1
\documentclass[12pt,a4paper]{article}
\usepackage{longtable,lscape}
\usepackage{rotating}
\usepackage{multirow,multicol}
\begin{document}
\begin{landscape}
\begin{longtable}{llllll}
\caption{Monolingual Online/Offline Recognition Systems}
\label{Tab:2}       
%\hline\noalign{\smallskip}
\multicolumn{1}{l}{Author} &
   \multicolumn{1}{c}{Script} &
   \multicolumn{1}{c}{Text mode} &
   \multicolumn{1}{c}{classifier}  &
   \multicolumn{1}{c}{Dataset} &
   \multicolumn{1}{c}{Results} 
\\[0.5ex]\hline \hline \\[-2ex]
\endfirsthead
\multicolumn{6}{c}{{\tablename} \thetable{} -- Continued}\\[0.5ex]
  \hline \hline \\[-2ex]
\multicolumn{1}{c}{Author} &
   \multicolumn{1}{c}{Script} &
  \multicolumn{1}{c}{Text mode} &
 \multicolumn{1}{c}{classifier}  &
 \multicolumn{1}{c}{Dataset} &
 \multicolumn{1}{c}{Results}
   \\[0.5ex]\hline \hline \\[-2ex]
\endhead
Rabi et al (2017) & Cursive Arabic &    Offline Handwritten &   HMM & IFN/ENIT  &87.93\% \\ \\
Roy et al (2017) &  Arabic & Offline,Handwritten & Deep belief network with HMM &   IFN/ENIT &  89.46\% \\
Iwana et al(2017) & Latin & Online &    DTW &   UNIPEN digits data &    96.67\% \\
Sen et al (2017) &  Bangla  & Online &  & Handwritten   10,000 character dataset &  95.57\% \\
Bhattacharya et al(2016) &  Bangla& Online  & & 33453 word samples written by 31 writers &  94.3\% \\
Dash et al (2016) & Bangla &    Offline & Binary external symmetry axis constellation with Boolean matching &   ISI kolkata and IITBBS database for Odia numerals, ISI Kolkata bangle numeral and IITBBS odia character database &  99.35\%,98.9\%,99.48\% and 95.01\% respectively accuracy 0.02528 s, 0.02615 s, 0.02392 s, 0.03791s resptive time \\
Pengchao et al (2016) & Chinese & Printed,offline & CNN & 2789965 samples of GB2312-80 database & 99.90\% \\
Zhang et al(2016) & Chinese & Online & Deep CNN & CASIA-OLHWDB 1.0, CASIA-OLHwDB 1.1 &  98.44\% and 98.05\% \\
Sundram et al 2015 & Tamil & Online & Expert SVMs & 15000 handwritten isolated words & 93.0\% and 81.6\% at symbol and word level respectively. \\
Suyyagh et al (2015) &  Arabic & Offline Handwritten & FPGA & IFN/ENIT & 20 times faster than the software implementation and is less accurate by only 2.8\% \\

Arora et al (2014) & Gurumukhi & Offline Printed & SVM with linear and polynomial kernel & 7257 different images & 92.38\% for linear, 85.38\% for polynomial \\
Nguyen et al(2014) & English &  Online & SVM with semi incremental approach & IAM-OnDB &    65.70\% WRR\\
Bral et al(2014) &  Bangla &Online Handwritten & 5890 training set, 3534 test set & 91.6\% \\
A et al (2014) & Devanagari & Online & HMM with Nearest Neighbor classifier & 32,192 samples of 47 characters & 91.38\% \\
%\noalign{\smallskip}\hline\noalign{\smallskip}

%\noalign{\smallskip}\hline\
%\end{tabularx}
\end{longtable}
\end{landscape}

\end{document}
  • 1
    What's the purpose of using \multicolumn{1}{c}{Author} ? It seems redundant and unnecessary. Simply put Author instead. – bmv Feb 16 '18 at 9:29
1

You are missing a \\ to end the row after the caption:

\caption{Monolingual Online/Offline Recognition Systems}
\label{Tab:2} \\      
0

Besides the missing \\ the following MWE provides some improvements of your table:

  • ltablex to support using tabularx's X columns in multipage tables
  • using p columns instead of l to save horizontal space
  • removing superfluous \multcolumn{1} commands
  • introducing siunitx for consistent spacing between numbers and units
  • replacing \hrule and surrounding spacing commands by \midrules
  • adding white space between the entries as a guide to the eye
  • reducing the font size to save space
  • added some missing spaces
  • ...

