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.
In this paper we introduce a novel framework for image classification using local visual descriptors ¨C group fusion sparse representation (GFSR), which casts the classification problem as a linear regression model with sparse constraints of the regression coefficients. Considering the intrinsic discriminative property of prior class label information, and the requirement of local consistency within...
The traditional KNN algorithm for text classification has some insufficiencies, an improved KNN algorithm has been presented in this paper. By use of the clustering center vector, we put the distance of the be classified text and the text category into the similarity calculation formula, and take the ratio of the number of common features appear in two texts and the maximum number of respective features...
The voluminous data analysis is an obstacle for video indexing and retrieval, a novel method based on video frame difference is proposed to make the fast indexing: firstly frame clustering with FSVM is used to extract the important scene in video; secondly the scenes are labelled with characteristic features; finally, the associated rule data-mining is used to fabricate the last video analysis. The...
A web text classification method using a neural network is presented here. The proposed method can classify a set of English text documents into a number of given classes depending on their contents where the number of such classes is not known a priori. Text documents, internet edition of news paper, from various faculties of games and sports are considered for experimentation. The method is found...
We approach the shape recognition domain in this paper. After an introduction in the image shape analysis domain, we describe a shape feature extraction technique using moment-based measures which are invariant to geometric transforms. Then, an automatic unsupervised feature vector classification approach is proposed. It is based on a sequence of hierarchical agglomerative region-growing clustering...
One key step in text mining is the categorization of texts, i.e., to put texts of the same or similar contents into one group so as to distinguish texts of different contents. However, traditional word-frequency-based statistical approaches, such as VSM model, failed to reflect the complicated meaning in texts. This paper ushers in domain ontology and constructs new conceptual vector space model in...
Texture segmentation by Pseudo Jacobi -Fourier moments is presented in this paper. Given a window size, moments for each pixel in the image are computed within small local windows, and then texture feature images be obtained by using a nonlinear transducer. Finally, each pixel in the image is classified by K-mean clustering algorithm.
Taking the features of data in low and high frequency texts and the frequencies which such features emerge in a single text into consideration, the paper sets up a vector space model for part of texts of field. Then the paper also establishes a classifying and clustering method with features of classification and clustering by designing and constructing the two-dimensional analytic indexes of similarities...
In this paper we study the problem of Chinese character recognition in video. We propose a series of algorithms on Chinese character division, tracking. Based on them we design a multi-level sorter. Firstly we extract the features of some samples and employ K-means clustering algorithm to carry on I level classification. Secondly, we employ the algorithm of multi back propagation neural network (MBPNN)...
Many content-based image mining systems extract local features from images to obtain an image description based on discrete feature occurrences. Such applications require a visual vocabulary also known as visual codebook or visual dictionary to discretize the extracted high-dimensional features to visual words in an efficient yet accurate way. Once such an application operates on images of a very...
We propose an automatic moment-based image recognition technique in this paper. The problem to be solved consists of classifying the images from a set, using the content similarity. In the feature extraction stage, we compute a set of feature vectors using area moments. An automatic unsupervised feature vector classification approach is proposed next. It uses a hierarchical agglomerative clustering...
Fusion based object detection method presented herein combines local and global features for object detection. The cluster based part detection facilitates adequate representation for the individual local parts of an image that carry the significant features of the object. The chain code is used for deriving the local and global information. The genetic algorithm is used to combine all the local and...
The Partitioned Feature-based Classifier (PFC) is proposed in this paper. PFC does not use entire feature vectors extracted from the original data at once to classify each datum, but use only groups of features related to each feature vector to classify data separately. In the training stage, the contribution rate calculated from each feature vector group is drawn throughout the accuracy of each feature...
Sub-surface and buried landmines, with the surrounding environment constitute a complex system with variable characteristics. Infrared thermography techniques are attractive candidates for this kind of applications. They can be used from a considerable standoff distance to provide information on several mine properties, and they can also rapidly survey large areas. This paper presents a robust method...
Due to the rapid technological developments in image/video capturing, huge data storage, video compression and networking, huge amount of video data are produced each day all over the world. Finding effective ways to store, index and retrieve these video remains a hot researching area. It is especially important for the producers/editors of television programs, since to keep track of the 1000's of...
This paper studies the combination of multiple classifiers with a prototyped-based supervised clustering algorithm, namely SGNG, for Thai printed character recognition. The proposed classification system consists of two steps. First, the prototypes obtained by the SGNG are firstly used to roughly classify an unknown input positioning around a training dataset. Second, several classifiers, such as...
There are relevance and redundancy of the feature words in the text vector space, so we proposed a text-reducing method based on the improved KNN algorithm in this paper. Vector polymer theory and feature selection methods were used to reducing the dimension of vector space. Feature words would have more ability to represent categories after feature selection. Experiments proved, the improved KNN...
The popularity of the Internet has caused a massive increase in the amount of Web pages. The information explosion has led to a growing challenge for information retrieval systems. Document clustering becomes an important process for helping the information retrieval systems organize this vast amount of data. It is believed that grouping similar documents together into clusters will help the users...
Fuzzy relational classifier (FRC) is the recently proposed two-step nonlinear classifiers, which effectively integrates the formed clusters and the given classes. However, FRC can not copy with the influence of those irrelevant or redundant features. To effectively filter out those irrelevant features and preserve the internal structure hidden in the given data, in this paper, a simultaneous clustering...
The image semantic classification is new focus in the image classification field, the traditional classification algorithm is based on the low level visual features, but there is an enormous semantic gap problem between the low-level visual features and high-level semantic information of images. An image semantic classification approach is proposed based on Kernel PCA Support Vector Machines (KPCA...
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.