DOCUMENT SKEW DETECTION — A NOVEL APPROACH

2008 ◽  
Vol 08 (01) ◽  
pp. 47-59
Author(s):  
A. V. N. MANJUNATH ◽  
K. G. HEMANTHA ◽  
S. NOUSHATH
Keyword(s):  
Standard Deviation ◽  
Second Order ◽  
Experimental Results ◽  
Text Line ◽  
Estimation Technique ◽  
Document Images ◽  
Indian Languages ◽  
Skew Detection ◽  
South Indian ◽  
Novel Approach

In this paper, we propose a novel skew estimation technique for binary document images based on Boundary Growing Method (BGM), thinning and moments. BGM helps in extracting the text line blocks from the document. Thinning1 is performed to fit the best line for extracted text line blocks. Further, skew is computed for thinned line using second order moments. Several experiments have been conducted on various types of documents such as documents containing south Indian languages, English documents, journals, text with picture, noisy images, and document with different fonts and resolutions, to reveal the robustness of the proposed method. Based on the experimental results we have realized that the proposed method outperforms existing methods both in terms of mean and standard deviation.

scholarly journals A Digital Improvement—Trimming a Digital Temperature Sensor with EEPROM Reprogrammable Fuses

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1700
Author(s):  
Anca Mihaela Vasile (Dragan) ◽  
Alina Negut ◽  
Adrian Tache ◽  
Gheorghe Brezeanu
Keyword(s):  
Standard Deviation ◽  
Power Supply ◽  
Temperature Sensor ◽  
Experimental Results ◽  
Temperature Error ◽  
Thermal Sensor ◽  
Memory Cells ◽  
Temperature Range ◽  
Read Only Memory ◽  
Digital Temperature Sensor

An EEPROM (electrically erasable programmable read-only memory) reprogrammable fuse for trimming a digital temperature sensor is designed in a 0.18-µm CMOS EEPROM. The fuse uses EEPROM memory cells, which allow multiple programming cycles by modifying the stored data on the digital trim codes applied to the thermal sensor. By reprogramming the fuse, the temperature sensor can be adjusted with an increased trim variation in order to achieve higher accuracy. Experimental results for the trimmed digital sensor showed a +1.5/−1.0 ℃ inaccuracy in the temperature range of −20 to 125 ℃ for 25 trimmed DTS samples at 1.8 V by one-point calibration. Furthermore, an average mean of 0.40 ℃ and a standard deviation of 0.70 ℃ temperature error were obtained in the same temperature range for power supply voltages from 1.7 to 1.9 V. Thus, the digital sensor exhibits similar performances for the entire power supply range of 1.7 to 3.6 V.

Mining discriminative patches for script identification in natural scene images

2021 ◽  
Vol 40 (1) ◽  
pp. 551-563
Author(s):  
Liqiong Lu ◽  
Dong Wu ◽  
Ziwei Tang ◽  
Yaohua Yi ◽  
Faliang Huang
Keyword(s):  
Neural Networks ◽  
Experimental Results ◽  
The Other ◽  
Natural Scene ◽  
Fixed Size ◽  
Script Identification ◽  
Aspect Ratios ◽  
Novel Approach ◽  
Public Datasets ◽  
Natural Scene Images

This paper focuses on script identification in natural scene images. Traditional CNNs (Convolution Neural Networks) cannot solve this problem perfectly for two reasons: one is the arbitrary aspect ratios of scene images which bring much difficulty to traditional CNNs with a fixed size image as the input. And the other is that some scripts with minor differences are easily confused because they share a subset of characters with the same shapes. We propose a novel approach combing Score CNN, Attention CNN and patches. Attention CNN is utilized to determine whether a patch is a discriminative patch and calculate the contribution weight of the discriminative patch to script identification of the whole image. Score CNN uses a discriminative patch as input and predict the score of each script type. Firstly patches with the same size are extracted from the scene images. Secondly these patches are used as inputs to Score CNN and Attention CNN to train two patch-level classifiers. Finally, the results of multiple discriminative patches extracted from the same image via the above two classifiers are fused to obtain the script type of this image. Using patches with the same size as inputs to CNN can avoid the problems caused by arbitrary aspect ratios of scene images. The trained classifiers can mine discriminative patches to accurately identify some confusing scripts. The experimental results show the good performance of our approach on four public datasets.

Preparation and Aplication of Cation Adsorbent by Canada Goldenrod (Solidago canadensis L.)

