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.
Image classification techniques play a significant role in the remote sensing imagery. Many of the researchers found some difficulties while doing the analysis of satellite images. During the classification task, many questions have arisen in the minds of the experts and they might face many challenging issues. SSEP (Semi Supervised Ensemble Projection) is a newly adopted method that yields better...
Image classification is one of the most multifaceted disciplines in image processing. There are quite a few approaches to categorize images and they offer good classification outcome but they not be up to snuff to provide acceptable classification upshots when the image comprises blurry content. The two chief techniques for image classification are supervised and unsupervised classification. Mutually...
Aiming at application to automated recognition of knee bone magnetic resonance (MR) images, an evolutional classification method called CBGA-LDIC is proposed. CBGA-LDIC finds an appropriate cell set towards efficient image segmentation. This method uses location-dependent image classification (LDIC), which is integrated by genetic algorithm (GA) combined with case based reasoning (CB). LDIC introduces...
In image classification and retrieval, the semantic gap is the major challenge. It characterizes the difference between human perception of a concept and how it can be represented using machine level language. Bag of visual words is a well-known efficient method for image representation, however it showed some limitations. The loss of information during the vector quantization process is one of these...
We present an image classification method which consists of salient region (SR) detection, local feature extraction, and pairwise local observations based Naive Bayes classifier (NBPLO). Different from previous image classification algorithms, we propose a scale, translation, and rotation invariant image classification algorithm. Based on the discriminative pairwise local observations, we develop...
This paper presents a novelty classification method based on multivariate Bernoulli naive Bayes with Dirichlet prior and hyper parameter optimization. We test the proposed method on 15-Scenes and Msrc-v2 data set by comparing with basic multivariate Bernoulli naive Bayes and SVM (Support Vector Machine). The experiments show that our method has advantages both in running time and classification precision.
We show that holistic image features, specifically GIST, can be used for semantic scene categorization. In our study, the problem of indooroutdoor scene classification is addressed. We first propose a simple yet efficient pipeline in which the GIST vector of an image is initially computed. For the classification task, a feedforward neural network is trained with a comprehensive training dataset. The...
In computer vision system, texture refers to the characteristics of an object that appear on its surface. Texture classification is to classify textures in correct texture groups. The accuracy of texture image classification depends on quality of texture features and classification algorithm used. In this paper, Brodatz texture images are used as an experimental data. Features are extracted from texture...
For hyperspectral image classification, feature extraction is a crucial pre-process for avoiding the Hughes phenomena. Some feature extraction methods such as linear discriminant analysis (LDA), nonparametric weighted feature extraction (NWFE), and their kernel versions, generalized discriminant analysis (GDA) and kernel nonparametric weighted feature extraction method (KNWFE) have been shown that...
Many research shows that we will encounter the Highes phenomenon when dealing with the high-dimensional data classification problem. In addition, non-linear support vector machine (SVM) has been shown that it can conquer the problem efficiently. However, the SVM is a black-box model based on the whole features and does not provide the feature importance or “good” feature subset for classification...
In recent years, the researches based on Convolutional Neural Network (CNN) have been doing in computer vision after the success in ILSVRC 2012. Hierarchical feature extraction is one of the reasons why CNN gives the state-of-the-art performance. On the other hand, Partial Least Squares (PLS) Regression which has been widely used in chemo-metrics is also used in computer vision in recent years. If...
Spatial information has been verified to be helpful in hyperspectral image classification. In this paper, a spatial feature extraction method utilizing spatial and orientational auto-correlations of image local gradients is presented for hyperspectral imagery (HSI) classification. The Gradient Local Auto-Correlations (GLAC) method employs second order statistics (i.e., auto-correlations) to capture...
Motivated by the widespread adoption of social networks and the abundant availability of user-generated multimedia content, our purpose in this work is to investigate how the known principles of active learning for image classification fit in this newly developed context. The process of active learning can be fully automated in this social context by replacing the human oracle with the user tagged...
Social media mining from Internet has been an emerging research topic. The problem is challenging because of massive data contents from various sources, especially image data from user upload. In recent years, dictionary learning based image classification has been widely studied and gained significant success. In this paper, we propose a framework for automatic detection of interested uniforms in...
This paper introduces a regularization method called Correlative Filter (CF) for Convolutional Neural Network (CNN), which takes advantage of the relevance between the convolutional kernels belonging to the same convolutional layer. During the process of training with the proposed CF method, several pairs of filters are designed in a manner of randomness to contain opposite weights in low-level layers...
Dictionary learning (DL) approach has been successfully applied to many pattern classification problems. Sparse property has played an important role in the success of DL-based classification models. However, the sparsity constraints make the learning problem expensive. Recently, there has been an emerged trend in relaxing the sparsity constraints by using L2-norm constraint. The new approach has...
We propose a convolutional autoencoder neural network for image classification in YCbCr color space to reduce computational complexity. We first learned local image features from image patches in YCbCr space with a sparse autoencoder and then convolved them with large images to obtain global features. Chrominance components were subsampled before convolution as it is permitted to reduce bandwidth...
This article puts forward a kind of huge amounts of multi-object image recognition method -- BVCNN. Firstly, BING method is used to recognize images, which greatly reduces the time of estimating image targets, and makes it possible that quickly identify multiple target images, compared to traditional convolution neural networks only achieving single target image recognition, Secondly, vectorization...
In this paper we explore the role of scale for improved feature learning in convolutional networks. We propose multi-neighborhood convolutional networks, designed to learn image features at different levels of detail. Utilizing nonlinear scale-space models, the proposed multi-neighborhood model can effectively capture fine-scale image characteristics (i.e., appearance) using a small-size neighborhood,...
A new approach called Fuzzy Extended Feature Line (FEFL) is proposed for image classification in this paper, which retain the advantages and ideas of Nearest Feature Line (NFL). The proposed FEFL use NFL to extend the prototype image sample set. Fuzzy K-Nearest Neighbor is applied for adding the new suitable samples to the prototype sample set. Experimental results on ORL face database and finger-knuckle-print...
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.