scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

An efficient and robust face detection method using neuro-fuzzy approach

22 Dec 2011-pp 1-5
TL;DR: The approach presented is an amalgamation of artificial neural networks and fuzzy set theory that runs in two phases and fuses the results for better performance and accuracy.
Abstract: Person identification plays a major role in any secured and safety system. Face is one of the major biometric explored by many researchers for human identification. The problem becomes more complex by means of any occlusion of objects, due to different illumination, expression and pose. We propose a novel pattern recognition approach for face detection in this paper. The approach presented is an amalgamation of artificial neural networks and fuzzy set theory. The proposed method runs in two phases and fuses the results for better performance and accuracy. The proposed method has been tested on BioID dataset and got 94% accuracy.
Citations
More filters
21 Jul 2009
TL;DR: Data mining techniques that use metrics defined on sets of partitions of finite sets such as decision tree induction, feature selection, and data discretization are discussed.
Abstract: The paper is centered on an algebraic approach to the notion of entropy and of several related concepts (conditional entropy, gain, metrics on sets of partitions produced by entropic approaches). Partitions are naturally associated with major data mining problems such as classification, clustering, data quality evaluations, and data preparation. This areas benefit from an algebraic and geometric study of metric structures defined on partitions. We discuss data mining techniques that use metrics defined on sets of partitions of finite sets such as decision tree induction, feature selection, and data discretization.

85 citations

Proceedings ArticleDOI
10 Jun 2012
TL;DR: The proposed technique demonstrated that ANNs trained by IPSONet has better performance than ANNstrained by BP in the face detection task.
Abstract: Artificial Neural Networks (ANNs) has been applied in the face detection task because of its ability to capture the complex probability distribution conditioned to the class of face patterns. However, many works use Back-Propagation (BP) to adapt the weights of the ANNs. The problem of using BP is that it has many disadvantages related to the appropriate choice of its parameters, as the learning rate and momentum. Furthermore, since BP assumes a fixed architecture for the ANN, an inappropriate choice of the architecture can make it have a sub-optimal performance. In this paper we investigate the application of the IPSONet in the facial detection task. IPSONet is a training technique for neural networks like multilayer perceptron (MLP) that uses an improved PSO to evolve simultaneously structure and weights of ANNs. Thus, the IPSONet produces ANNs with higher generalization ability if compared to BP. The system developed in this work, which includes the feature extraction process of the input image and the training of a MLP net using IPSONet is called IPSONetFD. The experiments using the MIT CBCL Face Database showed that the proposed technique is robust in the sense that it can detect faces with a wide variety of pose, lighting and face expression. The results showed that the IPSONetFD had better performance than others ANN's architectures (PyraNet and I-PyraNet, in this study), and an equivalent performance if compared to SVM. Thus, the proposed technique demonstrated that ANNs trained by IPSONet has better performance than ANNs trained by BP in the face detection task.

1 citations


Cites methods from "An efficient and robust face detect..."

  • ...In [9], for example, several experiments were performed for find a reasonable architecture for the face detection task....

    [...]

01 Jan 2015
TL;DR: This paper applied AdaBoost, an aggressive learning algorithm for solving classification problems, which combines an ensemble of weak classifiers into a strong classifier for face detection, and a new boosting algorithm i.e. MLPBoost which is hybridization between AdaBoost and multi-layer perceptron networks.
Abstract: An ideal Face Detection system should be able to identify and locate all faces regardless of their positions, scale, orientation, lightning conditions, and expressions and so on. Face Detection is the prior stage in any face processing system, as it provides challenging research area in computer vision and is of great interest. Challenges resides in the fact that the faces are non-rigid objects. The goal of face detection is to detect human faces in still images or in different situations. Some parameters plays a crucial role while detecting the faces amongst still images such as false positive, false negative, true positive, and detection rate. High detection rate with high speed and accuracy of detector is the prime goal of this system. In this paper, we applied Boosting Algorithm [5] which is capable of processing images rapidly. Here, we applied AdaBoost which is an aggressive learning algorithm for solving classification problems, which combines an ensemble of weak classifiers into a strong classifier. Specifically, to increase the Speed and Accuracy of the system which is the important feature in case of this face detection system is being done with these neural network based boosting algorithms. By taking AdaBoost classifiers in cascaded manner, a new boosting algorithm i.e. MLPBoost [1] which we used as a strong classifier for face detection. Basically, MLPBoost is hybridization between AdaBoost and multi-layer perceptron networks. PCA i.e. Principal Component Analysis is a very popular unsupervised statistical method to find useful image representation [2]. This method find out set of basic images and represents all the faces as a linear combination of those images. Keywords-AdaBoost, Face Detection, MLPBoost, PCA (Principal Component Analysis).
References
More filters
Book
16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Abstract: From the Publisher: This book represents the most comprehensive treatment available of neural networks from an engineering perspective. Thorough, well-organized, and completely up to date, it examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Written in a concise and fluid manner, by a foremost engineering textbook author, to make the material more accessible, this book is ideal for professional engineers and graduate students entering this exciting field. Computer experiments, problems, worked examples, a bibliography, photographs, and illustrations reinforce key concepts.

