The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Traffic sign recognition is an example of a hard multiclass classification problem. The existing approaches to that problem typically associate with each sign class a real-valued likelihood function and assign such a label to the unknown image that maximizes the value of this function. These template-matching techniques are usually based on arbitrary similarity metrics, such as normalized cross correlation,...
Video artificial text detection is a challenging problem of pattern recognition. Current methods which are usually based on edge, texture, connected domain, feature or learning are always limited by size, location, language of artificial text in video. To solve the problems mentioned above, this paper applied SOM (Self-Organizing Map) based on supervised learning to video artificial text detection...
Defect detection on industrial flat surface products like textiles, steel slabs, metal plates, plastic films, painted car body, parquet slabs and paper is a necessary requirement for quality control and satisfaction of consumers. This paper presents a system for feature extraction and fusion in order to enhance the performance of the defect detection process. A multi-feature fusion technique based...
In this paper, we present an active boosting algorithm to learn the object detector. This algorithm is to find good features from a confidential map instead of brute-force searching the predefined feature set. The confidential map is computed from the importance re-sampled data. A new feature is created by the linear combination of blocks that are selected from different segmented regions. In addition,...
This paper describes the comparison of accuracy and performance of two machine learning approaches for visual object detection and tracking vehicles, from an on-road image sequence. The first is a neural network based approach. where an algorithm of multi resolution technique based on Haar basis functions was used to obtain an image with different scales. Thereafter a classification was carried out...
Artificial Neural Networks (ANN) is gaining significant importance for pattern recognition applications particularly in the medical field. A hybrid neural network such as Counter Propagation Neural Network (CPN) is highly desirable since it comprises the advantages of supervised and unsupervised training methodologies. Even though it guarantees high accuracy, the network is computationally non-feasible...
An automatic detection algorithm for dead birds based on support vector machine (SVM) is proposed. Firstly, according to the changes of central region of cockscomb in the picture, logic and operation is used to remove the image of live chickens; Secondly, in order to distinguish accurately the dead birds in processed picture, the perimeter, area, eccentricity and complexity of the cockscomb are extracted...
Sparse representation for machine learning has been exploited in past years. Several sparse representation based classification algorithms have been developed for some applications, for example, face recognition. In this paper, we propose an improved sparse representation based classification algorithm. Firstly, for a discriminative representation, a non-negative constraint of sparse coefficient is...
We investigate the problem of combining multiple feature channels for the purpose of efficient image classification. Discriminative kernel based methods, such as SVMs, have been shown to be quite effective for image classification. To use these methods with several feature channels, one needs to combine base kernels computed from them. Multiple kernel learning is an effective method for combining...
This paper presents a novel and domain-independent approach for graph-based structure learning. The approach is based on solving the maximum common subgraph-isomorphism problem to generalise a model graph over a set of training examples. Then a full probabilistic model is assigned to the learnt graph. We call this approach probabilistic structure graphs (PSGs). This article explains how PSG models...
Support vector machine (SVM) is a machine learning algorithm, which has been used recently for classification of hyperspectral images. SVM uses various kernel functions like RBF and polynomial to map the data into higher dimensional space to improve data separability. New kernel functions are used in this paper to classify hyperspectral images which are based on wavelet functions as named wavelet-kernels...
State-of-the-art pattern recognition methods have difficulties dealing with problems where the dimension of the output space is large. In this article, we propose a framework based on deep architectures (e. g. deep neural networks) in order to deal with this issue. Deep architectures have proven to be efficient for high dimensional input problems such as image classification, due to their ability...
This paper represents a currency recognition system using ensemble neural network (ENN). The individual neural networks (NN) in an ENN are trained via negative correlation learning. The object of using negative correlation learning (NCL) is to expertise the individuals in an ensemble on different parts or portion of input patterns. The available currencies in the market consist of new, old and noisy...
In order to eliminate the shortcomings of traditional neural networks in handwritten Chinese characters recognition, such as the premature convergence, a novel intelligent method is presented, which uses the particle swarm optimization (PSO) algorithm with adaptive inertia weight to train the neural networks. The main idea is that the optimum weights and thresholds of the neural networks is acquired...
Artificial Metaplasticity (AMP) is a novel Artificial Neural Network (ANN) training algorithm inspired in biological metaplasticity property of neurons and Shannon's information theory. During training phase, the AMP training algorithm gives more relevance to the less frequent patterns and subtracts relevance to the frequent ones, achieving a much more efficient training, while at least maintaining...
We consider the problem of parsing facial features from an image labeling perspective. We learn a per-pixel unary classifier, and a prior over expected label configurations, allowing us to estimate a dense labeling of facial images by part (e.g. hair, mouth, moustache, hat). This approach deals naturally with large variations in shape and appearance characteristic of unconstrained facial images, and...
We propose an incremental classifier learning framework that starts with a small amount of labeled training data to create an initial set of classifiers, and gradually incorporates unlabeled data into the incremental learning process to improve the models. A key to the effectiveness of the proposed framework is to judicially select a good incremental learning subset from all remaining unlabeled samples...
This paper examines whether machine learning and image analysis tools can be used to assist art experts in the authentication of unknown or disputed paintings. Recent work on this topic has presented some promising initial results. Our reexamination of some of these recently successful experiments shows that variations in image clarity in the experimental datasets were correlated with authenticity,...
Since health care on foods is drawing people's attention recently, a system that can record everyday meals easily is being awaited. In this paper, we propose an automatic food image recognition system for recording people's eating habits. In the proposed system, we use the Multiple Kernel Learning (MKL) method to integrate several kinds of image features such as color, texture and SIFT adaptively...
Sparse representation for robust face recognition is a novel concept in the pattern analysis and machine learning community. Through the l1-minimization model, representing a test sample as the sparse combination of the training dictionary can effectively achieve facial images classification. However, when the number of training samples is relatively small, it is insufficient to give the test sample...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.