scholarly journals An Efficient Skewed Line Segmentation Technique for Cursive Script OCR

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Saud Malik ◽  
Ahthasham Sajid ◽  
Arshad Ahmad ◽  
Ahmad Almogren ◽  
Bashir Hayat ◽  
...  
Keyword(s):  
Recognition Accuracy ◽  
Segmentation Algorithm ◽  
Arabic Text ◽  
Cursive Script ◽  
Printed Text ◽  
Text Page ◽  
Baseline Detection ◽  
Line Segmentation ◽  
Language Text

Segmentation of cursive text remains the challenging phase in the recognition of text. In OCR systems, the recognition accuracy of text is directly dependent on the quality of segmentation. In cursive text OCR systems, the segmentation of handwritten Urdu language text is a complex task because of the context sensitivity and diagonality of the text. This paper presents a line segmentation algorithm for Urdu handwritten and printed text and subsequently to ligatures. In the proposed technique, the counting pixel approach is employed for modified header and baseline detection, in which the system first removes the skewness of the text page, and then the page is converted into lines and ligatures. The algorithm is evaluated on manually generated Urdu printed and handwritten dataset. The proposed algorithm is tested separately on handwritten and printed text, showing 96.7% and 98.3% line accuracy, respectively. Furthermore, the proposed line segmentation algorithm correctly extracts the lines when tested on Arabic text.

A Robust Line Segmentation Algorithm for Arabic Printed Text with Diacritics

2017 ◽  
Vol 2017 (13) ◽  
pp. 42-47 ◽  
Author(s):  
Muna Ayesh ◽  
Khader Mohammad ◽  
Aziz Qaroush ◽  
Sos Agaian ◽  
Mahdi Washha
Keyword(s):  
Segmentation Algorithm ◽  
Printed Text ◽  
Line Segmentation

scholarly journals Setting Standards to Promote Artificial Intelligence in Colon Mass Endoscopic Sampling

2019 ◽  
Author(s):  
Yueping Zheng ◽  
Ruizhang Su ◽  
Wangyue Wang ◽  
Sijun Meng ◽  
Hang Xiao ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Light Source ◽  
Recognition Accuracy ◽  
Poor Quality ◽  
Digestive Endoscopy ◽  
Treatment Efficiency ◽  
Picture Processing ◽  
Medical Institutions ◽  
Multiple Regions

ABSTRACTObjectiveArtificial intelligence (AI) has undeniable values in detection, characterization, and monitoring of tumors during cancer imaging. However, major AI explorations in digestive endoscopy have not been systematically planned, and more important, most AI productions are based on Single-center Studies (ScSs). ScSs result in data scarcity, redundancy as well as island effects, which leads to some limitations in applying it on endoscopy. We investigate the disadvantages of picture processing which may effect the AI detection, and make improvements in AI detection and image recognition accuracy.DesignCurrent investigation aggregates a total of 2,500 gastroenteroscopy samples from various hospitals in multiple regions and carries out deep learning.ResultsIt is found that factors inconducive to AI recognition are common such as: (a) the gastrointestinal tract is not cleaned up completely; (b) shooting angle (from left to right and the top of polyp are unexposed clearly), shooting distance (too close or too far to shoot causes the lump to be unclear), shooting light (insufficient light source or overexposed light source in mass) and unstable shooting lead to poor quality of pictures.ConclusionWe set standards for a multicenter cooperation involving three-level medical institutions from the provincial, municipal and county to improve the recognition accuracy as well as the diagnosis and treatment efficiency meanwhile.

scholarly journals Experimental studies of the quality of embossed characters of the Braille alphabet

2016 ◽  
Vol 64 (3) ◽  
pp. 607-614
Author(s):  
R. Barczyk ◽  
D. Jasińska-Choromańska
Keyword(s):  
Surface Roughness ◽  
Statistical Analysis ◽  
3D Printing ◽  
Rapid Prototyping ◽  
Experimental Studies ◽  
Printed Text ◽  
Blind Persons ◽  
Blind Individuals

Abstract The paper presents studies pertaining to the quality of embossed characters of the Braille alphabet used, among other applications, for tagging drug labels. The following parameters of embossed inscriptions were measured: height, diameter of the dots and surface roughness (18 samples with various combinations of their values). 48 blind individuals assessed the quality of the printed text. Statistical analysis proved that a text with dots having height of 0.9 millimeter, diameter of 1.6 millimeters and roughness Ra of about 1 micrometer to be the best. The samples had been made using two different methods of rapid prototyping: PolyJet and SLS. 3D printing is increasingly popular and the studies proved the usefulness of these methods for labeling with embossed inscriptions, due to the repeatability, durability and quality they ensure. The assessing group of blind individuals was comprised of 24 persons 14–17 years old and other 24 persons aged over 60 who were not proficient in reading Braille alphabet, This allows to conclude that a text featuring the above values of the parameters will be easy to read for the majority of blind persons.

