Feature Extraction Operations Research Articles

A Face Recognition Using Linear-Diagonal Binary Graph Pattern Feature Extraction Method

Face recognition is one the most interesting topic in the field in computer vision and image processing. Face recognition is a processing system that recognizes and identifies individuals human by their faces. Automatic face recognition is powerful way to provide, authorized access to control their system. Face recognition has many challenging problems (like face pose, face expression variation, illumination variation, face orientation and noise) in the field of image analysis and computer vision. This method is work on feature extraction part of face recognition. New way to extract face feature using LD-BGP code operator it is like LGS and LBP feature extraction operator. In our LD-BGP-code operator work in two direction first linear then diagonal. In both direction, its create eight digits code to every pixel of image. Means of these two directional are taken so that is cover all neighbor of center pixel. First linear direction, only horizontal and vertical pixel are taken. Second diagonal direction only diagonal pixels taken. In matching phase, we use Euclidean distance to match a face image. We perform the Linear and diagonal directional operator method on face database ORL. We get accuracy 95.3 %. LD-BGP method also works on different type image like illuminated and expression variation image.

An Efficient VLSI Architecture for Multi-Channel Spike Sorting Using a Generalized Hebbian Algorithm.

A novel VLSI architecture for multi-channel online spike sorting is presented in this paper. In the architecture, the spike detection is based on nonlinear energy operator (NEO), and the feature extraction is carried out by the generalized Hebbian algorithm (GHA). To lower the power consumption and area costs of the circuits, all of the channels share the same core for spike detection and feature extraction operations. Each channel has dedicated buffers for storing the detected spikes and the principal components of that channel. The proposed circuit also contains a clock gating system supplying the clock to only the buffers of channels currently using the computation core to further reduce the power consumption. The architecture has been implemented by an application-specific integrated circuit (ASIC) with 90-nm technology. Comparisons to the existing works show that the proposed architecture has lower power consumption and hardware area costs for real-time multi-channel spike detection and feature extraction.

Gradient operators for feature extraction from omnidirectional panoramic images

We propose an extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views. It solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity. For the first problem, we derive a Laplacian operator and a class of differential corner detectors that can handle spatial inhomogeneities in omnidirectional panoramic images using differential schemes. To solve the second problem, we use an overset grid system on the sphere called the Yin–Yang grid. This is realized based on the property that each of the modified Laplacian operator and corner detector is invariant with respect to coordinate transformation between the two spherical polar coordinate systems associated with the Yin–Yang grid system.

Defects Detection of Pharmaceutical Blister Packaging Based on Shape Template Matching

In machine vision defects detection of pharmaceutical blister packaging, the traditional defects detection algorithms always do the binary image processing and edge feature extraction and other operations, and then locate the analysis image through these features. These operations are very tedious and inflexible. In this paper, the shape template matching algorithm is applied to pharmaceutical blister packaging defects detection. The algorithm can determine whether there is a positioning region of the sheet or pieces missing through search algorithm to locate the template image and comparing the difference of gray value between the detection region and the template region. This paper packaged the software of pharmaceutical blister packaging machine vision defects detection via the professional image processing library of Halcon and visual programming software Visual C++. Detection case demonstrates the feasibility and effectiveness of detection algorithm and system.

A new method for Arabic/Farsi numeral data set size reduction via modified frequency diagram matching

Purpose – Pattern recognition systems often have to handle problem of large volume of training data sets including duplicate and similar training samples. This problem leads to large memory requirement for saving and processing data, and the time complexity for training algorithms. The purpose of the paper is to reduce the volume of training part of a data set – in order to increase the system speed, without any significant decrease in system accuracy. Design/methodology/approach – A new technique for data set size reduction – using a version of modified frequency diagram approach – is presented. In order to reduce processing time, the proposed method compares the samples of a class to other samples in the same class, instead of comparing samples from different classes. It only removes patterns that are similar to the generated class template in each class. To achieve this aim, no feature extraction operation was carried out, in order to produce more precise assessment on the proposed data size reduction technique. Findings – The results from the experiments, and according to one of the biggest handwritten numeral standard optical character recognition (OCR) data sets, Hoda, show a 14.88 percent decrease in data set volume without significant decrease in performance. Practical implications – The proposed technique is effective for size reduction for all pictorial databases such as OCR data sets. Originality/value – State-of-the-art algorithms currently used for data set size reduction usually remove samples near to class's centers, or support vector (SV) samples between different classes. However, the samples near to a class center have valuable information about class characteristics, and they are necessary to build a system model. Also, SV s are important samples to evaluate the system efficiency. The proposed technique, unlike the other available methods, keeps both outlier samples, as well as the samples close to the class centers.

