Multiple Neural Networks and Bayesian Belief Revision for a never-ending unsupervised learning. (original) (raw)
Related papers
A Face Recognition Problem Solved by a Never-Ending Unsupervised Learning
We propose a Hybrid System for dynamic environments, where a "Multiple Neural Networks" system works with Bayes Rule to solve the face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject), by applying two algorithms, the “Inclusion based weighted” and the “Weighted” one over all the maximally consistent subsets of the global outcome. Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning
The interest towards biometric approach to identity verification is high, because of the need to protect everything that could have a value for some purpose. Face recognition is one of these biometric techniques, having its greater advantage in requiring a limited interaction by user. We present a Face Recognition System (FRS) based on multiple neural networks using a belief revision mechanism. Each network is associated to an a-priori reliability value for each identity stored in database, modelling the specific skill of the modules composing the system with the recognition of a given subject. Every time a network is in conflict with the global response, it is forced to retrain itself, subjecting the system to a continuous learning. The main goal of this work is to carry out some preliminary tests to evalu- ate accuracy and robustness of FRS with “subject-dependent” reliability values, when some changes can affect the considered features. Tests over digitally aged faces are also conducted
A Continuous Learning for Solving a Face Recognition Problem
We propose a Hybrid System for dynamic environments, where a "Multiple Neural Networks" system works with Bayes Rule to solve the face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject), by applying two algorithms, the “Inclusion based weighted” and the “Weighted” one over all the maximally consistent subsets of the global outcome. Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.
Face Recognition System in a Dynamical Environment.
We propose a Hybrid System for dynamic environments, where a “Multiple Neural Networks” system works with Bayes Rule to solve the face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice. Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.
A Continuous Learning in a Changing Environment.
We propose a Hybrid System for dynamic environments, where a "Multiple Neural Networks" system works with Bayes Rule to solve a face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net's degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject). Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning
A Multi-Agent Model for Face Recognition Using Multi-Featurs and Multi-Classifiers
The International Conference on Electrical Engineering (Print), 2008
This paper presents a new model based on multi-agent technology for face recognition using multi-features and multi-classifiers. The human faces are verified by projecting face images onto a feature space that spans the significant variations among known faces by computing the discrete cosine transform (DCT) and discrete wavelet transform (DWT) features. The classifiers used in this research namely, K-nearest neighbor (K-NN), neural network (NN), support vector machine (SVM), BayesNet, classification and regression tree (CART), and decision tree algorithm (C4.5). The experimental results using these classifiers individually show that the recognition rate is up to 95% on the Olivetti Research Laboratory (ORL) database of facial images [14]. To improve the performance of the model, the classifier with the highest recognition rate is correlated with other classifiers to select the most suitable complementary group of classifiers that give a high recognition rate. Each classifier in the group is represented by agent in a multi-agent system. An average of 97% recognition rate is reached using K-NN, NN, and CART. Again, to improve the performance of the model, each classifier in the agents group is applied on the DCT feature vector and if the recognized face is not matched with the personal information database then it is applied on the DWT feature vector. The experimental results showed that the recognition rate using this model is up to 99.5%.
FACE RECOGNITION USING NEURAL NETWORK
Although the distinction between optimum decision and pre-processing or feature extraction is not essential, the concept of functional breakdown provides a clear picture for the understanding of the pattern recognition problem. Correct recognition will depend on the amount of discriminating information contained in the measurements and the effective utilization of this information. In some applications, contextual information is indispensable in achieving accurate recognition. For instance, in the recognition of cursive handwritten characters and the classification of fingerprints, contextual information is extremely desirable. When we wish to design a pattern recognition system which is resistant to distortions, flexible under large pattern deviations, and capable of self-adjustment, we are confronted with the adaptation problem. There are many interesting problems that remain in the area of face recognition.
Dynamic Bayesian Network for Unconstrained Face Recognition in Surveillance Camera Networks
IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2013
The demand for robust face recognition in real-world surveillance cameras is increasing due to the needs of practical applications such as security and surveillance. Although face recognition has been studied extensively in the literature, achieving good performance in surveillance videos with unconstrained faces is inherently difficult. During the image acquisition process, the noncooperative subjects appear in arbitrary poses and resolutions in different lighting conditions, together with noise and blurriness of images. In addition, multiple cameras are usually distributed in a camera network and different cameras often capture a subject in different views. In this paper, we aim at tackling this unconstrained face recognition problem and utilizing multiple cameras to improve the recognition accuracy using a probabilistic approach. We propose a dynamic Bayesian network to incorporate the information from different cameras as well as the temporal clues from frames in a video sequence. The proposed method is tested on a public surveillance video dataset with a three-camera setup. We compare our method to different benchmark classifiers with various feature descriptors. The results demonstrate that by modeling the face in a dynamic manner the recognition performance in a multi-camera network is improved over the other classifiers with various feature descriptors and the recognition result is better than using any of the single camera.
Face Recognition in Multi-Camera Surveillance Videos using Dynamic Bayesian Network
Face recognition in surveillance videos is inherently difficult due to the limitation of the camera hardware as well as the image acquisition process in which non-cooperative subjects are recorded in arbitrary poses and resolutions in different lighting conditions with noise and blurriness. Furthermore, as multiple cameras are usually distributed in a camera network and the subjects are moving, different cameras often capture the subject in different views. In this paper, we propose a probabilistic approach for face recognition suitable for a multi-camera video surveillance network. A Dynamic Bayesian Network (DBN) is used to incorporate the information from different cameras as well as the temporal clues from consecutive frames. The proposed method is tested on a public surveillance video dataset. We compare our method to different well-known classifiers with various feature descriptors. The results demonstrate that by modeling the face in a dynamic manner the recognition performance in a multi-camera network can be improved.
Face Recognition using Probabilistic Model for Locally Changed Face
International Journal of Innovative Technology and Exploring Engineering, 2019
Face recognition is an attention-grabbing area in research field due to various challenges like aging, pose variation, facial expression, and illumination problem. Now-a-days, plastic surgery is a standout amongst the above mentioned exciting issues of face recognition. Local plastic surgery is a type of plastic surgery in which any one feature of the face is changed instead of all features of face. In this paper, the face recognition on local plastic surgical faces using probabilistic approach is presented, where a probabilistic approach like Naive Bayes Classifier, Neural Network Classifier are used to recognize the faces with local plastic surgery from the database. Naive Bayes classifier is fused with Expectation Maximization Algorithm (EMA) for better recognition of the faces from the database. Finally, Results of Naive Bayes Classifier, Naive Bayes Classifier with EMA is evaluated on standard Plastic Surgery Database(PSD). Similarly, Neural network classifier is also been test...