Unraveling the Taste Fabric of Social Networks

2009 ◽  
pp. 1521-1546
Author(s):  
Hugo Liu ◽  
Pattie Maes ◽  
Glorianna Davenport
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Online Social Networks ◽  
Social Connectedness ◽  
Natural Language Text ◽  
Cross Domain ◽  
Semantic Mining ◽  
The Rich ◽  
Language Text

Popular online social networks such as Friendster and MySpace do more than simply reveal the superficial structure of social connectedness—the rich meanings bottled within social network profiles themselves imply deeper patterns of culture and taste. If these latent semantic fabrics of taste could be harvested formally, the resultant resource would afford completely novel ways for representing and reasoning about web users and people in general. This paper narrates the theory and technique of such a feat—the natural language text of 100,000 social network profiles were captured, mapped into a diverse ontology of music, books, films, foods, etc., and machine learning was applied to infer a semantic fabric of taste. Taste fabrics bring us closer to improvisational manipulations of meaning, and afford us at least three semantic functions—the creation of semantically flexible user representations, cross-domain taste-based recommendation, and the computation of taste-similarity between people— whose use cases are demonstrated within the context of three applications—the InterestMap, Ambient Semantics, and IdentityMirror. Finally, we evaluate the quality of the taste fabrics, and distill from this research reusable methodologies and techniques of consequence to the semantic mining and Semantic Web communities.

scholarly journals Optical Flow Filtering-Based Micro-Expression Recognition Method

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2056
Author(s):  
Junjie Wu ◽  
Jianfeng Xu ◽  
Deyu Lin ◽  
Min Tu
Keyword(s):  
Optical Flow ◽  
Recognition Accuracy ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Expression Recognition ◽  
Recognition Method ◽  
Video Clips ◽  
Low Degree ◽  
Micro Expression

The recognition accuracy of micro-expressions in the field of facial expressions is still understudied, as current research methods mainly focus on feature extraction and classification. Based on optical flow and decision thinking theory, we propose a novel micro-expression recognition method, which can filter low-quality micro-expression video clips. Determined by preset thresholds, we develop two optical flow filtering mechanisms: one based on two-branch decisions (OFF2BD) and the other based on three-way decisions (OFF3WD). In OFF2BD, which use the classical binary logic to classify images, and divide the images into positive or negative domain for further filtering. Differ from the OFF2BD, OFF3WD added boundary domain to delay to judge the motion quality of the images. In this way, the video clips with low degree of morphological change can be eliminated, so as to directly improve the quality of micro-expression features and recognition rate. From the experimental results, we verify the recognition accuracy of 61.57%, and 65.41% for CASMEII, and SMIC datasets, respectively. Through the comparative analysis, it shows that the scheme can effectively improve the recognition performance.

A NEW STRUCTURAL TECHNIQUE FOR RECOGNIZING PRINTED ARABIC TEXT

1995 ◽  
Vol 09 (01) ◽  
pp. 101-125 ◽  
Author(s):  
HUMOUD B. AL-SADOUN ◽  
ADNAN AMIN
Keyword(s):  
Binary Tree ◽  
Average Length ◽  
Recognition Rate ◽  
Text Recognition ◽  
Arabic Text ◽  
Tree Construction ◽  
Printed Text

This paper proposes a new structural technique for Arabic text recognition. The technique can be divided into five major steps: (1) preprocessing and binarization; (2) thinning; (3) binary tree construction; (4) segmentation; and (5) recognition. The advantage of this technique is that its execution does not depend on either the font or size of character. Thus, this same technique might be utilized for the recognition of machine or hand printed text. The relevant algorithm is implemented on a microcomputer. Experiments were conducted to verify the accuracy and the speed of this algorithm using about 20,000 subwords each with an average length of 3 characters. The subwords used were written using different fonts. The recognition rate obtained in the experiments indicated an accuracy of 93.38 % with a speed of 2.7 characters per second.

