Image Processing Reference
In-Depth Information
On the other hand, segmentation techniques are divided into either contextual or noncon-
textual. The noncontextual techniques do not care about account of special relations between
features in an image and group pixels together based on some global atribute, for example,
gray level or color. However, contextual techniques mainly are exploiting these relations, for
example, pixels with similar gray levels, and close spatial locations grouped with each other
[ 1 , 3 ] . Actually, the proposed algorithm is trying to exploit the segmentation contextual tech-
niques in object detection and classification. Succeeding section illustrates in details the idea
for the suggested algorithm.
4 The proposed algorithm
The proposed object detection and matching framework are divided into three parts. They are
consisting of segmentation, construction of objects' signatures in image, and matching them to
classify the object based on its signature [ 13 ] . The segmentation process represents the main
stone in this algorithm, which is giving initial hypotheses of object positions, scales and sup-
porting based on matching. These hypotheses are then refined through the object signature
classiier, to obtain final detection and signatures matching results. Figure 1 describes all steps
of the proposed algorithm [ 22 ] .
FIGURE 1 The proposed algorithm steps.
This figure starts by an example of original RGB image with all different objects, many mor-
phological functions and filters (edge detection, erosion, dilation, determination the number
of objects, watershed segmentation, etc.) are applied to enhance the work of this image. The
areas, centroids, orientations, eccentricities, convex areas for every object can easily be determ-
ined. Moreover, the boundary points ( x ij , y ij ) for each object are calculated individually, wherei
i represents the number of objects and j is the number of boundary points related to an ob-
ject. These boundary points and the objects' previous information are saved to start construc-
tion of own proposed signature for every object based on all these information. The relation
among all these information and Euclidian distance from objects' centroids ( x tc , y tc ) is plotted
and saved as an individual signature for each object, that is shown in Figure 1 by one object.
These signatures for all objects are saved and waiting for matching with any input object's sig-
nature, as in Section 5 . Moreover, the contour is drawn around all objects and tracing the ex-
terior boundaries of them.
The third part of this proposed algorithm after segmentation and constructing signatures is
the matching process between input and saved objects' signatures as in the above. Two dif-
ferent ways in matching process have used to make a comparison between them in accuracy
and activity; one is using statistical measures related to the signatures and the second is using
SURF [ 22 ] .
Additionally, all shown steps in Figure 1 have applied on the input object to construct its
signature. Actually, the matching process is depending on statistical measures on both types
 
 
Search WWH ::




Custom Search