diff --git a/docs/verslag.tex b/docs/verslag.tex index c099d669d396abc0ec932b2c93a68712ba3169ba..375e45dfbd1ea4624a3c81d39128927ae17a8dc6 100644 --- a/docs/verslag.tex +++ b/docs/verslag.tex @@ -124,7 +124,13 @@ straight lines and simple curves, LBP should be suited to identify these. \subsubsection{LBP Algorithm} The LBP algorithm that we implemented is a square variant of LBP, the same that is introduced by Ojala et al (1994). Wikipedia presents a different -form where the pattern is circular. +form where the pattern is circular, this form is convenient because with +interpolation you can choose the size of the circle \textbf{and} to how many +neighbours the circle has. That means how many times the center pixel +has to be evaluated against a neighbour. + +In the literature there are lots of examples where LBP is used for surface +recognition, facial recognition, human face emotion recoqnition ((Pietik\"ainen, Hadid, Zhao \& Ahonen (2011))) \begin{itemize} \item Determine the size of the square where the local patterns are being registered. For explanation purposes let the square be 3 x 3. \\ @@ -135,7 +141,7 @@ than the threshold it will be become a one else a zero. \begin{figure}[h!] \center \includegraphics[scale=0.5]{lbp.png} -\caption{LBP 3 x 3 (Pietik\"ainen, Hadid, Zhao \& Ahonen (2011))} +\caption{LBP 3 x 3 (Pietik\"ainen et all (2011))} \end{figure} Notice that the pattern will be come of the form 01001110. This is done when a @@ -169,7 +175,7 @@ order. Starting with dividing the pattern in to cells of size 16. \begin{figure}[h!] \center \includegraphics[scale=0.7]{cells.png} -\caption{Divide in cells(Pietik\"ainen et all (2011))} +\caption{Divide in cells(Pietik\"ainen et al. (2011))} \end{figure} \item Consider every histogram as a vector element and concatenate these. The @@ -200,6 +206,8 @@ subsection of the given dataset called the ''Learning set''. Once trained, the entire classifier can be saved as a Pickle object\footnote{See \url{http://docs.python.org/library/pickle.html}} for later usage. + + \section{Implementation} In this section we will describe our implementations in more detail, explaining @@ -314,9 +322,8 @@ dividing the \textbf{pattern} in to cells and create a histogram of that. So mul cells are related to one histogram. All the histograms are concatenated and feeded to the SVM that will be discussed in the next section, Classification. - \subsection{Classification} - +The SVM used in our project is a Gaussian radial based function. Where the kernel is \section{Finding parameters} @@ -474,5 +481,15 @@ were instantaneous! A crew to remember. Awesome +\begin{thebibliography}{9} +\bibitem{lbp1} + Matti Pietik\"ainen, Guoyin Zhao, Abdenour hadid, + Timo Ahonen. + \emph{Computational Imaging and Vision}. + Springer-Verlag, London, + 1nd Edition, + 2011. +\end{thebibliography} + \end{document}