02-05-2012, 01:11 PM
BACKGROUND DETECTION AND ENHANCEMENT OF POOR LIGHTING IMAGES USING WEBER’S LAW
BACKGROUND DETECTION AND ENHANCEMENT OF POOR LIGHTING IMAGES USING WEBER’S LAW.ppt (Size: 2.75 MB / Downloads: 101)
ABSTRACT
Some morphological transformations are used to detect the background in images characterized by poor lighting.
After that, contrast image enhancement has been carried out based on the Weber’s law notion.
Two methodologies are used to compute the background.
The first method is information from block analysis.
The second method is opening by reconstruction
EXISTING SYSTEM :
IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION METHOD
The existing method is histogram equalization method.
In the histogram equalization process, grey level intensities are reordered within the image to obtain an uniform distributed histogram.
DRAWBACKS
The main disadvantage of histogram equalization is that the global properties of the image can not be properly applied , and it produces very poor performance.
PROPOSED SYSTEM:
In this work, two methodologies to compute the image background are proposed. Lately image enhancement has been carried out. Image Enhancement is based on the logarithm function in Weber’s law . The use of the logarithm function avoids abrupt changes in lighting. The two approximations to compute the background in the processed images are proposed.
The first proposal consists in an analysis by blocks,
The second proposal, the opening by reconstruction is used given its following properties:
a) it passes through regional minima, and
b) it merges components of the image without considerably modifying other structures
ADVANTAGES:
Abrupt changes have been avoided.
Objects which are not clear in the original images can be
seen clearly.
we get good results for poor lighting images.
Morphological transformations and weber’s law
There are four morphological operations
Erosion
Dilation
Opening
Closing
By using these operations undesirable regions are eliminated.
Statement of Weber’s Law
If the luminance Lmin of an object is just noticeably different from the luminance Lmax of its surround, then their ratio is
Block Analysis:
Image will be divided into blocks
Each block is a subimage of original image
The maximum intensity value in each subimage is
determined(Mi)
Similarly Minimum intensity value in each subimage is determined(mi)
With mi and Mi the background criteria will be calculated with the following expression
where is the background of the image
Opening by Reconstruction:
No division of images into blocks and no usage of any morphological transformations.
Reason - Morphological transformations (dilation, erosion, opening ..) employs structuring element.
Increasing in the structuring element generates new contours in the image
To avoid this (new contours), another class of transformation called ‘Transformation By Reconstruction’ will be used.
Opening By reconstruction is one among them.
In the opening by reconstruction one further operation is necessary to detect the local information in the original image i.e; morphological erosion operation