diff --git a/Article/intro.tex b/Article/intro.tex index ed01ccd06c78674138c0ceb900039af1135e27c3..8efbf7fb15c7573e94f71932a6343fbfd1068f20 100755 --- a/Article/intro.tex +++ b/Article/intro.tex @@ -37,7 +37,7 @@ blurred segments of fixed width in gray-level images was already introduced. It is based on a first rough detection in a local area of the image either defined by the user in supervised context or blindly explored in automatic mode. The goal is to disclose the presence of an edge. -Therefore, a simple test as the gradient maximal value is performed. +Therefore a simple test as the gradient maximal value is performed. In case of success, refinement steps are run through an exploration of the image in the direction of the detected edge. @@ -48,25 +48,23 @@ untill a correct candidate with an acceptable gradient orientation is found. Only the gradient information is processed as it provides a good information on the image dynamics, and hence the presence of edges. Trials to also use the intensity signal were made through costly correlation -techniques, but they were mostly successful for detecting objects with -stable appearance such as metallic pipes \cite{AubryAl17}. +techniques, but they were mostly successful for detecting shapes with a +stable appearance such as metallic tubular objects \cite{AubryAl17}. -Despite of good performances obtained compared to other methods from the -literature, several drawbacks remain. -First, the blurred segment width is not measured, but initially set by the -user to meet the application requirements, so that no quality information -can be derived from the computed segment. -Moreover, the blurred segment hull is left free to shift sidewards, or worst, -to rotate around a thin edge in the image, and the produced orientation -value can be largely biased. +Despite of good performances achieved, several drawbacks remain. +First, the blurred segment width is not measured but initially set by the +user according to the application requirements. The produced information +on the edge quality is rather poor, and especially when the edge is thin, +the risk to incorporate outlier points is quite high, thus producing a +biased estimation of the edge orientation. -Then, two refinement steps are systematically run to cope with most of the -tested data, although this is useless when the first detection is successfull. -Beyond, there is no guarantee that this could treat all kinds of data. -The search direction is fixed by the support vector of the blurred segment -detected at the former step, and because the set of vectors in a bounded -discrete space is finite, there is necessarily a limit on this direction -accuracy. +Then, two refinement steps are systematically run. +On one hand, this is useless when the first detection is successfull. +On the other hand, there is no guarantee that this approach is able to +process larger images. +The search direction relies on the support vector of the blurred segment +detected at the former step, and the numerization rounding fixes a limit +on this estimated orientation accuracy. It results that more steps would inevitably be necessary to process higher resolution images. @@ -83,10 +81,10 @@ As a side effect, these two major evolutions also led to a noticeable improvement of the time performance of the detector. In the next section, the main theoretical notions this work relies on are -introduced, with a specific focus on the new concept of adaptive directional -scanner. -Then the new detector workflow and its integration into both supervised and -unsupervised contexts are presented and discussed in \RefSec{sec:method}. +introduced. +Then the new detector workflow, the adaptive directional scanner, the control +of the assigned with and their integration into both supervised +and unsupervised contexts are presented and discussed in \RefSec{sec:method}. Experiments led to assess the expected increase of performance are decribed in \RefSec{sec:expe}. Finally achieved results are summarized in \RefSec{sec:conclusion}, diff --git a/Article/method.tex b/Article/method.tex index 919b5c18e774fa605f97c557f05690ec742ee47e..f2d4d1bd47ade10f870c6b77b4a40726405626b0 100755 --- a/Article/method.tex +++ b/Article/method.tex @@ -267,7 +267,7 @@ This distinction is illustrated on \RefFig{fig:edgeDir}. Another option, called multi-detection allows the detection of all the segments crossed by the input stroke $AB$. -The multi-detection algorithm is displayed below. +The multi-detection algorithm (Algorithm 1) is displayed below. \input{Fig_method/algoMulti} @@ -282,6 +282,7 @@ detected blurred segments $\mathcal{B}_j''$ at the end of each successful detection; iii) points marked as occupied are rejected when selecting candidates for the blurred segment extension in the fine tracking step. +Multiple detections of the same edge are thus avoided. In edge selection mode (\RefFig{fig:edgeDir} b), the multi-detection algorithm is executed twice. @@ -341,7 +342,8 @@ segment. \subsection{Automatic blurred segment detection} An unsupervised mode is also proposed to automatically detect all the -straight edges in the image. A stroke that crosses the whole image, is +straight edges in the image. The principle of this automatic detection +is described in Algorithm 2. A stroke that crosses the whole image, is swept in both direction, vertical then horizontal, from the center to the borders. At each position, the multi-detection algorithm is run to collect all the segments found under the stroke. diff --git a/Article/notions.tex b/Article/notions.tex index 21c395ce7c88b920405be44b68dd9c7c2cc8f41b..981465fa9cb99ee066c99200a21adb43cedf1486 100755 --- a/Article/notions.tex +++ b/Article/notions.tex @@ -67,7 +67,7 @@ DS = \left\{ S_i = \mathcal{D} \cap \mathcal{N}_i \cap \mathcal{I} \end{array} \right. \right\} %S_i = \mathcal{D} \cap \mathcal{N}_i, \mathcal{N}_i \perp \mathcal{D} \end{equation} -In this expression, the clause +In this definition, the clause $\delta(\mathcal{N}_i) = - \delta^{-1}(\mathcal{D})$ expresses the othogonality constraint between the scan lines $\mathcal{N}_i$ and the scan strip $\mathcal{D}$. @@ -79,7 +79,7 @@ The scans $S_i$ are developed on each side of a start scan $S_0$, and ordered by their distance to the start line $\mathcal{N}_0$ with a positive (resp. negative) sign if they are on the left (resp. right) side of $\mathcal{N}_0$ (\RefFig{fig:ds}). -The directional scan is iterately processed from the start scan to both ends. +The directional scan is iterately parsed from the start scan to both ends. At each iteration $i$, the scans $S_i$ and $S_{-i}$ are successively processed. \begin{figure}[h] @@ -111,9 +111,11 @@ At each iteration $i$, the scans $S_i$ and $S_{-i}$ are successively processed. \put(-60,30){$\mathcal{N}_8$} \put(-169,8){$\mathcal{N}_{-5}$} \end{picture} - \caption{A directional scan: the start scan $S_0$ in blue, odd scans in - green, even scans in red, scan lines bounds $\mathcal{N}_i$ in - plain lines and scan strip bounds $\mathcal{D}$ in dotted lines.} + \caption{A directional scan. + The start scan $S_0$ is drawn in blue, odd scans in green, + even scans in red, the bounds of scan lines $\mathcal{N}_i$ + with plain lines and the bounds of scan strip $\mathcal{D}$ + with dotted lines.} \label{fig:ds} \end{figure}