29,130 citations


"An efficient and robust face detect..." refers background in this paper

  • ...The concepts reviewed are taken as they are defined in [11-12]....

    [...]

Book
01 Dec 1994
TL;DR: This chapter discusses Fuzzy Systems Simulation, specifically the development of Membership Functions and the Extension Principle, and some of the methods used to derive these functions.
Abstract: About the Author. Preface to the Third Edition. 1 Introduction. The Case for Imprecision. A Historical Perspective. The Utility of Fuzzy Systems. Limitations of Fuzzy Systems. The Illusion: Ignoring Uncertainty and Accuracy. Uncertainty and Information. The Unknown. Fuzzy Sets and Membership. Chance Versus Fuzziness. Sets as Points in Hypercubes. Summary. References. Problems. 2 Classical Sets and Fuzzy Sets. Classical Sets. Operations on Classical Sets. Properties of Classical (Crisp) Sets. Mapping of Classical Sets to Functions. Fuzzy Sets. Fuzzy Set Operations. Properties of Fuzzy Sets. Alternative Fuzzy Set Operations. Summary. References. Problems. 3 Classical Relations and Fuzzy Relations. Cartesian Product. Crisp Relations. Cardinality of Crisp Relations. Operations on Crisp Relations. Properties of Crisp Relations. Composition. Fuzzy Relations. Cardinality of Fuzzy Relations. Operations on Fuzzy Relations. Properties of Fuzzy Relations. Fuzzy Cartesian Product and Composition. Tolerance and Equivalence Relations. Crisp Equivalence Relation. Crisp Tolerance Relation. Fuzzy Tolerance and Equivalence Relations. Value Assignments. Cosine Amplitude. Max Min Method. Other Similarity Methods. Other Forms of the Composition Operation. Summary. References. Problems. 4 Properties of Membership Functions, Fuzzification, and Defuzzification. Features of the Membership Function. Various Forms. Fuzzification. Defuzzification to Crisp Sets. -Cuts for Fuzzy Relations. Defuzzification to Scalars. Summary. References. Problems. 5 Logic and Fuzzy Systems. Part I Logic. Classical Logic. Proof. Fuzzy Logic. Approximate Reasoning. Other Forms of the Implication Operation. Part II Fuzzy Systems. Natural Language. Linguistic Hedges. Fuzzy (Rule-Based) Systems. Graphical Techniques of Inference. Summary. References. Problems. 6 Development of Membership Functions. Membership Value Assignments. Intuition. Inference. Rank Ordering. Neural Networks. Genetic Algorithms. Inductive Reasoning. Summary. References. Problems. 7 Automated Methods for Fuzzy Systems. Definitions. Batch Least Squares Algorithm. Recursive Least Squares Algorithm. Gradient Method. Clustering Method. Learning From Examples. Modified Learning From Examples. Summary. References. Problems. 8 Fuzzy Systems Simulation. Fuzzy Relational Equations. Nonlinear Simulation Using Fuzzy Systems. Fuzzy Associative Memories (FAMS). Summary. References. Problems. 9 Decision Making with Fuzzy Information. Fuzzy Synthetic Evaluation. Fuzzy Ordering. Nontransitive Ranking. Preference and Consensus. Multiobjective Decision Making. Fuzzy Bayesian Decision Method. Decision Making Under Fuzzy States and Fuzzy Actions. Summary. References. Problems. 10 Fuzzy Classification. Classification by Equivalence Relations. Crisp Relations. Fuzzy Relations. Cluster Analysis. Cluster Validity. c-Means Clustering. Hard c-Means (HCM). Fuzzy c-Means (FCM). Fuzzy c-Means Algorithm. Classification Metric. Hardening the Fuzzy c-Partition. Similarity Relations from Clustering. Summary. References. Problems. 11 Fuzzy Pattern Recognition. Feature Analysis. Partitions of the Feature Space. Single-Sample Identification. Multifeature Pattern Recognition. Image Processing. Summary. References. Problems. 12 Fuzzy Arithmetic and the Extension Principle. Extension Principle. Crisp Functions, Mapping, and Relations. Functions of Fuzzy Sets Extension Principle. Fuzzy Transform (Mapping). Practical Considerations. Fuzzy Arithmetic. Interval Analysis in Arithmetic. Approximate Methods of Extension. Vertex Method. DSW Algorithm. Restricted DSW Algorithm. Comparisons. Summary. References. Problems. 13 Fuzzy Control Systems. Control System Design Problem. Control (Decision) Surface. Assumptions in a Fuzzy Control System Design. Simple Fuzzy Logic Controllers. Examples of Fuzzy Control System Design. Aircraft Landing Control Problem. Fuzzy Engineering Process Control. Classical Feedback Control. Fuzzy Control. Fuzzy Statistical Process Control. Measurement Data Traditional SPC. Attribute Data Traditional SPC. Industrial Applications. Summary. References. Problems. 14 Miscellaneous Topics. Fuzzy Optimization. One-Dimensional Optimization. Fuzzy Cognitive Mapping. Concept Variables and Causal Relations. Fuzzy Cognitive Maps. Agent-Based Models. Summary. References. Problems. 15 Monotone Measures: Belief, Plausibility, Probability, and Possibility. Monotone Measures. Belief and Plausibility. Evidence Theory. Probability Measures. Possibility and Necessity Measures. Possibility Distributions as Fuzzy Sets. Possibility Distributions Derived from Empirical Intervals. Deriving Possibility Distributions from Overlapping Intervals. Redistributing Weight from Nonconsonant to Consonant Intervals. Comparison of Possibility Theory and Probability Theory. Summary. References. Problems. Index.

