Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
L
licenseplates
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
This is an archived project. Repository and other project resources are read-only.
Show more breadcrumbs
Taddeüs Kroes
licenseplates
Commits
40b20121
Commit
40b20121
authored
13 years ago
by
Taddeus Kroes
Browse files
Options
Downloads
Patches
Plain Diff
Added some text to plan.tex.
parent
7a002df7
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
.gitignore
+5
-1
5 additions, 1 deletion
.gitignore
docs/plan.tex
+31
-15
31 additions, 15 deletions
docs/plan.tex
with
36 additions
and
16 deletions
.gitignore
+
5
−
1
View file @
40b20121
*.swp
*.swp
*~
*.pyc
*.pyc
*.pdf
*.pdf
*~
*.aux
*.log
*.synctex.gz
*.toc
This diff is collapsed.
Click to expand it.
plan.tex
→
docs/
plan.tex
+
31
−
15
View file @
40b20121
...
@@ -3,6 +3,10 @@
...
@@ -3,6 +3,10 @@
\title
{
Teaching a computer to learn, find and read licence plates
}
\title
{
Teaching a computer to learn, find and read licence plates
}
\date
{
November 17th, 2011
}
\date
{
November 17th, 2011
}
% Paragraph indentation
\setlength
{
\parindent
}{
0pt
}
\setlength
{
\parskip
}{
1ex plus 0.5ex minus 0.2ex
}
\begin{document}
\begin{document}
\maketitle
\maketitle
...
@@ -15,50 +19,62 @@ Gijs van der Voort\\Richard Torenvliet\\Jayke Meijer\\Tadde\"us Kroes\\Fabi\'en
...
@@ -15,50 +19,62 @@ Gijs van der Voort\\Richard Torenvliet\\Jayke Meijer\\Tadde\"us Kroes\\Fabi\'en
\section
{
Introduction
}
\section
{
Introduction
}
Licence plates are used all over the world. The plates are, usually, attached to the front and rear
Licence plates are used all over the world. The plates are, usually, attached to the front and rear
of a motorised vehicle and used for i
n
dentifying this vehicle. Every
of a motorised vehicle and used for identifying this vehicle. Every
country can have more or less its own version of a licence plate, but all these systems do not
country can have more or less its own version of a licence plate, but all these systems do not
differ greatly. We will be focusing on the
d
utch system for licence plates.
differ greatly. We will be focusing on the
D
utch system for licence plates.
\section
{
Problem Description
}
\section
{
Problem Description
}
License plates are used for i
n
dentification and thus made to recognize from great
License plates are used for identification and thus made to recognize from great
distances and still be seen in many weather conditions. Our learning set of photos contains
distances and still be seen in many weather conditions. Our learning set of photos contains
''
'
ik weet niet precies wat voor camera ''. The angle in which these pictures are taken or the angle
'' ik weet niet precies wat voor camera ''. The angle in which these pictures are taken or the angle
of the approaching vehicles are always different and some licence plates are a bit dirty,
of the approaching vehicles are always different and some licence plates are a bit dirty,
but for a human they are still pretty easy to i
n
dentify. A computer or perhaps a small
but for a human they are still pretty easy to identify. A computer or perhaps a small
chipset will need to be tho
u
rougly practiced. In short our program must be able to
chipset will need to be thoroug
h
ly practiced. In short our program must be able to
do the following:
do the following:
\begin{
itemiz
e}
\begin{
enumerat
e}
\item
Find the location of the license plate.
\item
Find the location of the license plate.
\item
Use transformations
s
o
it gets
an upfront view.
\item
Use
perspective
transformations
t
o
obtain
an upfront view.
\item
Reduce noise where possible.
\item
Reduce noise where possible.
\item
Get
the locations of each letter and extract
ing
it.
\item
Find
the locations of each letter and extract it.
\item
Apply a
l
ocal
b
inary
p
attern algorithm on each letter.
\item
Apply a
L
ocal
B
inary
P
attern algorithm on each letter.
\item
Match
ing
the found patterns with
found
results and return the best match.
\item
Match the found patterns with results
from the learning set
and return the best match
for each letter
.
\end{
itemiz
e}
\end{
enumerat
e}
\section
{
Solution
}
\section
{
Solution
}
Now that we know the problem we can start with stating our solution. This will
Now that we know the problem we can start with stating our solution. This will
come in a few steps aswell.
come in a few steps as
well.
\subsection
{
Localizing the plate
}
\subsection
{
Localizing the plate
}
The photos are of very high contrast. Most of the time only the lights of a vehicle
The photos are of very high contrast. Most of the time only the lights of a vehicle
are visible in addition to the license plate. We can first crop the image until
l
are visible in addition to the license plate. We can first crop the image until
it finds brighter pixel values in a row or column. Then we can apply ''?? weet niet hoor'' local histogram
it finds brighter pixel values in a row or column. Then we can apply ''?? weet niet hoor'' local histogram
matching to find out whether we have a light or license plate.
matching to find out whether we have a light or license plate.
\subsection
{
Transformations
}
\subsection
{
Transformations
}
Affine transformations will do the trick
Once the locations of the four corner points of the license plate have been
found, a simple perspective transformation will be sufficient to transform and
resize the plate to a normalized format.
\subsection
{
Reducing noise
}
\subsection
{
Reducing noise
}
Weet niet precies hoe, maar van die kleine rondjes / vlekjes / stipjes moeten
Weet niet precies hoe, maar van die kleine rondjes / vlekjes / stipjes moeten
we wel een beetje weghalen want die maken het wel een beetje lelijk
we wel een beetje weghalen want die maken het wel een beetje lelijk
Taddeus: Ik brainstorm hier een beetje...:
Small amounts of noise will probably be suppressed by usage of a Gaussian
filter. A real problem occurs in very dirty licence plates, where branches and
dirt over a letter could radically change the local binary pattern. A question
we can ask ourselves here, is whether we want to concentrate ourselves on
these exceptional cases. By law, license plates have to be readable.
Therefore, we will first direct our attention at getting a higher score in the
'regular' test set before addressing these cases.
\subsection
{
Extracting a letter
}
\subsection
{
Extracting a letter
}
De karakteristiek bepalen van het dash/streepje (-) dan heb je in elk geval al
De karakteristiek bepalen van het dash/streepje (-) dan heb je in elk geval al
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment