05-11-2016, 11:28 AM
An Automatic Face Recognition System for Frontal Face Images using Local Binary Pattern Feature Space and K-Nearest Neighbors Classification
[attachment=74623]
Abstract
Over a last decade face recognition has become increasingly important in the direction of computer vision, pattern recognition, surveillance, fraud detection, psychology, and content based video processing, etc. Rapid development of face recognition is due to combination of the factors such as active development of algorithms, availability of large facial database and method of evaluating the performance of recognition algorithms. Hence Face Recognition Technology has emerged as an attractive solution to address many contemporary requirements for identification and verification of identity claims.
To address human face recognition problem lots of algorithms have been proposed in the past few years. Although the available algorithms provides good face recognition, but the field is still looking for the efficient mild stone algorithm which can provide higher face recognition efficiency. To efficiently address this problem, in this paper, an Automatic Face Recognition System (AFRS) is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of some extracted features. For the detection of the frontal face proposed method uses well known Viola Jones face detection technique. Once face detection is performed, feature of interested region that is eyes and mouth are extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition, the proposed method employed highly efficient K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features. The whole system is implemented on the dataset of 30 images of frontal faces by using MATLAB 2012(b). The images were collected from the Karolinska Directed Emotional Faces (KDEF) Database. After the successful testing with the proposed system the face recognition efficiency found for the proposed system is very high and close to 100% for all the face images.
Keywords— Face Recognition, Face Features, Feature Extraction, LBP, K-NN Classifier.
1. Introduction
Face recognition is one of the important challenges in appearance-based pattern recognition field. This technology has emerged as an attractive solution to address many new needs for identification and verification of identity. It is the more familiar functionality of visual surveillance systems. It has received significant attention for decades due to its numerous potential applications. Some of these applications are national security, low enforcement, surveillance, public safety field. There are many factors affect the face recognition performance like facial expression, illumination, pose, cluttered background or occlusion. The process begins with face detection and extraction from the larger image, then normalizing the probe image so that it is in the same format (size, rotation, etc.) as the images in the database. The normalized face image is then passed to the recognition phase. Face recognition can typically be used for verification or identification. In verification an individual is already enrolled in the reference database or gallery i.e. it is a one-to-one matching task whereas in identification, a probe image is matched with a biometric reference in the gallery i.e. it represents a one-to-many problem.
To efficiently address this problem, in this paper, an Automatic Face Recognition System (AFRS) is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of some extracted features. For the detection of the frontal face proposed method uses well known Viola Jones face detection technique. Once face detection is performed, feature of interested region that is eyes and mouth are extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition, the proposed method employed highly efficient K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features.
2. Proposed Methodology
In this proposed work, an Automatic Face Recognition System is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of extracted LBP features. For face recognition, system follows a step by step procedure that comprises face detection, feature extraction and recognition (Classification). For the detection of the frontal face proposed method uses well known face detection technique known as Viola Jones method.
Once face detection is performed, feature of interested region that is eyes and mouth is extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition the proposed method utilized K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features. The complete process of the proposed technique is shown in figure (1), with the help of flow chart representation.
Detail description of the proposed face detection technique, LBP extraction and K- Nearest Neighbors classification are as follows:
2.1 Preprocessing
Preprocessing is the most important and the required step of the image processing. It is performed to get uniform and noise free image for further processing. This step includes the following functions:
Auto Brightness- Auto brightness function adjust the brightness of the image.
Auto Contrast- Auto contrast function automatically calculates the favorable contrast for the image will increase the brightness of the image.
Auto Color- Auto color function adjust the color of the image.
2.2 Face Detection using Viola-Jones Method
The basic principle of the Viola-Jones algorithm is to scan a sub-window capable of detecting faces across a given input image. The standard image processing approach would be to rescale the input image to different sizes and then run the fixed size detector through these images. This approach turns out to be rather time consuming due to the calculation of the different size images. Contrary to the standard approach Viola-Jones rescale the detector instead of the input image and run the detector many times through the image each time with a different size. At first one might suspect both approaches to be equally time consuming, but Viola-Jones have devised a scale invariant detector that requires the same number of calculations whatever the size. This detector is constructed using a so-called integral image and some simple rectangular features reminiscent of Haar wavelets.
2.3 Local binary patterns (LBP) Based Feature Extraction
LBP is a type of feature used for classification in computer vision. LBP is the particular case of the Texture Spectrum model proposed in 1990. LBP was first described in 1994. It has since been found to be a powerful feature for texture classification.
The LBP feature vector, in its simplest form, is created in the following manner:
• Divide the examined window into cells (e.g. 4x4 pixels for each cell).
• For each pixel in a cell, compare the pixel to each of its 2 neighbors (on its left-top, left-middle, left-bottom, right-top, etc.). Follow the pixels along a circle, i.e. clockwise or counter-clockwise.
• Where the center pixel's value is less than the neighbor's value, write "0". Otherwise, write "1". This gives an 8-digit binary number (which is usually converted to decimal for convenience).
• Compute the histogram, over the cell, of the frequency of each "number" occurring (i.e., each combination of which pixels are smaller and which are greater than the center).
