Feature selective template mode filtering

Face recognition is a method which identifies a person based on the profile or features of the face of that person. LBPH (Local Binary Patterns Histogram) is a method to detect and recognize the face of a person. In LBP, first, some portion of an image which is in grayscale is taken as 3×3 window size and the pixel value of neighborhood is compared with the central pixel value and then the binary value is assigned which is then converted to a decimal value. LBP is then combined with histograms and so is called an LBPH algorithm. GPU (Graphics Processing Unit) is an electronic circuit which is more powerful than CPU (Central Processing Unit). In this paper, a frontal face and side profile face recognition using LBPH algorithm are implemented on GPU. The performance of the CPU and GPU are then compared.

An iterative digital image filtering algorithm based on signaling game idea is presented. Aim at shortages of the standard medium filtering algorithm, this paper provides an improving approach through appointing signaling game idea. The method is that choose filtering window, sort every pixel value in the window and find the median first and then compare the median and the window central pixel value, and obtain the probability that the window central pixel is signal point or noise point according to the similarity between the medium and window central pixel value, finally, construct membership function to fix the value of window central pixel and bring the value amended to the following pixel filtering operation. As the method above, we repeat the operation until all the value of pixels in the image have been amended. The results of computer simulation prove that the improved algorithm not only can suppress the noise but also keep details of the image well.

Recognition of patterns in a person by using parts of the human body, such as on fingerprints, has been widely applied in life such as to perform absenteeism, tracking a criminal, system security and so on. Local Binary Pattern (LBP) algorithm is known as an algorithm that can describe local texture pattern in an area. LBP uses 8 scattered circular neighborhoods with center pixels centered. In a 3 x 3 pixel image, the binary value in the image center is compared with the surrounding value. The surrounding value will be 1 if the central pixel value is smaller, and is 0 if the central binary value is greater. A total of 78 data were used for this study where 26 data were using blue ink fingerprints, and 26 black ink data. After the fingerprint pattern data obtained then the image is scanned. After that the image in the crop to be 50 pixels x 50 pixels, so all the data becomes uniform. The algorithm used to make an introduction is the Manhattan Distance algorithm. Based on the test results of 26 test data with different color inks, the result obtained accuracy of 61.54%.

A Novel Texture Classification Scheme based on Completed Multiple Adaptive Threshold Patterns

This paper proposes a novel approach in image compression based on Local Binary Pattern (LBP). LBP has already been used as a simple texture descriptor, labeling the image pixels by looking at the points surrounding a central point (usually on a 3×3 neighborhood) and examining whether these neighbors' color values are greater or less than the central point and accordingly assigning a binary value to the corresponding bit. The description of image's local pattern results in an eight-bit binary description, but in order to restore the image from such a LBP description, the value of each central pixel is also needed. These two pieces of information, i.e. the LBP description and the actual original value for each local neighborhood central pixel, are stored in a newly proposed Local Binary Compressed format, denoted .LBC, from which the image can be reconstructed by employing statistical methods, i.e. generating smaller or larger sets of random numbers to fill in the missing information within each local neighborhood, based on the LBP descriptor. Two statistical distributions were tested and, apart from the compression performance, a Structural Similarity Index Metric was used to evaluate the results.

This paper derives a new procedure for age classification of facial image based on the local region of facial image. The local region of facial image is extracted from a Significant Binary Pattern of Local Maximum Edge (SBPLME). The SBPLME is generated by calculating the absolute value of local difference between the average of local 3×3 sub window pixel values and its neighbors instead of the center pixel value. In the case of Local Maximum Edge Binary Pattern (LMEBP) calculating the absolute value of local difference between the center pixel value of local 3×3 sub window and its neighbors. The proposed SBPLME can generate 512 (0 to 511) different patterns. The present paper utilized Prominent LBP (PLBP) on the proposed SBPLME. The PLBP contains the significant patterns of Uniform LBP (ULBP) and Non Uniform LBP (NULBP). Thus the derived Significant PLBP of Local Maximum Edge (SPBPLME) becomes an efficient image classification and analysis, which will have a significant role in many areas. The novelty of the proposed SPBPLME method is, it has shown excellent age classification results by reducing the overall dimension, thus reducing the overall complexity.

Biometrics is the study of methods of recognizing humans based on their behavioral and physical characteristics or traits. Face recognition is one of the biometric modalities that received a great amount of attention from many researchers during the past few decades because of its potential applications in a variety of security domains. Face recognition however is not only concerned with recognizing human faces, but also with recognizing faces of non-biological entities or avatars. Fortunately, the need for secure and affordable virtual worlds is attracting the attention of many researchers who seek to find fast, automatic and reliable ways to identify virtual worlds’ avatars. In this work, I propose new techniques for recognizing avatar faces, which also can be applied to recognize human faces. Proposed methods are based mainly on a well-known and efficient local texture descriptor, Local Binary Pattern (LBP). I am applying different versions of LBP such as: Hierarchical Multi-scale Local Binary Patterns and Adaptive Local Binary Pattern with Directional Statistical Features in the wavelet space and discuss the effect of this application on the performance of each LBP version. In addition, I use a new version of LBP called Local Difference Pattern (LDP) with other well-known descriptors and classifiers to differentiate between human and avatar face images. The original LBP achieves high recognition rate if the tested images are pure but its performance gets worse if these images are corrupted by noise. To deal with this problem I propose a new definition to the original LBP in which the LBP descriptor will not threshold all the neighborhood pixel based on the central pixel value. A weight for each pixel in the neighborhood will be computed, a new value for each pixel will be calculated and then using simple statistical operations will be used to compute the new threshold, which will change automatically, based on the pixel’s values. This threshold can be applied with the original LBP or any other version of LBP and can be extended to work with Local Ternary Pattern (LTP) or any version of LTP to produce different versions of LTP for recognizing noisy avatar and human faces images.

HoMeNL: A Homogeneity Measure-Based NonLocal Filtering Framework for Detail-Enhanced (Pol)(In)SAR Image Denoising

The DM (Data Matrix) two-dimensional barcode images collected on metal parts with complex lighting conditions are prone to low contrast and local shadow, and the problem of uneven brightness leads to the loss of two-dimensional barcode information, which brings difficulties to the subsequent processing. However, the existing binarization algorithms will have the problems of too much noise and long segmentation time when dealing with this kind of images. To solve these problems, an improved local threshold algorithm is proposed to improve the anti-noise performance and computational efficiency. First of all, the algorithm model is improved to reduce the sensitivity to noise, and then the integral image algorithm is used to speed up the calculation of the local mean. In addition, the gray value of the local central pixel and the local mean are used to adjust the threshold adaptively according to the gray change characteristics of each pixel neighborhood, so as to further improve the segmentation efficiency. The improved local threshold algorithm and other five algorithms are tested on images with complex illumination conditions. The results show that the improved local threshold algorithm can not only effectively overcome the influence of complex illumination, has a good anti-noise effect, but also greatly shorten the time of image segmentation.

Edge detection can be of great importance to image processing in various digital imaging applications such as digital television and camera. Therefore, extracting more accurate edge properties are significantly demanded for achieving a better image understanding. In vector gradient edge detection, absolute difference of RGB values between a center pixel value, and its neighborhood values are usually used, although such a device-dependent color space does not account for human visual characteristics well. The goal of this study is to test a variety of color difference equations and propose the most effective model that can be used for the purpose of color edge detection. Three of synthetic images generated using perceptibility threshold of the human visual system were used for objectively evaluate to 5 color difference equations studied in this paper. A set of 6 complex color images was also used to testing the 5 color difference equations psychophysically. The equations include ΔRGB, ΔE^* _ab, ΔE_CMC, CIEDE2000 (ΔE₀₀) and CIECAM02-UCS delta E (ΔE_CAM-UCS). Consequently, there were not significant performance variations observed between those 5 color difference equations for the purpose of edge detection. However, ΔE₀₀ and ΔE_CAM-UCS showed slightly higher mean opinion score (MOS) in detected edge information.

Face recognition has lot of challenges in biometrics. The challenges are addressed effectively by local pattern descriptors. The idea of local descriptors is to determine the feature vector and then compute the difference between test images with training images by using similarity measure. Based on the observation, local approaches attained better performance rate than other approaches in face recognition. Due to that, researchers made a significant attention on local descriptors for face recognition. For nonlinear subspace, the local descriptors will achieve better result than holistic approach. Local pattern descriptor follows simple procedure to extract the facial features. The steps are face alignment, face representation, and matching. Face alignment is the first step of local descriptor, which is used to divide the image into several blocks. Face representation is used to extract the meaningful information from each region. This local feature extraction method carries discriminant information of the region; it will improve the classification rate and matching rate. Local descriptors extract the discriminant information from the neighbors by setting a threshold value as center pixel value, and it is not capable of extracting the detailed information from microstructure. Finally, matching by classification techniques or distance measure is used to identify or verify the person. The local pattern descriptors are more robust against pose, lighting, and scale variations. This chapter describes the various local pattern descriptors and shows the effectiveness of the descriptor. The results of local pattern descriptors are experimented on standard benchmark databases such as FERET, Extended Yale-B, ORL, CAS-PEAL, LFW, JAFFE, and Cohn–Kannade.

