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.
The goal of this paper is the presentation of a method and results for artificial neural networks crops classification based on HyMap hyperspectral data. The method that uses an ANNs does not only depend on statistical parameters of particular class and hence makes it possible to include texture information. To experiment with variable pattern size two data sets were chosen with 10 bands obtained...
This paper proposes a new multiple instance learning (MIL) method based on a MIL back-propagation neural network (MIBP), which is an extension of the standard back-propagation neural network (BPNN) that uses labeled bags of instances as training data. The method finds a concept point t in the feature space which is close to instances from positive bags and far from instances in negative bags. Our...
This paper reviews the current soft computing (SC) techniques employed in image steganography as well as proposes a new hybrid approach of these SC techniques to exploit their complementary strengths. Four main SC techniques in image steganography - neural network (NN), genetic algorithm (GA), support vector machines (SVM) and fuzzy logic (FL) are assessed based on the three main measurements of steganography...
In recent years, the development of high-resolution remote sensing image extends the visual field of the terrain features. Quickbird and other high-resolution remote sensing image can show more characteristics such as shape, spectral, texture and so on. Back Propagation neural network is widely used in remote sensing image classification in recent years, it is a self-adaptive dynamical system which...
This paper presents a new classification method based on a combination of GIS and BP (back propagation) artificial neural network, taking the TM image of the area of Jinzhou city in 2000 as the testing one. BP neural network can be optimized by means of selecting GIS data aided training sample, improving training algorithm, calculating the number of nodes in the hidden layer and so on. Compared with...
Supervised classification in remote sensing imagery is receiving increasing attention in current research. In order to improve the classification ability, a lot of spatial-features (e.g., texture information generated by GLCM) have been utilized. Unfortunately, too many spatial-features often cause classifier over-fit to a certain features' character and lead to lower classification accuracy. The...
Optical Characters Recognition (OCR) is one of the active subjects of research since the early days of computer science. There are two main stages in most of OCR systems: features extraction and classification. Artificial Neural Networks and Hidden Markov Models are the most popular classification methods used for OCR systems. In this paper, a method that relays on Fast Wavelets Transform (FWT) for...
Gender classification problem is an active area of research; recently it had attracted many researchers. This study presents an efficient gender classification technique. Weighted Majority Voting (WMV) is the most popular technique used to combine individual classifiers in an ensemble based classification. Genetic Algorithm (GA) is a global optimization technique and is being widely used by the researchers...
The remote sensing shows a widest perspective for land reclamation in mining areas. Based on how to improve the classification accuracy of mine image, we did some classification researchs with LVQ2 neural network. The proposed method had been applied to the aerial image of Heng country, Guangxi Province. The total classification accuracy was 72%, comparing with the minimum distance method increased...
This paper presents a novel multi-level approach for bleeding detection in Wireless Capsule Endoscopy (WCE) images. In the low-level processing, each cell of K×K pixels is characterized by an adaptive color histogram which optimizes the information representation for WCE images. A Neural Network (NN) cell-classifier is trained to classify cells in an image as bleeding or non-bleeding patches. In the...
To improve the accuracy and sensitivity of the breast tumor classification based on ultrasound images, a computer-aided classification algorithm is proposed using the Affinity Propagation (AP) clustering. Five morphologic features and three texture features are extracted from each breast ultrasound image. The AP clustering with an empirical value of "preference" is used as the primary classification...
This paper presents a novel approach to single-frame pedestrian classification and orientation estimation. Unlike previous work which addressed classification and orientation separately with different models, our method involves a probabilistic framework to approach both in a unified fashion. We address both problems in terms of a set of view-related models which couple discriminative expert classifiers...
The classification of affective semantics in images is a very challenging research direction that gains more and more attention in the research community. However, as an emerging topic, contributions remain relatively rare, and a lot of issues need to be addressed particularly concerning the three following fundamentals problems: emotion representation, image features used to represent emotions and...
The k-nearest neighbor (K-NN) framework was successfully used for tasks of computer vision. In image categorization, k-NN is an important and significant rule. However, two major problems usually affect this rule: the NN classifier vote and the metric employed to compute the distance between neighbors. This paper deals with both. First, a boosting k-NN algorithm learns the coefficients of weak classifiers,...
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensionality reduction can be employed to find a low-dimensional representation on which classification can be done more efficiently. Existing methods for supervised dimensionality reduction often presume that the data is densely sampled...
This paper presents a method to extract features by PCA (Principal component analysis) from a series of woods surfaces' images. The method introduces a principal component subspace and can reserve original information while extraction mainly information. The emulated results show that we can fuse the image series and extract features from the four images of a same surface by using this method. After...
This paper proposes a new learning method, which integrates feature selection with classifier construction for human detection via solving three optimization models. Firstly, the method trains a series of weak-classifiers by the proposed L1-norm Minimization Learning (LML) and min-max penalty function models. Secondly, the proposed method selects the weak-classifiers by using the integer optimization...
Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like Nearest-Neighbor...
Automatic inspection on line plays an important role in industrial quality management nowadays. This paper proposes a new computer vision system for automatic steel surface inspection. The system analyzes the images sequentially acquired from steel bar to detect different kinds of defects on the steel surface. Several image processing strategies are used to detect and outline the defects. The detected...
This paper presents a method for pavement crack detection, classification and evaluation using the Radon transform. The detection part of the algorithm is built upon the wavelet transform and the evaluation part is considered in the Radon transform domain. Since cracks have specific linear features in the space domain, the Radon transform can effectively be used on a binary image to classify and evaluate...
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.