• Optionally normalize the histogram.
• Concatenate (normalized) histograms of all cells. This gives the feature vector for the window.
2.4 K-Nearest Neighbor Classifier
In pattern recognition, the K-Nearest Neighbors algorithm (or k-NN for short) is a non-parametric method used for classificationand regression.In both cases, the input consists of the k closest training examples in the feature space. The output depends on whether k-NN is used for classification or regression:
• In k-NN classification, the output is a class membership. An object is classified by a majority vote of its neighbors, with the object being assigned to the class most common among its k nearest neighbors (k is a positive integer, typically small). If k = 1, then the object is simply assigned to the class of that single nearest neighbor.
• In k-NN regression, the output is the property value for the object. This value is the average of the values of its k nearest neighbors.
K-NN is a type of instance-based learning, or lazy learning, where the function is only approximated locally and all computation is deferred until classification. The k-NN algorithm is among the simplest of all machine learning algorithms.Both for classification and regression, it can be useful to weight the contributions of the neighbors, so that the nearer neighbors contribute more to the average than the more distant ones. For example, a common weighting scheme consists in giving each neighbor a weight of 1/d, where d is the distance to the neighbor.
The neighbors are taken from a set of objects for which the class (for k-NN classification) or the object property value (for k-NN regression) is known. This can be thought of as the training set for the algorithm, though no explicit training step is required.
2.4.1 Algorithm of K-Nearest Neighbor Classifier
The training examples are vectors in a multidimensional feature space, each with a class label. The training phase of the algorithm consists only of storing the feature vectors and class labels of the training samples.
In the classification phase, k is a user-defined constant, and an unlabeled vector (a query or test point) is classified by assigning the label which is most frequent among the k training samples nearest to that query point.
A commonly used distance metric for continuous variables is Euclidean distance. For discrete variables, such as for text classification, another metric can be used, such as the overlap metric (or Hamming distance). Often, the classification accuracy of K-NN can be improved significantly if the distance metric is learned with specialized algorithms such as Large Margin Nearest Neighbor orNeighborhood components analysis.
3. Conclusions
In this paper, a novel fast and efficient approach for human recognition via recognition of frontal faces is presented. This new approach gives excellent and effective result. The proposed system uses an efficient approach for the recognition of human being via recognition of frontal faces on the basis of LBP features. For the detection of the frontal face a well-knownViola Jones face detection technique has been employed. After the extraction of the LBP feature for the classification or recognition, the K-NN classifier has been utilized. The K-NN classier used, has inbuilt advan
[attachment=74623]
Abstract
Over a last decade face recognition has become increasingly important in the direction of computer vision, pattern recognition, surveillance, fraud detection, psychology, and content based video processing, etc. Rapid development of face recognition is due to combination of the factors such as active development of algorithms, availability of large facial database and method of evaluating the performance of recognition algorithms. Hence Face Recognition Technology has emerged as an attractive solution to address many contemporary requirements for identification and verification of identity claims.
To address human face recognition problem lots of algorithms have been proposed in the past few years. Although the available algorithms provides good face recognition, but the field is still looking for the efficient mild stone algorithm which can provide higher face recognition efficiency. To efficiently address this problem, in this paper, an Automatic Face Recognition System (AFRS) is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of some extracted features. For the detection of the frontal face proposed method uses well known Viola Jones face detection technique. Once face detection is performed, feature of interested region that is eyes and mouth are extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition, the proposed method employed highly efficient K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features. The whole system is implemented on the dataset of 30 images of frontal faces by using MATLAB 2012(b). The images were collected from the Karolinska Directed Emotional Faces (KDEF) Database. After the successful testing with the proposed system the face recognition efficiency found for the proposed system is very high and close to 100% for all the face images.
Keywords— Face Recognition, Face Features, Feature Extraction, LBP, K-NN Classifier.
1. Introduction
Face recognition is one of the important challenges in appearance-based pattern recognition field. This technology has emerged as an attractive solution to address many new needs for identification and verification of identity. It is the more familiar functionality of visual surveillance systems. It has received significant attention for decades due to its numerous potential applications. Some of these applications are national security, low enforcement, surveillance, public safety field. There are many factors affect the face recognition performance like facial expression, illumination, pose, cluttered background or occlusion. The process begins with face detection and extraction from the larger image, then normalizing the probe image so that it is in the same format (size, rotation, etc.) as the images in the database. The normalized face image is then passed to the recognition phase. Face recognition can typically be used for verification or identification. In verification an individual is already enrolled in the reference database or gallery i.e. it is a one-to-one matching task whereas in identification, a probe image is matched with a biometric reference in the gallery i.e. it represents a one-to-many problem.
To efficiently address this problem, in this paper, an Automatic Face Recognition System (AFRS) is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of some extracted features. For the detection of the frontal face proposed method uses well known Viola Jones face detection technique. Once face detection is performed, feature of interested region that is eyes and mouth are extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition, the proposed method employed highly efficient K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features.
