ClusTi: Clustering Method for Table Structure Recognition in Scanned Images

2021 ◽  
Author(s):  
Arthur Zucker ◽  
Younes Belkada ◽  
Hanh Vu ◽  
Van Nam Nguyen
Keyword(s):  
Clustering Method ◽  
Structure Recognition ◽  
Scanned Images

Cracking at the fold in double layer coated paper: the influence of latex and starch composition

TAPPI Journal ◽  
2019 ◽  
Vol 18 (2) ◽  
pp. 93-99
Author(s):  
SEYYED MOHAMMAD HASHEMI NAJAFI ◽  
DOUGLAS BOUSFIELD, ◽  
MEHDI TAJVIDI
Keyword(s):  
Mechanical Properties ◽  
Double Layer ◽  
Starch Content ◽  
Single Layer ◽  
Double Layers ◽  
Coated Paper ◽  
Coated Papers ◽  
Coating Layers ◽  
Scanned Images ◽  
Packaging Paper

Cracking at the fold of publication and packaging paper grades is a serious problem that can lead to rejection of product. Recent work has revealed some basic mechanisms and the influence of various parameters on the extent of crack area, but no studies are reported using coating layers with known mechanical properties, especially for double-coated systems. In this study, coating layers with different and known mechanical properties were used to characterize crack formation during folding. The coating formulations were applied on two different basis weight papers, and the coated papers were folded. The binder systems in these formulations were different combinations of a styrene-butadiene latex and mixtures of latex and starch for two different pigment volume concentrations (PVC). Both types of papers were coated with single and double layers. The folded area was scanned with a high-resolution scanner while the samples were kept at their folded angle. The scanned images were analyzed within a constant area. The crack areas were reported for different types of papers, binder system and PVC values. As PVC, starch content, and paper basis weight increased, the crack area increased. Double layer coated papers with high PVC and high starch content at the top layer had more cracks in comparison with a single layer coated paper, but when the PVC of the top layer was low, cracking area decreased. No measurable cracking was observed when the top layer was formulated with a 100% latex layer.

Цифровая морфометрия разнокачественности семян овощных культур

2018 ◽  
Author(s):  
F.B. Musaev ◽  
N.S. Priyatkin ◽  
M.V. Arkhipov ◽  
P.A. Shchukina ◽  
A.F. Bukharov ◽  
...  
Keyword(s):  
Seed Quality ◽  
Image Analysis System ◽  
Flatbed Scanner ◽  
The Future ◽  
Scanned Images ◽  
Computer Morphometry ◽  
Analysis System ◽  
Matrix Heterogeneity ◽  
Relationship Of ◽  
Selection Of

