oalib
Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
最大稳定极值区域与笔画宽度变换的 自然场景文本提取方法
A Natural Scene Text Extraction Method Based on the Maximum Stable Extremal Region and Stroke Width Transform
 [PDF]

张国和,黄凯,张斌,符欢欢,赵季中
- , 2017, DOI: 10.7652/xjtuxb201701021
Abstract: 针对从背景复杂、视角多变、语言形式多样的场景图像中难以准确提取文本信息的问题,提出了一种基于最大稳定极值区域(MSER)和笔画宽度变换(SWT)场景文本提取方法。该方法结合MSER、SWT算法的优点,采用MSER算法的准确检测文字区域,建立文本候选区域,利用SWT算法计算文本候选区域笔画宽度得到候选文本区域的笔画宽度;根据笔画宽度图,利用连通域标记建立笔画宽度连通图,然后根据笔画宽度连通图,建立笔画连通图的启发性规则,删除非文本候选区域,并根据文本的几何特征分析及局部自适应窗口最大类间方差(Otsu)分割,有效提取出自然场景图像中的文本,文本提取的准确率、召回率及综合性能分别为0.74、0.64及0.68。仿真实验结果表明,在文本视角多变,字符大小、尺寸、字体各异的复杂条件下,所提方法具有较好的鲁棒性,适用于多语言和多字体混合的场景文本提取。
To extract text information effectively from natural scene image with complex background, multi??orientation perspective and multilingual languages, a scenario text extraction method based on maximum stable extremal region (MSER) and stroke width transform (SWT) is presented. The method combines the merits of MSER and SWT algorithms. It establishes text candidate regions by utilizing MSER algorithm to detect text regions, and SWT algorithm is used to calculate the text stroke width of candidate region to get its stroke width. According to the stroke width graph, the stroke??connected graph is established by using connected component labeling. Then the heuristic rules of stroke??connected graph are established to remove non??text candidate regions according to the stroke??connected graph. By using the geometrical feature analysis and the local adaptive window Otsu segmentation, the text in natural scene images can be extracted effectively. The text extraction accuracy, recall rate and comprehensive performance of this method are 0.74, 0.64 and 0.68, respectively. Simulation experiment shows that the method can achieve good robustness for complex background with multi??orientation perspective, various characters and font sizes, and it is suitable for variety of languages and fonts
Detecting multiword phrases in mathematical text corpora  [PDF]
Winfried G?dert
Computer Science , 2012,
Abstract: We present an approach for detecting multiword phrases in mathematical text corpora. The method used is based on characteristic features of mathematical terminology. It makes use of a software tool named Lingo which allows to identify words by means of previously defined dictionaries for specific word classes as adjectives, personal names or nouns. The detection of multiword groups is done algorithmically. Possible advantages of the method for indexing and information retrieval and conclusions for applying dictionary-based methods of automatic indexing instead of stemming procedures are discussed.
Spatial Semantic Scan: Detecting Subtle, Spatially Localized Events in Text Streams  [PDF]
Abhinav Maurya
Computer Science , 2015,
Abstract: Many methods have been proposed for detecting emerging events in text streams using topic modeling. However, these methods have shortcomings that make them unsuitable for rapid detection of locally emerging events on massive text streams. We describe Spatially Compact Semantic Scan (SCSS) that has been developed specifically to overcome the shortcomings of current methods in detecting new spatially compact events in text streams. SCSS employs alternating optimization between using semantic scan to estimate contrastive foreground topics in documents, and discovering spatial neighborhoods with high occurrence of documents containing the foreground topics. We evaluate our method on Emergency Department chief complaints dataset (ED dataset) to verify the effectiveness of our method in detecting real-world disease outbreaks from free-text ED chief complaint data.
Detecting and resolving spatial ambiguity in text using named entity extraction and self learning fuzzy logic techniques  [PDF]
Kanagavalli V R,Raja. K
Computer Science , 2013,
Abstract: Information extraction identifies useful and relevant text in a document and converts unstructured text into a form that can be loaded into a database table. Named entity extraction is a main task in the process of information extraction and is a classification problem in which words are assigned to one or more semantic classes or to a default non-entity class. A word which can belong to one or more classes and which has a level of uncertainty in it can be best handled by a self learning Fuzzy Logic Technique. This paper proposes a method for detecting the presence of spatial uncertainty in the text and dealing with spatial ambiguity using named entity extraction techniques coupled with self learning fuzzy logic techniques
New Algorithm for Text Segmentation Based on Stroke Filter
一种stroke滤波器文字分割算法

