke chinmayi.t@somaiya.edu Chirag Dhamecha Mumbai India chirag.d@somaiya.edu Kavisha Shah kavisha.shah@somaiya.edu
More informationA Survey on Feature Extraction Techniques for Palmprint Identification
International Journal Of Computational Engineering Research (ijceronline.com) Vol. 03 Issue. 12 A Survey on Feature Extraction Techniques for Palmprint Identification Sincy John 1, Kumudha Raimond 2 1
More informationFeature-level Fusion for Effective Palmprint Authentication
Feature-level Fusion for Effective Palmprint Authentication Adams Wai-Kin Kong 1, 2 and David Zhang 1 1 Biometric Research Center, Department of Computing The Hong Kong Polytechnic University, Kowloon,
More informationA Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation
A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation * A. H. M. Al-Helali, * W. A. Mahmmoud, and * H. A. Ali * Al- Isra Private University Email: adnan_hadi@yahoo.com Abstract:
More informationPalmprint Recognition Using Transform Domain and Spatial Domain Techniques
Palmprint Recognition Using Transform Domain and Spatial Domain Techniques Jayshri P. Patil 1, Chhaya Nayak 2 1# P. G. Student, M. Tech. Computer Science and Engineering, 2* HOD, M. Tech. Computer Science
More informationCHAPTER 3 IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN
CHAPTER 3 IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN CHAPTER 3: IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN Principal objective: to process an image so that the result is more suitable than the original image
More informationKeywords Wavelet decomposition, SIFT, Unibiometrics, Multibiometrics, Histogram Equalization.
Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Secure and Reliable
More informationTutorial 5. Jun Xu, Teaching Asistant March 2, COMP4134 Biometrics Authentication
Tutorial 5 Jun Xu, Teaching Asistant nankaimathxujun@gmail.com COMP4134 Biometrics Authentication March 2, 2017 Table of Contents Problems Problem 1: Answer The Questions Problem 2: Indeterminate Region
More informationChapter 3: Intensity Transformations and Spatial Filtering
Chapter 3: Intensity Transformations and Spatial Filtering 3.1 Background 3.2 Some basic intensity transformation functions 3.3 Histogram processing 3.4 Fundamentals of spatial filtering 3.5 Smoothing
More informationDigital Image Processing, 2nd ed. Digital Image Processing, 2nd ed. The principal objective of enhancement
Chapter 3 Image Enhancement in the Spatial Domain The principal objective of enhancement to process an image so that the result is more suitable than the original image for a specific application. Enhancement
More informationIris Recognition for Eyelash Detection Using Gabor Filter
Iris Recognition for Eyelash Detection Using Gabor Filter Rupesh Mude 1, Meenakshi R Patel 2 Computer Science and Engineering Rungta College of Engineering and Technology, Bhilai Abstract :- Iris recognition
More informationIntegrating Palmprint and Fingerprint for Identity Verification
2009 Third nternational Conference on Network and System Security ntegrating Palmprint and Fingerprint for dentity Verification Yong Jian Chin, Thian Song Ong, Michael K.O. Goh and Bee Yan Hiew Faculty
More informationKeywords Palmprint recognition, patterns, features
Volume 7, Issue 3, March 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Review on Palm
More informationImage Enhancement in Spatial Domain. By Dr. Rajeev Srivastava
Image Enhancement in Spatial Domain By Dr. Rajeev Srivastava CONTENTS Image Enhancement in Spatial Domain Spatial Domain Methods 1. Point Processing Functions A. Gray Level Transformation functions for
More informationVivekananda. Collegee of Engineering & Technology. Question and Answers on 10CS762 /10IS762 UNIT- 5 : IMAGE ENHANCEMENT.