A Consistency-Based Feature Selection Method Allied with Linear SVMs for HIV-1 Protease Cleavage Site Prediction

BackgroundPredicting type-1 Human Immunodeficiency Virus (HIV-1) protease cleavage site in protein molecules and determining its specificity is an important task which has attracted considerable attention in the research community. Achievements in this area are expected to result in effective drug design (especially for HIV-1 protease inhibitors) against this life-threatening virus. However, some drawbacks (like the shortage of the available training data and the high dimensionality of the feature space) turn this task into a difficult classification problem. Thus, various machine learning techniques, and specifically several classification methods have been proposed in order to increase the accuracy of the classification model. In addition, for several classification problems, which are characterized by having few samples and many features, selecting the most relevant features is a major factor for increasing classification accuracy.ResultsWe propose for HIV-1 data a consistency-based feature selection approach in conjunction with recursive feature elimination of support vector machines (SVMs). We used various classifiers for evaluating the results obtained from the feature selection process. We further demonstrated the effectiveness of our proposed method by comparing it with a state-of-the-art feature selection method applied on HIV-1 data, and we evaluated the reported results based on attributes which have been selected from different combinations.ConclusionApplying feature selection on training data before realizing the classification task seems to be a reasonable data-mining process when working with types of data similar to HIV-1. On HIV-1 data, some feature selection or extraction operations in conjunction with different classifiers have been tested and noteworthy outcomes have been reported. These facts motivate for the work presented in this paper.Software availabilityThe software is available at http://ozyer.etu.edu.tr/c-fs-svm.rar.The software can be downloaded at esnag.etu.edu.tr/software/hiv_cleavage_site_prediction.rar; you will find a readme file which explains how to set the software in order to work.

An Improved Image Edge Feature Extraction Algorithm Based on Ant Colony Algorithm

In this paper, a new method for the optimization design of ant colony algorithm is used to extract the edge character of the model in the air of the image. The organization is as follows: the second part is a basic ant colony algorithm in the edge of the model feature extraction. The result of the advisory council on AIDS will be compared with the results analysis, and think this is smart operator most edge feature extraction operator. Contrast indicates that the algorithm can effectively edge feature extraction, especially the image.

Text‐Dependent Writer Identification for Arabic Handwriting

This paper proposes a system for text‐dependent writer identification based on Arabic handwriting. First, a database of words was assembled and used as a test base. Next, features vectors were extracted from writers′ word images. Prior to the feature extraction process, normalization operations were applied to the word or text line under analysis. In this work, we studied the feature extraction and recognition operations of Arabic text on the identification rate of writers. Because there is no well‐known database containing Arabic handwritten words for researchers to test, we have built a new database of offline Arabic handwriting text to be used by the writer identification research community. The database of Arabic handwritten words collected from 100 writers is intended to provide training and testing sets for Arabic writer identification research. We evaluated the performance of edge‐based directional probability distributions as features, among other characteristics, in Arabic writer identification. Results suggest that longer Arabic words and phrases have higher impact on writer identification.

Surface Defect Inspection and Classification of Segment Magnet by Using Machine Vision Technique

In this paper, we propose a machine vision based approach for detecting and classifying irregular low-contrast surface defects of segment magnet. The constituent material of it is ferrite which varies from silver gray to black in color .For this reason, the defects embedded in a low-contrast surface show no big different from its surrounding region, and even worse, all the surfaces and chamfers of segment magnet must be inspected. Our system is able to analyze all surfaces under inspection, to discover and classify its defects by means of image processing algorithms and support vector machine (SVM). A working prototype of the system has been built and tested to validate the proposed approach and to reproduce the difficult issues of the inspection system. The developed prototype includes three subsystems: an array of several CCD area cameras (Fig.1); a controllable roller LED light source(Fig.1); and a PC-based image processing system. The detection of the defects is performed by means of Canny edge detection, morphology and other feature extraction operations. The image processing and classification results demonstrate that the proposed method can identify surface defects effectively.

