\section{Performance Evaluation}
\label{sec:eval}

To evaluate the effectiveness of the proposed method, we do the different ratios of compressing on a thermal image by our method compare to JPEG image using different quality and png image, a lossless bit map image. We set the camera at the ceiling and view direction is perpendicular to the ground, and the image size is $480 \times 640$ pixels. The JPEG image is generated by OpenCV $3.3.0$, and image quality from $1$ to $99$.

Figure~\ref{fig:4KMy} and Figure~\ref{fig:4KJpeg} show the different of JPEG and our method. JPEG image id generated by image quality level $3$, and image of our method does $1390$ rounds of separate and compressed by Huffman Coding. In this case, Huffman Coding can reduce $39\%$ of our image size.

\begin{figure}[ht]
	\centering
 	\includegraphics[width=0.6\columnwidth]{figures/my4000.png}
	\caption{4KB Image by Proposed Method}
	\label{fig:4KMy}
\end{figure}

\begin{figure}[ht]
	\centering
 	\includegraphics[width=0.6\columnwidth]{figures/quality3.jpg}
	\caption{4KB Image by JPEG}
	\label{fig:4KJpeg}
\end{figure}

Figure~\ref{fig:compareToJpeg} shows that the size of file can reduce more than $50\%$ compare to JPEG image when both have $0.5\% (0.18^\circ C)$ of root-mean-square error. Our method has $82\%$ less error rate when both size are $4KB$ image. The percentage of file size is compare to PNG image. 

\begin{figure}[ht]
	\centering
 	\includegraphics[width=\columnwidth]{figures/compareToJpeg.pdf}
	\caption{Proposed method and JPEG comparing}
	\label{fig:compareToJpeg}
\end{figure}

The computing time on Raspberry Pi 3 is:
\subsubsection{Date Structure Initialize}
XXX.XXX second.
\subsubsection{Image Loading}
XXX.XXX second.
\subsubsection{Region Separation}
XXX.XXX second. (a chart)