Object Detection By Global Contour Shape

8/3/2019 Object Detection By Global Contour Shape

1/27

Presented by

S Raghavender

B080520CS


2/27

Introduction The aim of this work is to investigate the potential of

global shape as a cue for object detection andrecognition.

This was the research done in two fields, digital imageprocessing and pattern recognition.

This is method for object class detection in images

based on global shape. If an image is given we have to find the objects that are

in that image comparing it with given templates.


3/27

ExampleTemplate Object found in the image


4/27

Basic Steps used in a Normal

method

RGB to gray conversion

Filtering the image Thresholding

Edge detection

Recognition of connected components

Correlating the component with a template.


5/27

RGB to gray conversion In this step a RGB (color) image is converted to a gray

scale image using following formula.

I = 0.3R + 0.59G + 0.11BA gray scale (mxn pixels)image is represented using a

two dimensional matrix (mxn size)

A RGB image (mxn pixels)is represented using a three

dimensional matrix (mxnx3 size)


6/27

Example RGB to Gray scale

RGB Image Gray scale image


7/27

Filtering the imageAn image is filtered to remove noises present in the

image.

There are many types of filtersMedian filter

Low pass filter

High pass filter

Band pass filter


8/27

Example of filtering

Noisy Image Filtered Image


9/27

Thresholding Thresholding is a technique which divides the image

in to different segments depending on the intensity ofthe color at that point. A threshold may have differentintensities.

If there are only 2 intensities then they will be balckand white.

Thresholding is done based on the calculatedthreshold value of the image.


10/27

Edge Detection In the stage of edge detection all the edges that are

present in the image are found.

There are different types of operators to find the edgesin the given image.

Example :

Sobel Operator

Laplacian operator


11/27

Example edge detection


12/27

Recognition of connected

components Finding the connected components deals with finding

different objects that are present in the given image.

There different types of algorithms available forfinding the connected components.


13/27

Correlation Correlation of the connected components with

template image deals with resizing the image totemplate size and matching the image with differenttemplates and finding the most matching templatefrom the set of the templates.

Here we have to mainly deal with finding the contour(shape) of the given object and match it with thetemplate image and find the corresponding object.


14/27

Disadvantages of above method Cannot detect the object if it is in different angle.

Template should match properly with the object.

Cannot find the objects which are oriented in differentway.


15/27

Detection by contour matchingThe major steps involved in object detection are

Segmentation

Finding the shape model Matching the shape

Computing space distance

Detecting objects


16/27

Segmentation vs. Edge detection The first step towards shape-based object detection is

to extract potential object contour points from theinput image, which then are compared to a shapetemplate.

The short-comings of this basic edge detection hasbeen one of the major difficulties for shape-basedobject detection.

An example of segmentation is

Statistical Region Merging


17/27

Example : Segmentation


18/27

Shape ModelA shape X is approximated by a closed polygon with a

fixed number of equally spaced vertices N. Since thepoints are equally spaced, the sequence of points canbe parametrised by an integer arc length:X={x(u),u=0,,N-1}.

The last vertex coincides with the first one forcomputational simplicity: x(N)=x(0).

To dive the shape of the curvatures a method is used inwhich tangents are drawn to every point and matchedwith the corresponding shapes.


19/27

Matching shapes Given are two shapes X and Y, one for the shape

template, and one for a candidate contour extractedfrom a test image.

A matching between the two shapes is a function,which associates the point sets {x(u)} and {y(v)} (bothparametrised by their arc length), such that each pointon either curve has at least one corresponding point onthe other curve.


20/27

Matching Shape (contd..) To achieve a rotation of contour X relative to contour Y,

the tangent angles x(u) have to be shifted in a circularmanner, and then re-normalised such that x(0)=0 forthe new starting point.


21/27

Computing shape distance This is used for comparing the objects or connected

components with templates.


22/27

Detecting Objects The nonlinear elastic matching distance is a measure

for the similarity between two contours.

Any group of neighboring super-pixels forms a closedcontour, and the combinatorial set of all such contoursis the search space for object detection.

If the shape of segments and distance between them

matches with that of template then object is detected. Since correlation is based on probability the results

may not be 100% accurate.


23/27

Experimental resultsA collection of four diverse object classes are used,

which have in common that they are mainly definedby their global shape, while they have either little

texture at all, or strongly varying texture.

In a detailed experimental evaluation, it has beenshown to outperform previous methods, and hasachieved a detection rate of 91%.


24/27

Example


25/27


26/27

References1. Konard Schindler, David Suter, Obect detection by

global contour matching.

2. R. Nock and F. Nielsen, Statistical region merging.IEEE Trans. Pattern Anal. Mach. Intell.,26 11 (2004),pp. 14521458.

3. L.J. Latecki and R. Lakmper, Shape similarity

measure based on correspondence of visual parts. IEEETrans. Pattern Anal. Mach. Intell.,22 10

4. Wikipedia


27/27

Object Detection By Global Contour Shape

Documents