2. Proposed Methodology
In this proposed work, an Automatic Face Recognition System is proposed. The proposed system uses an efficient approach for the recognition of human faces on the basis of extracted LBP features. For face recognition, system follows a step by step procedure that comprises face detection, feature extraction and recognition (Classification). For the detection of the frontal face proposed method uses well known face detection technique known as Viola Jones method.
Once face detection is performed, feature of interested region that is eyes and mouth is extracted. In feature extraction, local binary pattern (LBP) is proposed as a feature. After the extraction of the LBP feature for the classification or recognition the proposed method utilized K- Nearest Neighbors Classification structure to efficiently cluster the obtained LBP features. The complete process of the proposed technique is shown in figure (1), with the help of flow chart representation.
Detail description of the proposed face detection technique, LBP extraction and K- Nearest Neighbors classification are as follows:
2.1 Preprocessing
Preprocessing is the most important and the required step of the image processing. It is performed to get uniform and noise free image for further processing. This step includes the following functions:
Auto Brightness- Auto brightness function adjust the brightness of the image.
Auto Contrast- Auto contrast function automatically calculates the favorable contrast for the image will increase the brightness of the image.
Auto Color- Auto color function adjust the color of the image.
2.2 Face Detection using Viola-Jones Method
The basic principle of the Viola-Jones algorithm is to scan a sub-window capable of detecting faces across a given input image. The standard image processing approach would be to rescale the input image to different sizes and then run the fixed size detector through these images. This approach turns out to be rather time consuming due to the calculation of the different size images. Contrary to the standard approach Viola-Jones rescale the detector instead of the input image and run the detector many times through the image each time with a different size. At first one might suspect both approaches to be equally time consuming, but Viola-Jones have devised a scale invariant detector that requires the same number of calculations whatever the size. This detector is constructed using a so-called integral image and some simple rectangular features reminiscent of Haar wavelets.
2.3 Local binary patterns (LBP) Based Feature Extraction
LBP is a type of feature used for classification in computer vision. LBP is the particular case of the Texture Spectrum model proposed in 1990. LBP was first described in 1994. It has since been found to be a powerful feature for texture classification.
The LBP feature vector, in its simplest form, is created in the following manner:
• Divide the examined window into cells (e.g. 4x4 pixels for each cell).
• For each pixel in a cell, compare the pixel to each of its 2 neighbors (on its left-top, left-middle, left-bottom, right-top, etc.). Follow the pixels along a circle, i.e. clockwise or counter-clockwise.
• Where the center pixel's value is less than the neighbor's value, write "0". Otherwise, write "1". This gives an 8-digit binary number (which is usually converted to decimal for convenience).
• Compute the histogram, over the cell, of the frequency of each "number" occurring (i.e., each combination of which pixels are smaller and which are greater than the center).
• Optionally normalize the histogram.
• Concatenate (normalized) histograms of all cells. This gives the feature vector for the window.
2.4 K-Nearest Neighbor Classifier
In pattern recognition, the K-Nearest Neighbors algorithm (or k-NN for short) is a non-parametric method used for classificationand regression.In both cases, the input consists of the k closest training examples in the feature space. The output depends on whether k-NN is used for classification or regression:
• In k-NN classification, the output is a class membership. An object is classified by a majority vote of its neighbors, with the object being assigned to the class most common among its k nearest neighbors (k is a positive integer, typically small). If k = 1, then the object is simply assigned to the class of that single nearest neighbor.
• In k-NN regression, the output is the property value for the object. This value is the average of the values of its k nearest neighbors.
K-NN is a type of instance-based learning, or lazy learning, where the function is only approximated locally and all computation is deferred until classification. The k-NN algorithm is among the simplest of all machine learning algorithms.Both for classification and regression, it can be useful to weight the contributions of the neighbors, so that the nearer neighbors contribute more to the average than the more distant ones. For example, a common weighting scheme consists in giving each neighbor a weight of 1/d, where d is the distance to the neighbor.
The neighbors are taken from a set of objects for which the class (for k-NN classification) or the object property value (for k-NN regression) is known. This can be thought of as the training set for the algorithm, though no explicit training step is required.
2.4.1 Algorithm of K-Nearest Neighbor Classifier
The training examples are vectors in a multidimensional feature space, each with a class label. The training phase of the algorithm consists only of storing the feature vectors and class labels of the training samples.
In the classification phase, k is a user-defined constant, and an unlabeled vector (a query or test point) is classified by assigning the label which is most frequent among the k training samples nearest to that query point.
A commonly used distance metric for continuous variables is Euclidean distance. For discrete variables, such as for text classification, another metric can be used, such as the overlap metric (or Hamming distance). Often, the classification accuracy of K-NN can be improved significantly if the distance metric is learned with specialized algorithms such as Large Margin Nearest Neighbor orNeighborhood components analysis.
3. Conclusions
In this paper, a novel fast and efficient approach for human recognition via recognition of frontal faces is presented. This new approach gives excellent and effective result. The proposed system uses an efficient approach for the recognition of human being via recognition of frontal faces on the basis of LBP features. For the detection of the frontal face a well-knownViola Jones face detection technique has been employed. After the extraction of the LBP feature for the classification or recognition, the K-NN classifier has been utilized. The K-NN classier used, has inbuilt advan