Further improvements might still need to be done.

\documentclass[12pt,a4paper]{article}
\usepackage{lscape}
\usepackage{ltablex}
\usepackage{siunitx}
\usepackage{ragged2e}
\usepackage{booktabs}
\usepackage{caption}

\begin{document}

{\RaggedRight \renewcommand{\arraystretch}{1.75} \small
\begin{landscape}
\captionsetup{singlelinecheck=off, justification=centering}
\begin{tabularx}{\linewidth}{p{2.5cm}p{2cm}p{2.5cm}XXX}
\caption{Monolingual Online/Offline Recognition Systems}
\label{Tab:2}       \\
\toprule\midrule
Author&
Script&
Text mode&
classifier  &
Dataset &
Results \\
\midrule\midrule
\endfirsthead
\multicolumn{6}{c}{{\tablename} \thetable{} -- Continued}\\ \toprule\midrule
Author&
Script&
Text mode&
classifier  &
Dataset &
Results \\
\midrule\midrule
\endhead
Rabi et al (2017) & Cursive Arabic &    Offline Handwritten &   HMM & IFN/ENIT  &87.93\% \\
Roy et al  (2017) &  Arabic & Offline, Handwritten & Deep belief network with HMM &   IFN/ENIT &  89.46\% \\
Iwana et al (2017) & Latin & Online &    DTW &   UNIPEN digits data &    96.67\% \\
Sen et al  (2017) &  Bangla  & Online &  & Handwritten   10,000 character dataset &  95.57\% \\
Bhattacharya et al (2016) &  Bangla& Online  & & 33453 word samples written by 31 writers &  94.3\% \\
Dash et al (2016) & Bangla &    Offline & Binary external symmetry axis constellation with Boolean matching &   ISI kolkata and IITBBS database for Odia numerals, ISI Kolkata bangle numeral and IITBBS odia character database &  99.35\%, 98.9\%, 99.48\% and 95.01\% respectively accuracy \SI{0.02528}{\s}, \SI{0.02615}{\s}, \SI{0.02392}{\s}, \SI{0.03791}{\s} resptive time \\
Pengchao et al (2016) & Chinese & Printed,offline & CNN & 2789965 samples of GB2312-80 database & 99.90\% \\
Zhang et al (2016) & Chinese & Online & Deep CNN & CASIA-OLHWDB 1.0, CASIA-OLHwDB 1.1 &  98.44\% and 98.05\% \\
Sundram et al (2015) & Tamil & Online & Expert SVMs & 15000 handwritten isolated words & 93.0\% and 81.6\% at symbol and word level respectively. \\
Suyyagh et al (2015) &  Arabic & Offline Handwritten & FPGA & IFN/ENIT & 20 times faster than the software implementation and is less accurate by only 2.8\% \\

Arora et al (2014) & Gurumukhi & Offline Printed & SVM with linear and polynomial kernel & 7257 different images & 92.38\% for linear, 85.38\% for polynomial \\
Nguyen et al (2014) & English &  Online & SVM with semi incremental approach & IAM-OnDB &    65.70\% WRR\\
Bral et al (2014) &  Bangla &Online Handwritten & 5890 training set, 3534 test set & 91.6\% \\
A et al (2014) & Devanagari & Online & HMM with Nearest Neighbor classifier & 32,192 samples of 47 characters & 91.38\% \\

\end{tabularx}
\end{landscape}
}
\end{document}

enter image description here

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.