2011 ◽  
Vol 396-398 ◽  
pp. 75-87
Author(s):  
Zai Fu Yang ◽  
Xiao Jing Yang ◽  
Li Hong Sun ◽  
Lian Lian Xu
Keyword(s):  
Sulfuric Acid ◽  
Cation Exchange ◽  
Agricultural Land ◽  
Reaction Medium ◽  
Volume Ratio ◽  
Second Order ◽  
Experimental Results ◽  
Solidago Canadensis ◽  
Order Kinetic ◽  
Pseudo Second Order

ABSTRACT: Cation adsorbent was prepared from the Solidago Canadensis（which are abandoned agricultural land of alien invasive plants）by Sulfuric acid esterification modified , isoamyl alcohol as reaction medium. Design L934 orthogonal experiment, the Solidago canadensis cation exchange adsorbent, the optimal preparation conditions. Experimental results show that at 15°C, concentrated sulfuric acid and amyl alcohol volume ratio of 5:6 obtained under conditions of Solidago canadensis cation exchange adsorbent for Pb(II) exchange best. The experimental results of Pb(II) adsorption onto the Solidago Canadensis based cation adsorbent showed that the best conditions are: the initial pH 5, the concentration of Pb(II) 300mg/L，the dosage of cation adsorbent 1.2mg/L and adsorption time 3h. The adsorption data were analyzed by using pseudo-first-order and pseudo-second-order kinetic models were found to follow the pseudo-second-order kinetic model.

scholarly journals An image dehazing algorithm based on double priors constraint

2018 ◽  
Vol 189 ◽  
pp. 04009
Author(s):  
Kun Liu ◽  
Shiping Wang ◽  
Linyuan He ◽  
Duyan Bi ◽  
Shan Gao
Keyword(s):  
Standard Deviation ◽  
Mean Value ◽  
Experimental Results ◽  
Dark Channel Prior ◽  
Image Dehazing ◽  
Color Distortion ◽  
Local Media ◽  
Dark Channel

Aiming at the color distortion of the restored image in the sky region, we propose an image dehazing algorithm based on double priors constraint. Firstly, we divided the haze image into sky and non-sky regions. Then the Color-lines prior and dark channel prior are used for estimating the transmission of sky and non-sky regions respectively. After introducing color-lines prior to correct sky regions restored by the dark channel prior, we get an accurate transmission. Finally, the local media mean value and standard deviation are used to refine the transmission to obtain the dehazing image. Experimental results show that the algorithm has obvious advantages in the recovery of the sky area.

Revealing the nanodomain structure of silicon oxycarbide via preferential etching and pore analysis

2016 ◽  
Vol 09 (03) ◽  
pp. 1650043 ◽  
Author(s):  
Haolin Wu ◽  
Jie Yang ◽  
Haibiao Chen ◽  
Feng Pan
Keyword(s):  
Porous Structure ◽  
Gas Adsorption ◽  
Inverse Image ◽  
Silicon Oxycarbide ◽  
Experimental Results ◽  
Porous Network ◽  
Pore Analysis ◽  
Novel Approach ◽  
Nanodomain Structure ◽  
Nanocomposite Structures

Preferentially etching either carbon or silica from silicon oxycarbide (SiOC) created a porous network as an inverse image of the removed phase. The porous structure was analyzed by gas adsorption, and the experimental results verified the nanodomain structure of SiOC. This work demonstrated a novel approach for analyzing materials containing nanocomposite structures.

A Percolation Equation for Modeling Experimental Results for Continuum Percolation Systems

2001 ◽  
Vol 699 ◽  
Author(s):  
D.S. McLachlan ◽  
C. Chiteme ◽  
W.D. Heiss ◽  
Junjie Wu
Keyword(s):  
Experimental Data ◽  
Ac Conductivity ◽  
Volume Fraction ◽  
Power Laws ◽  
Second Order ◽  
Experimental Results ◽  
Analytical Equation ◽  
Scaling Properties ◽  
First Order ◽  
Dc And Ac Conductivity

AbstractThe standard percolation equations or power laws, for dc and ac conductivity (dielectric constant) are based on scaling ansatz, and predict the behaviour of the first and second order terms, above and below the percolation or critical volume fraction (øc), and in the crossoverregion. Recent experimental results on ac conductivity are presented, which show that these equations, with the exception of real σm above øc and the first order terms in the crossover region, are only valid in the limit σi/σc = 0, where for an ideal dielectric σi=ωε0εr.A single analytical equation, which has the same parameters as the standard percolation equations, and which, for ac conductivity, reduces to the standard percolation power laws in the limit σi(ωε0εr)/σc = 0 for all but one case, is presented. The exception is the expression for real σm below øc, where the standard power law is always incorrect. The equation is then shown to quantitatively fit both first and second order dc and ac experimental data over the entire frequency and composition range. This phenomenological equation is also continuous, has the scaling properties required at a second order metal-insulator and fits scaled first order dc and ac experimental data. Unfortunately, the s and t exponents that are necessary to fit the data to the above analytical equation are usually not the simple dimensionally determined universal ones and depend on a number of factors.

Sign in / Sign up

Export Citation Format

Share Document