Vivekananda Collegee of Engineering & Technology Question and Answers on 10CS762 /10IS762 UNIT- 5 : IMAGE ENHANCEMENT Dept. Prepared by Harivinod N Assistant Professor, of Computer Science and Engineering,
More informationLecture 6: Edge Detection
#1 Lecture 6: Edge Detection Saad J Bedros sbedros@umn.edu Review From Last Lecture Options for Image Representation Introduced the concept of different representation or transformation Fourier Transform
More informationImage Enhancement Techniques for Fingerprint Identification
March 2013 1 Image Enhancement Techniques for Fingerprint Identification Pankaj Deshmukh, Siraj Pathan, Riyaz Pathan Abstract The aim of this paper is to propose a new method in fingerprint enhancement
More informationChapter - 2 : IMAGE ENHANCEMENT
Chapter - : IMAGE ENHANCEMENT The principal objective of enhancement technique is to process a given image so that the result is more suitable than the original image for a specific application Image Enhancement
More informationCHAPTER 6 RESULTS AND DISCUSSIONS
151 CHAPTER 6 RESULTS AND DISCUSSIONS In this chapter the performance of the personal identification system on the PolyU database is presented. The database for both Palmprint and Finger Knuckle Print
More informationGaussian Mixture Model Coupled with Independent Component Analysis for Palmprint Verification
Gaussian Mixture Model Coupled with Independent Component Analysis for Palmprint Verification Raghavendra.R, Bernadette Dorizzi, Ashok Rao, Hemantha Kumar G Abstract In this paper we present a new scheme
More informationFusion of Hand Geometry and Palmprint Biometrics
(Working Paper, Dec. 2003) Fusion of Hand Geometry and Palmprint Biometrics D.C.M. Wong, C. Poon and H.C. Shen * Department of Computer Science, Hong Kong University of Science and Technology, Clear Water
More informationOutlines. Medical Image Processing Using Transforms. 4. Transform in image space
Medical Image Processing Using Transforms Hongmei Zhu, Ph.D Department of Mathematics & Statistics York University hmzhu@yorku.ca Outlines Image Quality Gray value transforms Histogram processing Transforms
More informationFILTERBANK-BASED FINGERPRINT MATCHING. Dinesh Kapoor(2005EET2920) Sachin Gajjar(2005EET3194) Himanshu Bhatnagar(2005EET3239)
FILTERBANK-BASED FINGERPRINT MATCHING Dinesh Kapoor(2005EET2920) Sachin Gajjar(2005EET3194) Himanshu Bhatnagar(2005EET3239) Papers Selected FINGERPRINT MATCHING USING MINUTIAE AND TEXTURE FEATURES By Anil
More informationCritique: Efficient Iris Recognition by Characterizing Key Local Variations
Critique: Efficient Iris Recognition by Characterizing Key Local Variations Authors: L. Ma, T. Tan, Y. Wang, D. Zhang Published: IEEE Transactions on Image Processing, Vol. 13, No. 6 Critique By: Christopher
More informationEmbedded Palmprint Recognition System on Mobile Devices
Embedded Palmprint Recognition System on Mobile Devices Yufei Han, Tieniu Tan, Zhenan Sun, and Ying Hao Center for Biometrics and Security Research National Labrotory of Pattern Recognition,Institue of
More informationPALM PRINT RECOGNITION AND AUTHENTICATION USING DIGITAL IMAGE PROCESSSING TECHNIQUE
PALM PRINT RECOGNITION AND AUTHENTICATION USING DIGITAL IMAGE PROCESSSING TECHNIQUE Prof.V.R.Raut 1, Prof.Ms.S.S.Kukde 2, Shraddha S. Pande 3 3 Student of M.E Department of Electronics and telecommunication,
More informationImage Enhancement in Spatial Domain (Chapter 3)
Image Enhancement in Spatial Domain (Chapter 3) Yun Q. Shi shi@njit.edu Fall 11 Mask/Neighborhood Processing ECE643 2 1 Point Processing ECE643 3 Image Negatives S = (L 1) - r (3.2-1) Point processing
More informationBroad field that includes low-level operations as well as complex high-level algorithms
Image processing About Broad field that includes low-level operations as well as complex high-level algorithms Low-level image processing Computer vision Computational photography Several procedures and
More informationMRT based Fixed Block size Transform Coding
3 MRT based Fixed Block size Transform Coding Contents 3.1 Transform Coding..64 3.1.1 Transform Selection...65 3.1.2 Sub-image size selection... 66 3.1.3 Bit Allocation.....67 3.2 Transform coding using
More informationGraph Matching Iris Image Blocks with Local Binary Pattern
Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of
More informationCHAPTER 3 PRINCIPAL COMPONENT ANALYSIS AND FISHER LINEAR DISCRIMINANT ANALYSIS
38 CHAPTER 3 PRINCIPAL COMPONENT ANALYSIS AND FISHER LINEAR DISCRIMINANT ANALYSIS 3.1 PRINCIPAL COMPONENT ANALYSIS (PCA) 3.1.1 Introduction In the previous chapter, a brief literature review on conventional
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 informationDigital Image Processing. Image Enhancement - Filtering
Digital Image Processing Image Enhancement - Filtering Derivative Derivative is defined as a rate of change. Discrete Derivative Finite Distance Example Derivatives in 2-dimension Derivatives of Images
More informationGraph Geometric Approach and Bow Region Based Finger Knuckle Biometric Identification System
_ Graph Geometric Approach and Bow Region Based Finger Knuckle Biometric Identification System K.Ramaraj 1, T.Ummal Sariba Begum 2 Research scholar, Assistant Professor in Computer Science, Thanthai Hans
More informationIntroduction to Digital Image Processing
Fall 2005 Image Enhancement in the Spatial Domain: Histograms, Arithmetic/Logic Operators, Basics of Spatial Filtering, Smoothing Spatial Filters Tuesday, February 7 2006, Overview (1): Before We Begin
More informationPalmprint Based Identification Using Principal Line Approach
Palmprint Based Identification Using Principal Line Approach Ms. Bhagyashri K. Mane, Prof. Pravin P. Kalyankar Abstract A principal line approach is used for identify accurate person based on palmprint
More informationAn Acceleration Scheme to The Local Directional Pattern
An Acceleration Scheme to The Local Directional Pattern Y.M. Ayami Durban University of Technology Department of Information Technology, Ritson Campus, Durban, South Africa ayamlearning@gmail.com A. Shabat
More informationImage Transformation Techniques Dr. Rajeev Srivastava Dept. of Computer Engineering, ITBHU, Varanasi
Image Transformation Techniques Dr. Rajeev Srivastava Dept. of Computer Engineering, ITBHU, Varanasi 1. Introduction The choice of a particular transform in a given application depends on the amount of
More informationUlrik Söderström 16 Feb Image Processing. Segmentation
Ulrik Söderström ulrik.soderstrom@tfe.umu.se 16 Feb 2011 Image Processing Segmentation What is Image Segmentation? To be able to extract information from an image it is common to subdivide it into background
More informationDevelopment of an Automated Fingerprint Verification System
Development of an Automated Development of an Automated Fingerprint Verification System Fingerprint Verification System Martin Saveski 18 May 2010 Introduction Biometrics the use of distinctive anatomical
More informationDecision Level Fusion of Face and Palmprint Images for User Identification
XI Biennial Conference of the International Biometric Society (Indian Region) on Computational Statistics and Bio-Sciences, March 8-9, 2012 83 Decision Level Fusion of Face and Palmprint Images for User
More informationPolar Harmonic Transform for Fingerprint Recognition
International Journal Of Engineering Research And Development e-issn: 2278-067X, p-issn: 2278-800X, www.ijerd.com Volume 13, Issue 11 (November 2017), PP.50-55 Polar Harmonic Transform for Fingerprint
More informationEEM 463 Introduction to Image Processing. Week 3: Intensity Transformations
EEM 463 Introduction to Image Processing Week 3: Intensity Transformations Fall 2013 Instructor: Hatice Çınar Akakın, Ph.D. haticecinarakakin@anadolu.edu.tr Anadolu University Enhancement Domains Spatial
More informationTexture. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors
Texture The most fundamental question is: How can we measure texture, i.e., how can we quantitatively distinguish between different textures? Of course it is not enough to look at the intensity of individual
More informationDigital Image Processing. Image Enhancement in the Spatial Domain (Chapter 4)
Digital Image Processing Image Enhancement in the Spatial Domain (Chapter 4) Objective The principal objective o enhancement is to process an images so that the result is more suitable than the original
More informationINTENSITY TRANSFORMATION AND SPATIAL FILTERING
1 INTENSITY TRANSFORMATION AND SPATIAL FILTERING Lecture 3 Image Domains 2 Spatial domain Refers to the image plane itself Image processing methods are based and directly applied to image pixels Transform