ON LINE SEGMENTATION ALGORITHM FOR ICU CONTINUOUSLY MONITORED CLINICAL DATA

2002 ◽  
Vol 35 (1) ◽  
pp. 139-144 ◽  
Author(s):  
S. Charbonnier ◽  
G. Becq ◽  
L. Biot ◽  
P.Y. Carry ◽  
J.P. Perdrix
Keyword(s):  
Clinical Data ◽  
Segmentation Algorithm ◽  
On Line ◽  
Line Segmentation

scholarly journals PENGGUNAAN HADIS-HADIS PADA SKRIPSI MAHASISWA IAIN PONTIANAK

Al-Hikmah ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 113
Author(s):  
Wajidi Sayadi
Keyword(s):  
Teacher Training ◽  
Research Methods ◽  
Islamic Education ◽  
Arabic Text ◽  
Academic Year ◽  
Student Thesis ◽  
Year 2013

This research was conducted to find out how the writing and quality of the Hadith of the Prophet Muhammad in the thesis of students of the Department of Islamic Education, Tarbiyah Faculty and Teacher Training of IAIN Pontianak, in academic year 2013/2014. The research methods used includes; First, do takhrij al-hadith; Second, do I’tibar al-hadith; Third, examine the narrators' personalities and methods of transmission by using, among others, the knowledge of al-jarh wa at-ta'dil. Fourth, conclude the results of the study. There are 100 theses studied, only 25 theses (25%) have hadiths in them, and 75 theses (75%) that do not include hadiths. There are two types of hadith writing in student thesis: First, hadith are written in Arabic text and their translations. Second, only the translation of the hadith was written. In writing the hadith of the Arabic text there are several errors. There is even a hadith text that is different from the translation. This happens, because most of the thesis is about improving the reading of the Qur'an in a particular school. The quality of the hadiths in student theses is 66 Sahih hadiths, 7 Hasan hadiths, 8 Daif Hadiths, 2 very daithic hadiths, 1 false hadith, 1 mauquf hadith, and 1 not known quality of hadith. Students' understanding of the hadith writing and the quality of the hadith is still lacking. Thesis supervisors and examiners are negligent in seeing the traditions of the hadith used by students. [Penelitian ini dilakukan untuk mengetahui bagaimana penulisan dan kualitas hadis-hadis Nabi Muhammad SAW dalam skripsi mahasiswa Jurusan Pendidikan Agama Islam Fakultas Tarbiyah dan Ilmu Keguruan IAIN Pontianak tahun akademik 2013/2014. Adapun metode penelitian yang digunakan antara lain; Pertama, melakukan takhrij al-hadits; Kedua, melakukan I’tibar al-hadits; Ketiga, meneliti pribadi para periwayat dan metode periwayatannya dengan menggunakan antara lain ilmu al-jarh wa at-ta’dil. Keempat, menyimpulkan hasil penelitian. Ada 100 skripsi yang diteliti, hanya 25 skripsi (25 %) yang ada hadis di dalamnya, dan 75 skripsi (75 %) yang tidak mencantumkan hadis. Ada dua macam cara penulisan hadis dalam skripsi mahasiswa: Pertama, hadis ditulis dalam teks Arab dan terjemahannya. Kedua, hanya terjemahan hadisnya yang ditulis. Dalam penulisan hadis teks Arabnya terdapat beberapa kekeliruan. Bahkan ada yang teks hadisnya berbeda dengan terjemahannya. Hal ini terjadi, karena kebanyakan skripsi mengenai upaya peningkatan membaca al-Qur’an di suatu sekolah tertentu. Adapun kualitas hadis-hadis dalam skripsi mahasiswa, adalah 66 hadis Sahih, 7 hadis Hasan, 8 hadis Daif, 2 hadis sangat daif, 1 hadis palsu, 1 hadis mauquf, dan 1 hadis yang belum diketahui kualitasnya. Pemahaman mahasiswa dalam hal penulisan hadis dan kualitas hadis masih sangat kurang. Para pembimbing dan penguji skripsi lalai dalam melihat keshahihan hadis yang digunakan oleh mahasiswa]. Kata Kunci: Hadis, Skripsi, Mahasiswa, Sahih, Da’if, dan Palsu.

scholarly journals Application of Convolutional Neural Network Method in Brain Computer Interface

2021 ◽  
Vol 2078 (1) ◽  
pp. 012044
Author(s):  
Lingzhi Chen ◽  
Wei Deng ◽  
Chunjin Ji
Keyword(s):  
Pattern Recognition ◽  
Recognition Accuracy ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Eeg Signals ◽  
Network Method ◽  
Electroencephalogram Eeg ◽  
The Brain ◽  
Bci System

Abstract Pattern Recognition is the most important part of the brain computer interface (BCI) system. More and more profound learning methods were applied in BCI to increase the overall quality of pattern recognition accuracy, especially in the BCI based on Electroencephalogram (EEG) signal. Convolutional Neural Networks (CNN) holds great promises, which has been extensively employed for feature classification in BCI. This paper will review the application of the CNN method in BCI based on various EEG signals.

Sign in / Sign up

Export Citation Format

Share Document