SHI Zhen-gang,GAO Li-qun,
石振刚
,高立群

计算机科学 , 2010,
Abstract: In order to solve segment text accurately and robustly from a complex background,this paper proposed a new algorithm for text segmentation in images by using a stroke filter.First,we described the stroke filter briefly based on local region analysis.Second,the determination of text color polarity and local region growing procedures were performed based on the response of the stroke filter.Finally,the feedback procedure by the recognition score from an optical character recognition (OCR) module was used to i...
Edge detection of rubbing text images based on wavelet transform
基于小波变换的拓片文字边缘检测*

YANG Shi-jun,HUANG Yong-dong,
杨世军
,黄永东

计算机应用研究 , 2010,
Abstract: The text images obtained through rubbing were featured by many fuzzy details, bad effect and so on, so it might lose more details in the traditional handling process.Proposed a new algorithm of the rubbing text image edge detection and enhancement based on dyadic wavelet transform. Firstly,transformed the rubbing text image using dyadic wavelet. Then combined with the property of cross-scale transmission for wavelet transform modulus value to extract enhance and refine the multi-scale edge. Experiments show this algorithm overcomes the shortcomings of traditional method and weakens the contradiction between the noise suppression and the accuracy of detecting edge details, so it has better practicality.
STROKE
MUHAMMAD AFTAB AKBAR
The Professional Medical Journal , 2008,
Abstract: Objective: (1) To finding the frequency of various electrocardiographic abnormalities in sufferers ofacute stroke (2) Comparing the ischemic and hemorrhagic stroke in this perspective. Study design: Observational.Place and duration of study: Emergency department of Nishtar Hospital, Multan from April 2003 to August 2005.Patients and methods: Two hundred patients of acute stroke who presented within 48 hours of the onset ofneurological symptoms, were included in the study, irrespective of the comorbid conditions like hypertension, diabetesmellitus, valvular heart disease, coronary artery disease and cardiomyopathy. Results: Majority of the patients hadischemic stroke. ECG changes due to variation in heart rate, rhythm ischemia, QTc prolongation and left ventricularhypertrophy were frequent findings in sufferes of acute stroke. Except atrial fibrillation and left ventricular hypertrophythese changes were more or less similar in two types of stroke. Conclusion: A variety of electrocardiographicabnormalities can be found in sufferers of acute stroke. Except atrial fibrillation and left ventricular hypertrophy, therefrequency is more or less similar whatever the type of stroke may be.
Stroke
H. Ghanaati,k. Firouznia
Iranian Journal of Radiology , 2008,
Abstract: Stroke is one of the leading causes of mortality & dis-ability in the word. A central concept in treating pa-tients with acute stroke is the existence of potentially salvageable tissue."nThe goal of imaging is to diagnose the precise type of stroke & so that appropriate management can be promptly implement. There was no efficacious treat-ment for acute cerebral ischemia. Therefore, the role of neuro imaging and radiologist was peripheral in the diagnosis & management of this disturbance."nThe demonstration of efficacy using thrombolysis has redefined this role, with the success of intervention becoming increasing dependent on timely imaging & accurate interpretation."nThe aim of this review is to discuss imaging methods in active stroke.
Print-Scan Resilient Text Image Watermarking Based on Stroke Direction Modulation for Chinese Document Authentication
L. Tan,X. Sun,G. Sun
Radioengineering , 2012,
Abstract: Print-scan resilient watermarking has emerged as an attractive way for document security. This paper proposes an stroke direction modulation technique for watermarking in Chinese text images. The watermark produced by the idea offers robustness to print-photocopy-scan, yet provides relatively high embedding capacity without losing the transparency. During the embedding phase, the angle of rotatable strokes are quantized to embed the bits. This requires several stages of preprocessing, including stroke generation, junction searching, rotatable stroke decision and character partition. Moreover, shuffling is applied to equalize the uneven embedding capacity. For the data detection, denoising and deskewing mechanisms are used to compensate for the distortions induced by hardcopy. Experimental results show that our technique attains high detection accuracy against distortions resulting from print-scan operations, good quality photocopies and benign attacks in accord with the future goal of soft authentication.
STROKE
ASAD ALI
The Professional Medical Journal , 2005,
Abstract: Stroke was defined according to WHO criteria as rapidly developingsymptoms and / or signs of focal and at times global loss of cerebral function with no apparent cause other than thatof vascular disease . Stroke is grossly divided into either 1). Thrombotic. 2). Embolic. 3).Hemorrhagic type (Which 1 2may be either intra cerebral bleed or subarachnoid hemorrhage). The brain, like other organs of the body, requires anadequate vascular system in order to supply it with nutrients and oxygen and to remove metabolic wastes and carbondioxide. Stabilization of medical problem with careful monitoring, and active prevention and timely management ofsecondary complications are of the utmost important for reducing stroke morality rates and avoiding further ischemicbrain injury. For the ischemic cerebral lesion itself, as yet no treatment or combination of treatment has beenestablished to be universally effective . However, current studies allow for the following 5 potential therapeutic areas 3to be identified.
Page 1 /100
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.