More informationwavelet packet transform
Research Journal of Engineering Sciences ISSN 2278 9472 Combining left and right palmprint for enhanced security using discrete wavelet packet transform Abstract Komal Kashyap * and Ekta Tamrakar Department
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 WRI C225 Lecture 04 130131 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Histogram Equalization Image Filtering Linear
More informationDigital Image Processing
Digital Image Processing Third Edition Rafael C. Gonzalez University of Tennessee Richard E. Woods MedData Interactive PEARSON Prentice Hall Pearson Education International Contents Preface xv Acknowledgments
More information234 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 14, NO. 2, FEBRUARY 2004
234 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 14, NO. 2, FEBRUARY 2004 On Hierarchical Palmprint Coding With Multiple Features for Personal Identification in Large Databases
More informationEfficient Nonlinear Image Processing Algorithms
Efficient Nonlinear Image Processing Algorithms SANJIT K. MITRA Department of Electrical & Computer Engineering University of California Santa Barbara, California Outline Introduction Quadratic Volterra
More informationFace Detection and Recognition in an Image Sequence using Eigenedginess
Face Detection and Recognition in an Image Sequence using Eigenedginess B S Venkatesh, S Palanivel and B Yegnanarayana Department of Computer Science and Engineering. Indian Institute of Technology, Madras
More informationCS334: Digital Imaging and Multimedia Edges and Contours. Ahmed Elgammal Dept. of Computer Science Rutgers University
CS334: Digital Imaging and Multimedia Edges and Contours Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines What makes an edge? Gradient-based edge detection Edge Operators From Edges
More informationFinger-Vein Image Enhancement Using a Fuzzy-Based Fusion Method with Gabor and Retinex Filtering
Sensors 2014, 14, 3095-3129; doi:10.3390/s140203095 Article OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Finger-Vein Image Enhancement Using a Fuzzy-Based Fusion Method with Gabor and
More informationBasic relations between pixels (Chapter 2)
Basic relations between pixels (Chapter 2) Lecture 3 Basic Relationships Between Pixels Definitions: f(x,y): digital image Pixels: q, p (p,q f) A subset of pixels of f(x,y): S A typology of relations:
More informationCHAPTER 5 GLOBAL AND LOCAL FEATURES FOR FACE RECOGNITION
122 CHAPTER 5 GLOBAL AND LOCAL FEATURES FOR FACE RECOGNITION 5.1 INTRODUCTION Face recognition, means checking for the presence of a face from a database that contains many faces and could be performed
More informationFiltering Images. Contents
Image Processing and Data Visualization with MATLAB Filtering Images Hansrudi Noser June 8-9, 010 UZH, Multimedia and Robotics Summer School Noise Smoothing Filters Sigmoid Filters Gradient Filters Contents
More informationAn Efficient Secure Multimodal Biometric Fusion Using Palmprint and Face Image
International Journal of Computer Science Issues, Vol. 2, 2009 ISSN (Online): 694-0784 ISSN (Print): 694-084 49 An Efficient Secure Multimodal Biometric Fusion Using Palmprint and Face Image Nageshkumar.M,
More informationCORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM
CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar
More informationFACE RECOGNITION USING INDEPENDENT COMPONENT
Chapter 5 FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS OF GABORJET (GABORJET-ICA) 5.1 INTRODUCTION PCA is probably the most widely used subspace projection technique for face recognition. A major
More informationComputationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms
Computationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms Andreas Uhl Department of Computer Sciences University of Salzburg, Austria uhl@cosy.sbg.ac.at
More informationDEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING DS7201 ADVANCED DIGITAL IMAGE PROCESSING II M.E (C.S) QUESTION BANK UNIT I 1. Write the differences between photopic and scotopic vision? 2. What
More informationPalmprint recognition by using enhanced completed local binary pattern (CLBP) for personal recognition
