Commit 8b312b8c authored by Jayke Meijer's avatar Jayke Meijer

Corrected some grammatical errors.

parent d3e13b6f
...@@ -39,8 +39,8 @@ Microsoft recently published a new and effective method to find the location of ...@@ -39,8 +39,8 @@ Microsoft recently published a new and effective method to find the location of
text in an image. text in an image.
Determining what character we are looking at will be done by using Local Binary Determining what character we are looking at will be done by using Local Binary
Patterns. The main goal of our research is finding out how effective LBPs are Patterns. The main goal of our research is finding out how effective LBP's are
in classifying characters on a licenseplate. in classifying characters on a license plate.
In short our program must be able to do the following: In short our program must be able to do the following:
...@@ -145,9 +145,9 @@ stored in XML files. So, the first step is to read these XML files.\\ ...@@ -145,9 +145,9 @@ stored in XML files. So, the first step is to read these XML files.\\
\paragraph*{Perspective transformation} \paragraph*{Perspective transformation}
Once we retrieved the cornerpoints of the licenseplate, we feed those to a Once we retrieved the cornerpoints of the license plate, we feed those to a
module that extracts the (warped) licenseplate from the original image, and module that extracts the (warped) license plate from the original image, and
creates a new image where the licenseplate is cut out, and is transformed to a creates a new image where the license plate is cut out, and is transformed to a
rectangle. rectangle.
\subsection{Noise reduction} \subsection{Noise reduction}
...@@ -157,11 +157,11 @@ etc., as from dirt on the license plate. In this case, noise therefore means ...@@ -157,11 +157,11 @@ etc., as from dirt on the license plate. In this case, noise therefore means
any unwanted difference in color from the surrounding pixels. any unwanted difference in color from the surrounding pixels.
\paragraph*{Camera noise and small amounts of dirt} \paragraph*{Camera noise and small amounts of dirt}
The dirt on the licenseplate can be of different sizes. We can reduce the The dirt on the license plate can be of different sizes. We can reduce the
smaller amounts of dirt in the same way as we reduce normal noise, by applying smaller amounts of dirt in the same way as we reduce normal noise, by applying
a gaussian blur to the image. This is the next step in our program.\\ a Gaussian blur to the image. This is the next step in our program.\\
\\ \\
The gaussian filter we use comes from the \texttt{scipy.ndimage} module. We use The Gaussian filter we use comes from the \texttt{scipy.ndimage} module. We use
this function instead of our own function, because the standard functions are this function instead of our own function, because the standard functions are
most likely more optimized then our own implementation, and speed is an most likely more optimized then our own implementation, and speed is an
important factor in this application. important factor in this application.
...@@ -179,7 +179,7 @@ surrounding the character. ...@@ -179,7 +179,7 @@ surrounding the character.
The retrieval of the character is done the same as the retrieval of the license The retrieval of the character is done the same as the retrieval of the license
plate, by using a perspective transformation. The location of the characters on plate, by using a perspective transformation. The location of the characters on
the licenseplate is also available in de XML file, so this is parsed from that the license plate is also available in de XML file, so this is parsed from that
as well. as well.
\subsection{Creating Local Binary Patterns and feature vector} \subsection{Creating Local Binary Patterns and feature vector}
...@@ -200,12 +200,12 @@ available. These parameters are:\\ ...@@ -200,12 +200,12 @@ available. These parameters are:\\
\begin{tabular}{l|l} \begin{tabular}{l|l}
Parameter & Description\\ Parameter & Description\\
\hline \hline
$\sigma$ & The size of the gaussian blur.\\ $\sigma$ & The size of the Gaussian blur.\\
\emph{cell size} & The size of a cell for which a histogram of LBPs will \emph{cell size} & The size of a cell for which a histogram of LBPs will
be generated.\\ be generated.\\
$\gamma$ & Parameter for the Radial kernel used in the SVM.\\ $\gamma$ & Parameter for the Radial kernel used in the SVM.\\
$c$ & The soft margin of the SVM. Allows how much training $c$ & The soft margin of the SVM. Allows how much training
errors are excepted. errors are accepted.
\end{tabular}\\ \end{tabular}\\
\\ \\
For each of these parameters, we will describe how we searched for a good For each of these parameters, we will describe how we searched for a good
...@@ -225,10 +225,10 @@ that this was $\sigma = ?$. ...@@ -225,10 +225,10 @@ that this was $\sigma = ?$.
The cell size of the Local Binary Patterns determines over what region a The cell size of the Local Binary Patterns determines over what region a
histogram is made. The trade-off here is that a bigger cell size makes the histogram is made. The trade-off here is that a bigger cell size makes the
classification less affected by relative movement of a character compared to classification less affected by relative movement of a character compared to
those in the learningset, since the important structure will be more likely to those in the learning set, since the important structure will be more likely to
remain in the same cell. However, if the cell size is too big, there will not remain in the same cell. However, if the cell size is too big, there will not
be enough cells to properly describe the different areas of the character, and be enough cells to properly describe the different areas of the character, and
the featurevectors will not have enough elements.\\ the feature vectors will not have enough elements.\\
\\ \\
In order to find this parameter, we used a trial-and-error technique on a few In order to find this parameter, we used a trial-and-error technique on a few
basic cell sizes, being ?, 16, ?. We found that the best result was reached by basic cell sizes, being ?, 16, ?. We found that the best result was reached by
...@@ -257,15 +257,15 @@ We found that the best values for these parameters are $c=?$ and $\gamma =?$. ...@@ -257,15 +257,15 @@ We found that the best values for these parameters are $c=?$ and $\gamma =?$.
\section{Results} \section{Results}
The wanted to find out two things with this research: The speed of the The goal was to find out two things with this research: The speed of the
classification and the accuracy. In this section we will show our findings. classification and the accuracy. In this section we will show our findings.
\subsection{Speed} \subsection{Speed}
Recognizing license plates is something that has to be done with good speed, Recognizing license plates is something that has to be done fast, since there
since there can be a lot of cars passing a camera, especially on a highway. can be a lot of cars passing a camera in a short time, especially on a highway.
Therefore, we measured how well our program performed in terms of speed. We Therefore, we measured how well our program performed in terms of speed. We
measure the time used to classify a license plate, not the trainign of the measure the time used to classify a license plate, not the training of the
dataset, since that can be done offline, and speed is not a primary necessity dataset, since that can be done offline, and speed is not a primary necessity
there.\\ there.\\
\\ \\
...@@ -275,13 +275,13 @@ The speed of a classification turned out to be blablabla. ...@@ -275,13 +275,13 @@ The speed of a classification turned out to be blablabla.
Of course, it is vital that the recognition of a license plate is correct, Of course, it is vital that the recognition of a license plate is correct,
almost correct is not good enough here. Therefore, we have to get the highest almost correct is not good enough here. Therefore, we have to get the highest
accuracy score we possibly can. According to Wikipedia accuracy score we possibly can.\\
\\ According to Wikipedia
\footnote{ \footnote{
\url{http://en.wikipedia.org/wiki/Automatic_number_plate_recognition}}, \url{http://en.wikipedia.org/wiki/Automatic_number_plate_recognition}},
commercial license plate recognition software score about $90\%$ to $94\%$, commercial license plate recognition software score about $90\%$ to $94\%$,
under optimal conditions and with modern equipment.\\ under optimal conditions and with modern equipment. Our program scores an
\\ average of blablabla.
Our program scores an average of blablabla.
\section{Conclusion} \section{Conclusion}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment