The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2005.227 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
BidCorpus: A multifaceted learning dataset for public procurement.
Data Brief
February 2025
Federal University of Maranhão. Av. dos Portugueses, 1966 São Luís, Maranhão, Brazil.
Digital transformation has significantly impacted public procurement, improving operational efficiency, transparency, and competition. This transformation has allowed the automation of data analysis and oversight in public administration. Public procurement involves various stages and generates a multitude of documents.
View Article and Find Full Text PDFExploratory multivariate analysis using R Language for method development in liquid chromatography.
Anal Bioanal Chem
January 2025
Department of Medical Biochemistry, Faculty of Medicine in Hradec Králové, Charles University, Šimkova 870, 500 03, Hradec Králové, Czech Republic.
The visual evaluation of data derived from screening and optimization experiments in the development of new analytical methods poses a considerable time investment and introduces the risk of subjectivity. This study presents a novel approach to processing such data, based on factor analysis of mixed data and hierarchical clustering - multivariate techniques implemented in the R programming language. The methodology is demonstrated in the early-stage screening and optimization of the chromatographic separation of 15 structurally diverse drugs that affect the central nervous system, using a custom R Language script.
View Article and Find Full Text PDFStatistical learning of spatiotemporal target regularities in the absence of saliency.
Atten Percept Psychophys
January 2025
Department of Experimental and Applied Psychology, Vrije Universiteit Amsterdam, Van Der Boechorststraat 7, 1081 BT, Amsterdam, The Netherlands.
In previous studies, it was established that individuals can implicitly learn spatiotemporal regularities related to how the distribution of target locations unfolds across the time course of a single trial. However, these regularities were tied to the appearance of salient targets that are known to capture attention in a bottom-up way. The current study investigated whether the saliency of target is necessary for this type of learning to occur.
View Article and Find Full Text PDFBackground: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal age-related cognitive decline and more severe degenerative conditions such as Alzheimer's disease. Understanding the differences between Early-MCI (EMCI) and Late-MCI (LMCI) is crucial to facilitate early diagnosis and future clinical interventions. This study employed free-water diffusion tensor imaging (FW-DTI) to explore the differences in white matter alterations between EMCI and LMCI.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Berenson-Allen Center for Noninvasive Brain Stimulation, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA.
Background: Alzheimer's disease (AD) is associated with cerebral slowing on electroencephalography (EEG), or a shift in oscillatory power from higher to lower frequencies. This change can be captured as the spectral power ratio (SPR) of alpha and beta over delta and theta: (α+β)/(δ+θ). Prior studies have shown that compared to cognitively unimpaired older adults, the SPR was lower in persons with a clinical diagnosis of dementia due to probable AD and those with a biomarker-confirmed diagnosis of amnestic mild cognitive impairment (aMCI) due to AD, and a lower SPR was associated with worse executive functions scores.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!