diff options
| -rw-r--r-- | abstract.tex | 9 | ||||
| -rw-r--r-- | uniqueness.tex | 2 |
2 files changed, 9 insertions, 2 deletions
diff --git a/abstract.tex b/abstract.tex index 09ede67..0c3d9f1 100644 --- a/abstract.tex +++ b/abstract.tex @@ -1,4 +1,11 @@ \begin{abstract} - + This paper explores a novel approach for person recognition based on + skeletal measurements. After showing that exact measurements allow + for exact recognition, we study two algorithmic approaches for + identification in case of approximate measurements. A real-life + experiment with 25 people and measurements obtained from the Kinect + range camera gives us promising results and comparison with state of + the art facial recognition and validates the viability of + skeleton-base identification, \end{abstract} diff --git a/uniqueness.tex b/uniqueness.tex index 5bd55e4..35f9a37 100644 --- a/uniqueness.tex +++ b/uniqueness.tex @@ -81,7 +81,7 @@ output of the algorithm for the threshold $\delta$ is defined as: Figure \ref{fig:roc} shows the ROC curve of the proximity threshold algorithm for different values of the standard deviation of the noise, as well as the ROC of the best performing face detection algorithm in -the Image-restricted LFW benchmark: \emph{Associate-Predict} +the image-restricted LFW benchmark: \emph{Associate-Predict} \cite{associate}. The results show that with a standard deviation of 3mm, skeleton |