Contour Detection My Ppt (1)

CONTOUR DETECTION in Computer Vision

Presented By

T.LAHARI V.ANEESHA

III/IV BTECH III/IV BTECH

IT IT

[email protected] [email protected]

Ph: 9347526507 Ph: 9703251812

V.R.SIDDHARTHA ENGINEERING COLLEGE(AUTONOMOUS)

VIJAYAWADA

ABSTRACT:

Computer vision is a scientific discipline, concerned with the theory behind artificial systems that extract information from images. The fields most closely related to computer vision are image processing, image analysis and machine vision. Image analysis is the extraction of meaningful information from images; mainly from digital images by means of digital image processing techniques.

INTRODUCTION

Definition:

The term Contour can be defined as an outline or a boundary of an object. Hence, Contour detection deals with detecting various objects in an image specifically. Use of contour detection in image processing is to locate objects and their boundaries in images.

Contour detection and Edge detection:

In general, contour detection follows edge detection, which is a process of identifying points in a digital image at which the image brightness changes sharply. The main difference between edge detection and contour detection is that in edge detection, edges are drawn based on intensity variations from pixel-to-pixel where as contours are salient region boundaries in an image. Hence, specific identification of objects is possible only through contours.

Outputs of Edge detection

Outputs of the Contour detection

The output of edge detection includes every small edge in the input image and this gives rise to confusion in detecting the individual objects specifically. So, this output is further analysed by removing the unimportant lines and noises and showing only the important edges which help in the extraction of meaningful information from that image. In the above examples we can see that the outputs of edge detection include every small edge and hence it is not possible to deduce some information like the number of animals in the image and the exact shapes of the individual objects due to many unimportant small edges, where as in the outputs of the contour detection, these unwanted unimportant edges are removed and only the salient region boundaries are shown, which give all the information about the objects in the image.

CONTOUR LINES

Contour lines are the lines joining points of equal elevation (height) above a given level. These are used in the construction of Contour maps, which show valleys and

hills, and the steepness of slopes. The contour interval of a contour map is the difference in elevation between successive contour lines.

APPLICATIONS of CONTOUR LINES:

Meteorological contour maps  may present collected data such as actual air pressure at a given time, or generalized data such as average pressure over a period of time, or forecast data such as predicted air pressure at some point in the future.

In Oceanography, contours are used as isobathytherms, lines showing depths of water with equal temperature, isohalines, lines of equal ocean salinity and Isopycnals, which are surfaces of equal water density.

Contour lines are used in Topography to study various factors like the number of mountain peaks in a region, the height of these peaks, and the shapes of islands can also be determined using these contours.

Contour lines are drawn by joining points which are at same height from the sea level. This helps in estimating the height of a peak accurately. Also by viewing the same contour map in the top view, we can determine the exact shape of the regions or islands based on the contour lines along with the number of peaks in that region. When there are less number of points of equal elevation located closely, they form smaller circles on the contour maps, these are nothing but mountain peaks. In the same way, the steep slopes can be identified as the closely located contour lines which almost overlap each other.

Contour Detection:

There are currently two main types of active contours:1) Parametric active contours, which represent contours explicitly as parameterized curves and 2) Geometric active contours, which represent contours implicitly as level sets oftwo-dimensional scalar functions.

SNAKE CONOTURS:

Snake is an energy minimizing, deformable spline influenced by constraint and image forces that pull it towards object contours. Snakes are greatly used in applications like object tracking, shape recognition, segmentation, edge detection, stereo matching.

geodesic: The shortest line between two points (on a mathematically defined surface). 

geodesic active contour: An active contour model similar to the snake model in that it attempts to minimize an energy function between the model and the data, but which also incorporates a geometrical model.

geodesic active region: A technique for region based segmentation that builds on geodesic active contours by adding a force that takes into account information within regions. Typically a geodesic active region will be bounded by a single geodesic active contour.

geodesic distance: The length of the shortest path between two points along some surface. This is different from the Euclidean distance that takes no account of the surface. The following example shows the geodesic distance between Calgary and London (following the curvature of the Earth).geodesic transform: Assigns to each point the geodesic distance to some feature or class of feature.