Приведено описание разработанной авторами методики цифровой компьютерной морфометрии семян овощных культур на основе системы анализа изображений, состоящей из планшетного сканера и программного обеспечения для автоматических измерений. В основу метода положено представление о разнокачественности семян, обусловленной генетической неоднородностью самих семенных растений, используемых в промышленном семеноводстве. Физические свойства семян (их форма и линейные размеры) – основные параметры при определении их качества. Цифровые изображения семян получены при помощи планшетного сканера HP Sсanjet 200 на базе Агрофизического НИИ с использованием серийного программного обеспечения «Argus-BIO», производства ООО «АргусСофт» (г. Санкт-Петербург). Метод состоит из подбора контрастной подложки (фона) для сканирования семян с минимальными теневыми эффектами, калибровку программного обеспечения для привязки к истинным размерным величинам, подбор параметров измерений и автоматическое распознавание цифровых сканированных изображений семян. Представлены экспериментальные данные по морфометрии экологически разнокачественных семян фасоли овощной, матрикально разнокачественных семян укропа, пастернака и лука Кристофа. Семена укропа и пастернака, собранные из разных порядков ветвления семенного растения, значительно различались по величине линейных параметров. Наиболее показательный линейный параметр семян – площадь проекции. Предложенная авторами методика цифровой морфометрии, уже использована на практике и в перспективе может быть задействована в исследованиях экологической и матрикальной разнокачественности семян овощных культур. Так, она прошла апробацию на разнокачественных семенах пяти сортов фасоли овощной (Настена, Магура, Миробела, Морена, Бажена) полученных в пяти контрастных эколого-географических условиях среды (Москва, Белгород, Ставрополь, Омск, Горки) в 2011–2012 годах. В дальнейшем методика может быть использована для улучшения качества цифровых изображений семян, изучения разнокачественности семян в том числе и для совершенствования контроля за селекционным процессом. Кроме того, она применима для изучения взаимосвязи совокупности морфометрических характеристик семян и их посевных качеств.The description of the method of digital computer morphometry of vegetable seeds developed by the authors on the basis of the image analysis system consisting of a flatbed scanner and software for automatic measurements is given. The method is based on the idea of seed quality, due to the genetic heterogeneity of the seed plants used in industrial seed production. Physical properties of seeds (their shape and linear dimensions) are the main parameters in determining their quality. Digital image of the seed obtained using the flatbed scanner, HP Sсanjet 200 on the basis of the Agrophysical research Institute with serial software “Argus-BIO”, produced by LLC “Argussoft” (Saint-Petersburg). The method consists of selection of a contrast substrate (background) for scanning seeds with minimal shadow effects, calibration of software for binding to true size values, selection of measurement parameters and automatic recognition of digital scanned images of seeds. Experimental data on the morphometry of ecologically different-quality seeds of vegetable beans, matrix seeds of dill, Pasternak and Christoph onion are presented. Seeds of dill and parsnip, collected from different orders of branching of the seed plant, significantly differed in size of linear parameters. The most revealing linear parameter seed – area projection. The method of digital morphometry proposed by the authors has already been used in practice and in the future can be used in studies of ecological and matrix heterogeneity of vegetable seeds. So, it was tested on different quality seeds of five varieties of vegetable beans (Nastena, Magura, Mirobelа, Morena, Bazhenf) obtained in five contrasting environmental and geographical conditions (Moscow, Belgorod, Stavropol, Omsk, Gorki) in 2011-2012. In the future, the technique can be used to improve the quality of digital images of seeds, study of seed diversity, including to improve the control of the breeding process. In addition, it is applicable to study the relationship of the set of morphometric characteristics of seeds and their sowing qualities.

Teknik Data Mining Dalam Clustering Produksi Susu Segar Di Indonesia Dengan Algoritma K-Means

2019 ◽  
Vol 1 (1) ◽  
pp. 31-39
Author(s):  
Ilham Safitra Damanik ◽  
Sundari Retno Andani ◽  
Dedi Sehendro
Keyword(s):  
Data Mining ◽  
Milk Production ◽  
Clustering Algorithm ◽  
Clustering Method ◽  
Data Mining Techniques ◽  
Low Level ◽  
Fresh Milk ◽  
Nutritional Needs ◽  
High Level ◽  
Level Cluster

Milk is an important intake to meet nutritional needs. Both consumed by children, and adults. Indonesia has many producers of fresh milk, but it is not sufficient for national milk needs. Data mining is a science in the field of computers that is widely used in research. one of the data mining techniques is Clustering. Clustering is a method by grouping data. The Clustering method will be more optimal if you use a lot of data. Data to be used are provincial data in Indonesia from 2000 to 2017 obtained from the Central Statistics Agency. The results of this study are in Clusters based on 2 milk-producing groups, namely high-dairy producers and low-milk producing regions. From 27 data on fresh milk production in Indonesia, two high-level provinces can be obtained, namely: West Java and East Java. And 25 others were added in 7 provinces which did not follow the calculation of the K-Means Clustering Algorithm, including in the low level cluster.

Sign in / Sign up

Export Citation Format

Share Document