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.
Spell checking plays an important role in improving the quality of documents by identifying misspelled words in the document. There are various efforts made towards advancement of spell checkers on other languages such as in English that has almost perfected spell checking system (e.g. Microsoft Word). However, few efforts were made to develop an efficient Filipino spell checker. One major challenge...
Human being normally uses natural language in form of written or spoken in their daily life. It is an entirely concept based on Artificial Intelligence, Computer Science and Linguistic resources. In Indian languages, Gujarati is an Indo — Aryan language with rich and high inflection. In these languages, several words have common root that's need to be reduced by using stemmer. Stemmer is used to reduce...
This paper considers a problem of highly compressing the data called “Digital-Ink” which is a sequence of position data sampled from the traced curve at a sampling rate. We here suppose that a set of digital-ink is measured and stored as two-dimensional position data by electronic device (e.g. smart-phone and pen-tablet PC, etc.). Then, we develop a method of digital-ink compression using B-spline...
Finding substantial features is a significant approach to cope the challenges of video anomaly detection and localization. The specific important representation are selected to detect an event in video. State-of-the-art models explore this fashion by do seeking interest points both spatially and temporally. However, it has to very selective towards undesired object or background. Selective Spatio-Temporal...
Efficient online algorithms are developed to perform dictionary learning (DL) for the features lifted to a high-dimensional space via nonlinear mapping. Inspired by recent works on batch kernelized DL with promising performance for real-world learning tasks, two kernel DL formulations are put forth, amenable to online processing. The first formulation aims at faithfully representing the high-dimensional...
Tunstall proposed an efficient algorithm for constructing the optimal dictionary of any particular size to obtain a variable-to-fixed code. More accurately, the algorithm constructs the optimal uniquely parsable dictionary. In fact, Savari showed that, if one allows herself to consider plurally parsable dictionaries, better codes may be constructed. Savari found a class of plurally parsable dictionaries...
Approximately 70% of the source code of a software system consists of identifiers. Hence, the names chosen as identifiers are of paramount importance for the readability of computer programs and therewith their comprehensibility. However, virtually every programming language allows programmers to use almost arbitrary sequences of characters as identifiers which far too often results in more or less...
Information technology is growing very rapidly, in particular for data handling. Data is a valuable asset for everyone, especially for larger companies with branches in several places. Data transmission from headquarters to branch offices make the company must provide good tools to do it. These companies also need tools that can be used to compress data to reduce their size. The main idea of the word-based...
Image Super-resolution (SR) reconstruction techniques based on sparse representation have attracted ever-increasing attentions in recent years, where the choice of over-complete dictionary is of prime important for reconstruction quality. However, most of the image SR methods based on sparse representation fail to consider the discrimination and the redundance of the dictionaries, which lead to obvious...
In this paper, we propose a cascade dictionary learning algorithm for action recognition. In the first stage, a dictionary for basic sparse coding is learned based on local descriptors. And then spatial pyramid features are extracted to represent all the images in the same dimensions. Instead of performing dimension reduction, all the features are regrouped and then fed into second dictionary learning...
Dictionary learning has been applied to computer vision problems such as facial expression recognition. K-SVD is one of the state-of-the-art dictionary learning algorithms. However, K-SVD is unsupervised and focuses only on the representational power. In this paper, we adopt label-consistent K-SVD with scattering transform in facial expression recognition. In addition to reducing the reconstruction...
This paper presents a novel algorithm for learning a hierarchical dictionary in the short-time Fourier (STFT) domain, which can improve the performance of dictionary learning (DL) based single-channel speech separation (SCSS). The goal of SCSS is to separate the underlying clean speeches from a signal mixture, which was often achieved by learning a pair of discriminative sub-dictionaries and sparsely...
This paper addresses the patch size issue in sparse representation over learned dictionaries. A strategy for selecting the best patch size is proposed. It is empirically shown that the representation quality of natural image patches depends on the patch size considered. The proposed strategy selectively chooses the most appropriate patch size based on the resulting sparse representation error. The...
Natural Language Processing (NLP) is one of the most important research areas carried out in the world of Human language. For every language, spell checker is an essential component of many of the common Desktop applications, Machine Translation system and Office Automation system. In Myanmar, Myanmar Language is used as an official language. Myanmar Pronunciation and orthography has differences because...
This paper introduces a novel video presentation term spatial-temporal pyramid sparse coding (STPSC) which characterizes both the spatial and temporal aspects of the video. Specifically, the co-occurrences of visual words are computed with respect to the spatial layout and the sequencing of the features in the video. The representation captures both the spatial arrangement and the temporal relationship...
The image patches learned by recent works are usually only bar-like or Gabor-like patterns. However those simple patterns are not meaningful enough to capture higher level information. In this study, we try to learn more complex image patterns from unaligned images. We propose Scale And Shift Invariant Sparse Coding (SASISC), which aligns basis patches at proper locations and scales to reconstruct...
Intelligent Dictionary Based Encoding (IDBE)[18], an encoding strategy offers higher compression ratios and rate of compression. Transforming text into some intermediate form by using IDBE is the basic philosophy of this compression technique. It is observed that a better compression is achieved by using IDBE as the preprocessing stage for the BWT based compressor. This paper aims at developing such...
Data compression algorithms are used to reduce the redundancy and storage requirement for data. Data compression is also an efficient approach to reduce communication costs by using available bandwidth effectively. Over the last decade we have seen an unprecedented explosion in the amount of digital data transmitted via the Internet in the form of text, images, video, sound, computer programs, etc...
The Lempel-Ziv 77 (LZ77) and LZ-Storer-Szymanski (LZSS) text compression algorithms use a sliding window over the sequence of symbols, with two sub-windows: the dictionary (symbols already encoded) and the look-ahead-buffer (LAB) (symbols not yet encoded). Binary search trees and suffix trees (ST) have been used to speedup the search of the LAB over the dictionary, at the expense of high memory usage...
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.