\relax 
\@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{1}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2}Dataset}{1}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Data Augmentation}{1}{}\protected@file@percent }
\newlabel{sec:augmentation}{{2.1}{1}{}{subsection.2.1}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Sample images from the training dataset, showing the effect of data augmentation.}}{2}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {3}Feature Extraction}{2}{}\protected@file@percent }
\newlabel{sec:features}{{3}{2}{}{section.3}{}}
\@writefile{toc}{\contentsline {section}{\numberline {4}Low-Level Features Models}{3}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Logistic Regression}{3}{}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Logistic regression training curves for different low level features.}}{3}{}\protected@file@percent }
\providecommand*\caption@xref[2]{\@setref\relax\@undefined{#1}}
\newlabel{fig:train_curves_color_logistic}{{2}{3}{}{figure.2}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces Summary of training (semi-transparent) and validation (solid) performance for different low-level feature combinations with logistic regression.}}{4}{}\protected@file@percent }
\newlabel{fig:color_recap_logistic}{{3}{4}{}{figure.3}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces Visualization of the \emph  {Histogram of Oriented Gradients} for a sample image. It's evident how HOG features perfectly capture shape and edge information, crucial for road sign classification.}}{4}{}\protected@file@percent }
\newlabel{fig:hogging}{{4}{4}{}{figure.4}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Feature reduction}{4}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {4.3}Grayscale}{5}{}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {5}{\ignorespaces Summary of training (semi-transparent) and validation (solid) performance for different low-level feature combinations with logistic regression on grayscale images.}}{5}{}\protected@file@percent }
\newlabel{fig:grayscale_recap_logistic}{{5}{5}{}{figure.5}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.4}Multi-Layer Perceptron}{5}{}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {6}{\ignorespaces Comparison of performance (both training and validation) on color and grayscale images with different MLPs.}}{6}{}\protected@file@percent }
\newlabel{fig:recap_mlp}{{6}{6}{}{figure.6}{}}
\@writefile{toc}{\contentsline {section}{\numberline {5}Convolutional Neural Network}{6}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces CNN architecture. $C = 3$ for RGB, $C = 1$ for grayscale.}}{7}{}\protected@file@percent }
\newlabel{tab:cnn_arch}{{1}{7}{}{table.1}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {7}{\ignorespaces CNN training curves for RGB images.}}{7}{}\protected@file@percent }
\newlabel{fig:cnn_training}{{7}{7}{}{figure.7}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Activation Maps}{7}{}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {8}{\ignorespaces Comparison of first-layer activation maps for RGB and grayscale inputs. The RGB maps show stronger responses to color features, while the grayscale maps focus more on edges, shapes and contrast.}}{8}{}\protected@file@percent }
\newlabel{fig:activation_maps}{{8}{8}{}{figure.8}{}}
\@writefile{toc}{\contentsline {section}{\numberline {6}Conclusion}{8}{}\protected@file@percent }
\gdef \@abspage@last{8}