We have proposed fuzzy filters in order to remove additive non-impulsive noise (e.g., Gussian noise)while preserving signal details. In this paper, we propose a novel fuzzy filter for removing mixed noise(i.e., Gaussian noise and impulse noise are mixed). Furthermore, we apply the proposed method to colorimage processing. In order to remove mixed noise efficiently, we set fuzzy rules by using multiple dii-ference values between arbitrary two pixels in a filter window. We show tuning result of the proposedfuzzy filter and present some simulation results. 1. Introduction Since the first introducing of Fuzzy Set Theory [1] fuzzy techniques for image processing applicationshave mainly detail with high-level computer vision and pattern recognition [2]. Only recently, however,fuzzy techniques have successfully entered the area of low-level computer vision for general purposeapplications becoming competitive with classical methods in some very important pre-processmg tasks.In particular, focusing on the area ofnonlinear filtering of noisy image data, many original approacheshave been proposed in the last few years[3-lOJ.Taguchi and Takashima propose a fuzzy filter which is one ofnonlinear filter for noisy image data, in[8]. This fuzzy filter is an adaptive weighted average filter whose weight derived by using fuzzy rules.The antecedents offuzzy rules are constructed by using two important local characteristics: the differ-ence value from centre pixel's value and the distance from centre pixel. Since the fuzzy filter is able tochange its property according to local characteristics, it can remove non-impulse noise (e.g., Gaussiannoise) while preserving details. However, the fuzzy filter isn't able to remove impulse noise, becausethe difference value from centre pixel's value which one of local characteristics, is very sensitive toimpulse noise.In this paper, we propose a novel fuzzy filter which is able to remove not only non-impulse noise butalso impulse noise, since we introduce a new local characteristics to the fuzzy filter. A new local char-acteristic is calculated by using multiple difference values between arbitrary pixels in the filter window.The proposed filter can be applied to color image processing. Thus, we also propose the fuzzy filter forcolor image processing.In Section 2, we introduce a new local characteristic for filtering. Furthermore we also show thesame concept local characteristic for color image processing. In Section 3, we propose a novel fuzzyfilter for monochrome and color images, which is called a modified fuzzy (MF) filter, by using these

In the paper, we investigate the effectiveness of modified many-factor (bilateral, tri-, and four-lateral) denoising MIMO-filters for gray, color, and hyperspectral image procession. Conventional bilateral filter performs merely weighted averaging of the local neighborhood pixels. The weight includes two components: spatial and radiometric ones. The first component measures the geometric distances between the center pixel and local neighborhood ones. The second component measures the radiometric distance between the values of the center pixel and local neighborhood ones. Noise affects all pixels even the center one which is used as a reference for the tonal filtering. Thus, the noise affecting the center pixel has a disproportionate effect onto the result. This suggests the first modification: the center pixel is replaced by the weighted average (with some estimate of the true value) of the neighborhood pixels contained in a window around it. The second modification uses the matrix-valued weights. They include four components: spatial, radiometric, interchannel weights, and radiometric interchannel ones. The fourth weight measures the radiometric distance (for gray-level images) between the interchannel values of the center scalar-valued channel pixel and local neighborhood channel ones.

The main goal of image enhancement is to enhance the fine details present in the images having low luminance for better image quality. In the digital image processing field, the enhancement and removing the noise from the image is a critical issue; image noise removal is the manipulation of the image data to produce a visually high-quality image. The important details and useful information on image decreasing by the noise where the noise treated as information. The filters are used to remove unwanted information. The filters’ objectives are to improve the image quality. This paper proposes an enhancement image system, which chooses the appropriate filter and value of center pixel depends on the number of similarities adjusted neighbors pixels to the center pixel. The performance of this system is evaluated by using different quality metrics, such as Mean square error (MSE), Peak Signal Noise to Ratio (PSNR), Absolute Mean Brightness Error (AMBE), Measure of Enhancement (EME), and Measure of Enhancement by Entropy (EMEE), Entropy, Second-Order Entropy (SOE), and Image Enhancement Metric (IEM). The proposed enhancement system is efficient in removing noises and enhancing the image quality. Experiments are applied to a set of images, such as Lena, butterfly, etc. with different image sizes. The results show that the enhancement quality was performed well in the proposed system with minimal unexpected artifacts as compared to the other techniques, where the results of the proposed system for MSE, PSNR, AMBE, Entropy, SOE, EME, EMEE, and IEM for baboon image with the size 255x 255 are 2.906, 8.875, 3.92, 5.154, 2.692, 3.915, 0.442 and 3.674 in sequence.

Medical images such as MRI images normally have smooth edges and round corners, but the existing general edge-preserving smoothing algorithms often result in coarse edges and sharp corners. A new image smoothing algorithm, based on a filter utilizing the weighted average of 21 average pixel values in 21 neighborhood subregions in a 3x3 square around the center pixel, is proposed to deal with the problem. Subregions with the center point being smoothed on its sharp corner are avoided from selection to make the edges being preserved smooth and round. During the smoothing process, each subregion is assigned a weight according to its homogeneousness which is evaluated by the variance of its pixel values. The weighted average of averages for all subregions is assigned to the center pixel being smoothed. The more homogeneous neighborhood has more influence on the center pixel, so that the edges can be well preserved. But contributions from all neighborhoods are also taken into consideration especially when their homogeneousness is largely equal so that the resultant areas are smoother. An evaluation of the algorithm on the simulated MRI images is carried out. Experimental results showed that the new algorithm can smooth the MRI images better while keeping the edges better compared with the existing smoothing algorithms.