diff options
Diffstat (limited to 'report')
| -rw-r--r-- | report/paper.md | 188 |
1 files changed, 79 insertions, 109 deletions
diff --git a/report/paper.md b/report/paper.md index e673adf..7453289 100644 --- a/report/paper.md +++ b/report/paper.md @@ -13,193 +13,163 @@ Caltech dataset. The number of clusters or the number of centroids determine the vocabulary size. - - - ## Bag-of-words histograms of example training/testing images -## Vector quantisation process - -# RF classifier - -Train and test Random Forest using the training and testing data set in the form of bag-of-words -obtained in Q1. Change the RF parameters (including the number of trees, the depth of trees, the -degree of randomness parameter, the type of weak-learners: e.g. axis-aligned or two-pixel test), -and show and discuss the results: - -## recognition accuracy, confusion matrix, - -## example success/failures, - -## time-efficiency of training/testing, - -## impact of the vocabulary size on classification accuracy. - -# RF codebook - -In Q1, replace the K-means with the random forest codebook, i.e. applying RF to 128 dimensional -descriptor vectors with their image category labels, and using the RF leaves as the visual -vocabulary. With the bag-of-words representations of images obtained by the RF codebook, train -and test Random Forest classifier similar to Q2. Try different parameters of the RF codebook and -RF classifier, and show/discuss the results in comparison with the results of Q2, including the -vector quantisation complexity. - -# Pictures +Looking at picture \ref{fig:histo_te} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/256t1_e200D5_cm.pdf} -\caption{Part 3 confusion matrix e100k256d5cm} -\label{fig:rerank} +\includegraphics[height=4em]{fig/hist_test.jpg} +\includegraphics[width=20em]{fig/km-histogram.pdf} +\caption{Bag-of-words Training histogram} +\label{fig:histo_tr} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/Depth_Trees_P2.pdf} -\caption{DepthTreesP2} -\label{fig:rerank} +\includegraphics[height=4em]{fig/hist_train.jpg} +\includegraphics[width=20em]{fig/km-histtest.pdf} +\caption{Bag-of-words Testing histogram} +\label{fig:histo_te} \end{center} \end{figure} -\begin{figure}[H] -\begin{center} -\includegraphics[width=18em]{fig/Depth_Trees_P3.pdf} -\caption{DepthTreesP3} -\label{fig:rerank} -\end{center} -\end{figure} +## Vector quantisation process -\begin{figure}[H] -\begin{center} -\includegraphics[width=18em]{fig/Depth_Trees_P3_fixedestimators.pdf} -\caption{DepthTreesP3fixedestimators} -\label{fig:rerank} -\end{center} -\end{figure} +# RF classifier -\begin{figure}[H] -\begin{center} -\includegraphics[width=18em]{fig/e100k256d5_cm.pdf} -\caption{e100k256d5cm Kmean Confusion Matrix} -\label{fig:rerank} -\end{center} -\end{figure} +## Hyperparameters tuning -\begin{figure}[H] -\begin{center} -\includegraphics[width=18em]{fig/error_depth_kmean100.pdf} -\caption{errordepthkmean100} -\label{fig:rerank} -\end{center} -\end{figure} +Figure \ref{fig:km-tree-param} shows the effect of tree depth and number of trees +for kmean 100 cluster centers. \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/error_depth_p3.pdf} -\caption{errordepthp3} -\label{fig:rerank} +\includegraphics[width=12em]{fig/error_depth_kmean100.pdf} +\includegraphics[width=12em]{fig/trees_kmean.pdf} +\caption{Classification error varying trees depth(left) and numbers of trees(right)} +\label{fig:km-tree-param} \end{center} \end{figure} -\begin{figure}[H] -\begin{center} -\includegraphics[width=18em]{fig/kmean_rand.pdf} -\caption{kmeanrand} -\label{fig:rerank} -\end{center} -\end{figure} +Figure \ref{fig:kmeanrandom} shows randomness parameter for kmean 100. \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/kmeans_vocsize.pdf} -\caption{kmeansvocsize} -\label{fig:rerank} +\includegraphics[width=18em]{fig/new_kmean_random.pdf} +\caption{newkmeanrandom} +\label{fig:kmeanrandom} \end{center} \end{figure} +## Weak Learners comparison + +In figure \ref{fig:2pt} it is possible to notice an improvement in recognition accuracy by 1%, +with the two pixels