4,958 citations


"An efficient and robust face detect..." refers background in this paper

  • ...The concepts reviewed are taken as they are defined in [11-12]....

    [...]

Journal ArticleDOI
TL;DR: A neural network-based upright frontal face detection system that arbitrates between multiple networks to improve performance over a single network, and a straightforward procedure for aligning positive face examples for training.
Abstract: We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates.

4,105 citations


"An efficient and robust face detect..." refers background in this paper

  • ...The researchers were focused on appearance-based approaches [5-8] and knowledge based methods [9]....

    [...]

Journal ArticleDOI
TL;DR: In this article, the authors categorize and evaluate face detection algorithms and discuss relevant issues such as data collection, evaluation metrics and benchmarking, and conclude with several promising directions for future research.
Abstract: Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.

3,894 citations


"An efficient and robust face detect..." refers methods in this paper

  • ...Early methods focused only on the detection and localization of human faces facing towards camera [2-3]....

    [...]

Proceedings ArticleDOI
04 Jan 1998
TL;DR: A general trainable framework for object detection in static images of cluttered scenes based on a wavelet representation of an object class derived from a statistical analysis of the class instances and a motion-based extension to enhance the performance of the detection algorithm over video sequences is presented.
Abstract: This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representation of an object class derived from a statistical analysis of the class instances. By learning an object class in terms of a subset of an overcomplete dictionary of wavelet basis functions, we derive a compact representation of an object class which is used as an input to a support vector machine classifier. This representation overcomes both the problem of in-class variability and provides a low false detection rate in unconstrained environments. We demonstrate the capabilities of the technique in two domains whose inherent information content differs significantly. The first system is face detection and the second is the domain of people which, in contrast to faces, vary greatly in color, texture, and patterns. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models or motion-based segmentation. The paper also presents a motion-based extension to enhance the performance of the detection algorithm over video sequences. The results presented here suggest that this architecture may well be quite general.

1,594 citations


"An efficient and robust face detect..." refers background in this paper

  • ...Face detection can also be considered as a specific case of object detection [1]....

    [...]