Palmprint recognition by using enhanced completed local binary pattern (CLBP) for personal recognition Dr. K.N. Prakash 1, M. Satya sri lakshmi 2 1 Professor, Department of Electronics & Communication
More informationChapter 4 Face Recognition Using Orthogonal Transforms
Chapter 4 Face Recognition Using Orthogonal Transforms Face recognition as a means of identification and authentication is becoming more reasonable with frequent research contributions in the area. In
More informationDigital Image Fundamentals II
Digital Image Fundamentals II 1. Image modeling and representations 2. Pixels and Pixel relations 3. Arithmetic operations of images 4. Image geometry operation 5. Image processing with Matlab - Image
More informationA Wavelet-based Feature Selection Scheme for Palm-print Recognition
Vol.1, Issue.2, pp-278-287 ISSN: 2249-6645 A Wavelet-based Feature Selection Scheme for Palm-print Recognition Hafiz Imtiaz, Shaikh Anowarul Fattah (Department of Electrical and Electronic Engineering
More informationFootprint Recognition using Modified Sequential Haar Energy Transform (MSHET)
47 Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET) V. D. Ambeth Kumar 1 M. Ramakrishnan 2 1 Research scholar in sathyabamauniversity, Chennai, Tamil Nadu- 600 119, India.
More informationColor Local Texture Features Based Face Recognition
Color Local Texture Features Based Face Recognition Priyanka V. Bankar Department of Electronics and Communication Engineering SKN Sinhgad College of Engineering, Korti, Pandharpur, Maharashtra, India
More informationPeg-Free Hand Geometry Verification System
Peg-Free Hand Geometry Verification System Pavan K Rudravaram Venu Govindaraju Center for Unified Biometrics and Sensors (CUBS), University at Buffalo,New York,USA. {pkr, govind} @cedar.buffalo.edu http://www.cubs.buffalo.edu
More informationCS4733 Class Notes, Computer Vision
CS4733 Class Notes, Computer Vision Sources for online computer vision tutorials and demos - http://www.dai.ed.ac.uk/hipr and Computer Vision resources online - http://www.dai.ed.ac.uk/cvonline Vision
More informationLecture 4 Image Enhancement in Spatial Domain
Digital Image Processing Lecture 4 Image Enhancement in Spatial Domain Fall 2010 2 domains Spatial Domain : (image plane) Techniques are based on direct manipulation of pixels in an image Frequency Domain
More informationPalmprint Recognition using Novel Fusion Algorithm
Palmprint Recognition using Novel Fusion Algorithm Kannan Subramanian Dept. of MCA, Bharath University, Chennai-600073, India ABSTRACT: Palmprint is a promising biometric feature for use in access control
More informationPALMPRINT AUTHENTICATION BASED ON GABOR WAVELET USING SLIDING WINDOW APPROACH
PALMPRINT AUTHENTICATION BASED ON GABOR WAVELET USING SLIDING WINDOW APPROACH Sadiya Thazeen, Feroz Morab, Mohammed Najmus Saqhib, Seema Morab Abstract A biometric system is a pattern recognition system
More informationProjected Texture for Hand Geometry based Authentication
Projected Texture for Hand Geometry based Authentication Avinash Sharma Nishant Shobhit Anoop Namboodiri Center for Visual Information Technology International Institute of Information Technology, Hyderabad,
More informationPalmprint Detection and Verification Using ROI and MLBP Method
almprint Detection and Verification Using ROI and MLB Method 1 1 2 Snigdha Mankar and A.A. Bardekar Computer Science and Engineering, Sipna COET, Amravati, 444701, India 2 Information & Technology, Sipna
More informationSIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014
SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image
More informationFingerprint Recognition using Texture Features
Fingerprint Recognition using Texture Features Manidipa Saha, Jyotismita Chaki, Ranjan Parekh,, School of Education Technology, Jadavpur University, Kolkata, India Abstract: This paper proposes an efficient
More informationCOMPUTER AND ROBOT VISION
VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington A^ ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California
More informationImproved Palmprint Authentication using Contactless Imaging
Improved Palmprint Authentication using Contactless Imaging Aythami Morales 1, 2, Miguel A. Ferrer 1, Ajay Kumar 2 1 Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones
More informationEdge and local feature detection - 2. Importance of edge detection in computer vision
Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature
More informationMULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION
MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of
More informationLecture 7: Most Common Edge Detectors
#1 Lecture 7: Most Common Edge Detectors Saad Bedros sbedros@umn.edu Edge Detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the
More informationLocal Image preprocessing (cont d)
Local Image preprocessing (cont d) 1 Outline - Edge detectors - Corner detectors - Reading: textbook 5.3.1-5.3.5 and 5.3.10 2 What are edges? Edges correspond to relevant features in the image. An edge
More informationFinger Vein Biometric Approach for Personal Identification Using IRT Feature and Gabor Filter Implementation
Finger Vein Biometric Approach for Personal Identification Using IRT Feature and Gabor Filter Implementation Sowmya. A (Digital Electronics (MTech), BITM Ballari), Shiva kumar k.s (Associate Professor,
More informationIntensity Transformations and Spatial Filtering
77 Chapter 3 Intensity Transformations and Spatial Filtering Spatial domain refers to the image plane itself, and image processing methods in this category are based on direct manipulation of pixels in
More informationArtifacts and Textured Region Detection
Artifacts and Textured Region Detection 1 Vishal Bangard ECE 738 - Spring 2003 I. INTRODUCTION A lot of transformations, when applied to images, lead to the development of various artifacts in them. In
More informationMotivation. Gray Levels
Motivation Image Intensity and Point Operations Dr. Edmund Lam Department of Electrical and Electronic Engineering The University of Hong ong A digital image is a matrix of numbers, each corresponding
More informationTutorial 8. Jun Xu, Teaching Asistant March 30, COMP4134 Biometrics Authentication
Tutorial 8 Jun Xu, Teaching Asistant csjunxu@comp.polyu.edu.hk COMP4134 Biometrics Authentication March 30, 2017 Table of Contents Problems Problem 1: Answer The Questions Problem 2: Daugman s Method Problem
More informationconvolution shift invariant linear system Fourier Transform Aliasing and sampling scale representation edge detection corner detection
COS 429: COMPUTER VISON Linear Filters and Edge Detection convolution shift invariant linear system Fourier Transform Aliasing and sampling scale representation edge detection corner detection Reading:
More informationTexture Segmentation by Windowed Projection
Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw
More informationFabric Defect Detection Based on Computer Vision
Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.
More informationSUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS
SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract
More informationFeature extraction. Bi-Histogram Binarization Entropy. What is texture Texture primitives. Filter banks 2D Fourier Transform Wavlet maxima points
Feature extraction Bi-Histogram Binarization Entropy What is texture Texture primitives Filter banks 2D Fourier Transform Wavlet maxima points Edge detection Image gradient Mask operators Feature space
More informationIT Digital Image ProcessingVII Semester - Question Bank
UNIT I DIGITAL IMAGE FUNDAMENTALS PART A Elements of Digital Image processing (DIP) systems 1. What is a pixel? 2. Define Digital Image 3. What are the steps involved in DIP? 4. List the categories of
More informationTexture. Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image.
Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach: a set of texels in some regular or repeated pattern
More informationSampling and Reconstruction
Sampling and Reconstruction Sampling and Reconstruction Sampling and Spatial Resolution Spatial Aliasing Problem: Spatial aliasing is insufficient sampling of data along the space axis, which occurs because
More informationFingerprint Matching Using Minutiae Feature Hardikkumar V. Patel, Kalpesh Jadav
Fingerprint Matching Using Minutiae Feature Hardikkumar V. Patel, Kalpesh Jadav Abstract- Fingerprints have been used in identification of individuals for many years because of the famous fact that each
More information