test, achieving better results than the axis-aligned counterpart. The two-pixels +test however brings a slight deacrease in time performance which has been measured to be on **average 3 seconds** +more. This is due to the complexity added by the two-pixels test, since it adds one dimension to the computation. + \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/new_kmean_random.pdf} -\caption{newkmeanrandom} -\label{fig:rerank} +\includegraphics[width=18em]{fig/2pixels_kmean.pdf} +\caption{Kmean classification accuracy changing the type of weak learners} +\label{fig:2pt} \end{center} \end{figure} +## Impact of the vocabulary size on classification accuracy. + \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/p3_colormap.pdf} -\caption{p3colormap} -\label{fig:rerank} +\includegraphics[width=12em]{fig/kmeans_vocsize.pdf} +\includegraphics[width=12em]{fig/time_kmeans.pdf} +\caption{Effect of vocabulary size; classification error left, time right} +\label{fig:km_vocsize} \end{center} \end{figure} +## Confusion matrix for case XXX, with examples of failure and success + \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/p3_rand.pdf} -\caption{p3rand} -\label{fig:rerank} +\includegraphics[width=18em]{fig/e100k256d5_cm.pdf} +\caption{e100k256d5cm Kmean Confusion Matrix} +\label{fig:km_cm} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/p3_time.pdf} -\caption{p3time} -\label{fig:rerank} +\includegraphics[width=10em]{fig/success_km.pdf} +\includegraphics[width=10em]{fig/fail_km.pdf} +\caption{Kmean: Success on the left; Failure on the right} +\label{fig:km_succ} \end{center} \end{figure} +# RF codebook + +In Q1, replace the K-means with the random forest codebook, i.e. applying RF to 128 dimensional +descriptor vectors with their image category labels, and using the RF leaves as the visual +vocabulary. With the bag-of-words representations of images obtained by the RF codebook, train +and test Random Forest classifier similar to Q2. Try different parameters of the RF codebook and +RF classifier, and show/discuss the results in comparison with the results of Q2, including the +vector quantisation complexity. + \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/p3_vocsize.pdf} -\caption{p3vocsize} -\label{fig:rerank} +\includegraphics[width=18em]{fig/256t1_e200D5_cm.pdf} +\caption{Part 3 confusion matrix e100k256d5cm} +\label{fig:p3_cm} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/time_kmeans.pdf} -\caption{timekmeans} -\label{fig:rerank} +\includegraphics[width=10em]{fig/success_3.pdf} +\includegraphics[width=10em]{fig/fail_3.pdf} +\caption{Part3: Success on the left; Failure on the right} +\label{fig:p3_succ} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/trees_kmean.pdf} -\caption{treeskmean} -\label{fig:rerank} +\includegraphics[width=12em]{fig/error_depth_p3.pdf} +\includegraphics[width=12em]{fig/trees_p3.pdf} +\caption{Classification error varying trees depth(left) and numbers of trees(right)} +\label{fig:p3_trees} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=18em]{fig/trees_p3.pdf} -\caption{treesp3} -\label{fig:rerank} +\includegraphics[width=18em]{fig/p3_rand.pdf} +\caption{Effect of randomness parameter on classification error} +\label{fig:p3_rand} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=10em]{fig/success_km.pdf} -\includegraphics[width=10em]{fig/fail_km.pdf} -\caption{Kmean: Success on the left; Failure on the right} -\label{fig:rerank} +\includegraphics[width=12em]{fig/p3_vocsize.pdf} +\includegraphics[width=12em]{fig/p3_time.pdf} +\caption{Effect of vocabulary size; classification error left, time right} +\label{fig:p3_voc} \end{center} \end{figure} \begin{figure}[H] \begin{center} -\includegraphics[width=10em]{fig/success_3.pdf} -\includegraphics[width=10em]{fig/fail_3.pdf} -\caption{Part3: Success on the left; Failure on the right} -\label{fig:rerank} +\includegraphics[width=18em]{fig/p3_colormap.pdf} +\caption{Varying leaves and estimators: effect on accuracy} +\label{fig:p3_colormap} \end{center} \end{figure} +# Comparison of methods and conclusions + # References |