Evaluation of fractal dimension estimation methods for feature extraction in motor imagery based brain computer interface

Abstract A brain computer interface (BCI) enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction and classification operations. Feature extraction is crucial as it has a substantial effect on the classification accuracy and speed. While fractal dimension has been successfully used in various domains to characterize data exhibiting fractal properties, its usage in motor imagery based BCI has been more recent. There are several fractal dimension estimation methods, some of which are not applicable to all types of data exhibiting fractal properties. In this study, commonly used fractal dimension estimation methods to characterize time series (Katz’s method, Higuchi’s method and the rescaled range method) were evaluated for feature extraction in motor imagery based BCI by conducting offline analyses of a two class motor imagery dataset. Different classifiers (fuzzy k nearest neighbors (FKNN), support vector machine and linear discriminant analysis) were tested in combination with these methods to determine the methodology with the best performance. This methodology was then modified by implementing the time dependent fractal dimension (TDFD), differential fractal dimension and differential signals methods to determine if the results could be further improved. Katz’s method with FKNN resulted in the highest classification accuracy (of 85%), and further improvements (by 3%) were achieved by implementing the TDFD method. The results point to Katz’s method with FKNN as a favorable methodology for motor imagery based BCI and warrant further research to implement this methodology in online analysis of motor imagery data and analysis of other signals.

Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery‐Based Brain Computer Interface

A brain computer interface BCI enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction, and classification operations. Feature extraction is crucial, as it has a substantial effect on the classification accuracy and speed. While fractal dimension has been successfully used in various domains to characterize data exhibiting fractal properties, its usage in motor imagery‐based BCI has been more recent. In this study, commonly used fractal dimension estimation methods to characterize time series Katz′s method, Higuchi′s method, rescaled range method, and Renyi′s entropy were evaluated for feature extraction in motor imagery‐based BCI by conducting offline analyses of a two class motor imagery dataset. Different classifiers fuzzy k‐nearest neighbours FKNN, support vector machine, and linear discriminant analysis were tested in combination with these methods to determine the methodology with the best performance. This methodology was then modified by implementing the time‐dependent fractal dimension TDFD, differential fractal dimension, and differential signals methods to determine if the results could be further improved. Katz′s method with FKNN resulted in the highest classification accuracy of 85%, and further improvements by 3% were achieved by implementing the TDFD method.

Gradient operators for feature extraction and characterisation in range images

In recent years range images have become prominent in computer vision applications as they provide an almost 3-D description of an otherwise 2-D scene and are suitable for computer vision tasks such as localisation and navigation. Feature extraction from range images has proven to be a complex problem; developing operators that can characterise features in a range image, such as step, crease, or smooth edges, is challenging, due to both the irregular spatial distribution of range image data and the nature of the features themselves. We present an adaptive design procedure for first order gradient operators that can automatically change shape to accommodate irregular data distribution; through appropriate analysis of the output responses, we show that the operators can also be specialised to characterise particular types of range image features. Hence the method is appropriate for direct use on range image data without re-sampling.

Feature extraction for target identification and image classification of OMIS hyperspectral image

In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives, two aspects of feature extraction were explored. Based on clustering and decision tree algorithm, spectral absorption index (SAI), continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets, and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA), minimum noise fraction (MNF), grouping PCA, and derivate spectral analysis, the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM, and SVM outperforms traditional SAM and MLC classifiers for OMIS data.

Processing Sparse Panoramic Images via Space Variant Operators

The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.

Methods for Improving Image Quality and Reducing Data Load of NIR Hyperspectral Images.

Near Infrared Hyperspectral Imaging (NIRHSI) is an emerging technology platform that integrates conventional imaging and spectroscopy to attain both spatial and spectral information from an object. Two important problems in NIRHSI are those of data load and unserviceable pixels in the NIR sensor. Hyperspectral imaging experiments generate large amounts of data (typically > 50 MB per image), which tend to overwhelm the memory capacity of conventional computer systems. This inhibits the utilisation of NIRHSI for routine online industrial application. In general, approximately 1% of pixels in NIR detectors are unserviceable or ‘dead’, containing no useful information. While this percentage of pixels is insignificant for single wavelength imaging, the problem is amplified in NIRHSI, where > 100 wavelength images are typically acquired. This paper describes an approach for reducing the data load of hyperspectral experiments by using sample-specific vector-to-scalar operators for real time feature extraction and a systematic procedure for compensating for ‘dead’ pixels in the NIR sensor. The feasibility of this approach was tested for prediction of moisture content in carrot tissue.

Real Coded Genetic Algorithm for Optimal Parameters Selection in Circular Mellin Feature Extractors

Texture is an important clue in region-based segmentation of images. Robust rotation and scale-invariant texture are important for digital image libraries and multimedia databases. Texture feature extraction operators, which comprise linear filtering followed by postprocessing, are considered. The CMF (Circular Mellin Feature) represents the spectral decomposition of the image scene in the polar-log coordinate system and is invariant to both scale and orientation of the target texture pattern. CMFs are used for rotation and scale-invariant texture classification. The image and CMFs are correlated, due to which the unique shift invariance property of the correlator architecture is also coupled. CMFs are based on log polar coordinate system. In this paper we present Real coded Genetic Algorithm (RcGA) for the parameter selection of CMFs. The simple genetic algorithm (GA) is search algorithms based on the mechanics of natural selection and genetics. It involves copying and swapping partial strings of data. A modified genetic algorithm is the RcGA, which basically employs real value vectors for representation of the chromosomes, and is widely applied to many optimization problems.

3-D Face Recognition Based on Warped Example Faces

In this paper, we describe a novel 3-D face recognition scheme for 3-D face recognition that can automatically identify faces from range images, and is insensitive to holes, facial expression, and hair. In our scheme, a number of carefully selected range images constitute a set of example faces, and another range image is chosen as a ldquogeneric face.rdquo The generic face is then warped to match each of the example faces in the least mean square sense. Each such warp is specified by a vector of displacement values. In feature extraction operation, when a target face image comes in, the generic face is warped to match it. The geometric transformation used in the warping is a linear combination of the example face warping vectors. The coefficients in the linear combination are adjusted to minimize the root mean square error. After the matching process is complete, the coefficients of the composite warp are used as features and passed to a Mahalanobis-distance-based classifier for face recognition. Our technique is tested on a data set containing more than 600 range images. Experimental results in the access-control scenario show the effectiveness of the extracted features.

The strain field method for structural damage identification using Brillouin optical fibersensing

The theory of the strain field (SF) method using Brillouin optical fiber sensing(BOFS) is proposed for structural damage identification in this paper. Field testverification of this method was carried out by implementing a destructive loadingtest to an existing prestressed concrete bridge. A series of structural damagescenarios were thus produced for identification. A sub-matrix featuring the damagescenarios was first extracted from the space–time matrix to obtain the strain fielddistribution in space–time coordinates. Furthermore, other feature extractionoperations, including row vector extraction, column vector extraction and boundaryextraction, were performed to characterize the structural damage behavior anddamage evolution patterns. Finally, damage localization and quantification weresuccessfully implemented in both space and time domains in terms of a damageindex vector array. The investigation results demonstrated the SF method usingBOFS is a feasible and efficient approach for structural damage identification.

Image Processing Algorithm for Quantitative Characterization of Thermal Imaging Acquired During On-line Weld Monitoring

Defect in welded structures is a matter of serious concern. The current practice involves interpretation by inspectors and experts, which is time consuming. With greater emphasis on automation during manufacturing process, automated NonDestructive Testing (NDT) Techniques have gained prominence. The key to success of automated NDT lies in the automatic defect recognition and characterization. Dimensional Characterization of defects or discontinuities is essential in order to compare this with the acceptable codes and standards. Greater emphasis is on selecting appropriate mathematical tools so that feature extraction is possible in accurate and reliable manner. Conventionally image-processing algorithms are applied to extract and quantify the features depicting defects. However many image processing algorithms are available for specific applications with its advantages and disadvantages. This paper explores the possibility of image processing algorithms like edge detection and morphological operators for feature extraction and proposes an algorithm for quantitative measurements of defects on thermal images. Lack of Fusion and Tungsten Inclusion are the defects considered. The choice of these particular defects is that these defects are the main causes for rejection and can be detected reliably during thermal imaging.

Improving angular error via systematically designed near-circular Gaussian-based feature extraction operators

In image filtering, the ‘circularity’ of an operator is an important factor affecting its accuracy. For example, circular differential edge operators are effective in minimising the angular error in the estimation of image gradient direction. We present a general approach to the computation of scalable circular low-level image processing operators that is based on the finite element method. We show that the use of Gaussian basis functions within the finite element method provides a framework for a systematic and efficient design procedure for operators that are scalable to near-circular neighbourhoods through the use of an explicit scale parameter. The general design technique may be applied to a range of operators. Here we evaluate the approach for the design of the image gradient operator. We illustrate that this design procedure significantly reduces angular error in comparison to other well-known gradient approximation methods.