image processing

Project presentation on

BACKGROUND DETECTION AND ENHANCEMENT OF IMAGES WITH POOR LIGHTING

  USING MORPHOLOGICAL TRANSFORMATION

Department of Electronics and communication Engineering

SREE VIDYANIKETHAN ENGINEERING COLLEGE

Sri Sainathnagar,A.Rangampet,Tirupathi-517102

Under the guidance of

Ms. H.D. PRAVEENA, M.Tech., ASSISTANT PROFESSOR Department of ECE, SVEC

ByM.Papaiah

M.Tech(DECS)RollNo:10121D3809

OUTLINE

Objective

Introduction

Existing Methods

Proposed Method

Block Diagram of proposed Method

Morphological operations

Morphological Operations on image

Detection of image background by Using Block Analysis

Simulation Results

Image background Using opening by reconstruction

References

The main objective of this project is to detect the background

image and enhance the contrast in gray level image with poor

lighting using some morphological transformations.

First operator applies information from block analysis and

second operator’s uses opening by reconstruction.

OBJECTIVE

The contrast enhancement problem in digital images occurs in many

fields like medical field, satellite imaging field, communication field

and radar imaging field.

In this poor lighting images it is difficult to know the actual information

like back ground. This work deals with the detection of background in

images with poor contrast.

Morphological transformations are used to detect the background in

images characterized by poor lighting.

Contrast image enhancement has been carried out by the application

of two operators based on the Weber’s law notion.

INTRODUCTION

EXISTING METHODS

There are number of existing systems based on the mathematical

morphological methodologies.

These existing methods are based on statistical analysis, such as the

Global & Local Histogram equalization.

The main disadvantage of histogram equalization is that the global

properties of the image can not be properly applied in local context

and producing poor performance in detail preservation.

PROPOSED METHOD

Contrast image enhancement has been carried out by the

application of two operators based on the Weber’s law notion.

The first operator employs information from block analysis, while

the second transformation utilizes the opening by reconstruction,

which is employed to define the multi-background notion.

The contrast operators consists in normalizing the grey level of the

input image with the purpose of avoiding abrupt changes in intensity

among the different regions.

the performance of the proposed operators is illustrated through the

processing of images with different backgrounds, the majority of them

with poor lighting conditions.

MATLAB simulation has to be carried out for the Proposed method

Block Diagram of Proposed Technique

Erosion

Every object pixel that is touching a background pixel is changed into a background pixel.

Erosion makes the objects smaller

  0   1   0

  1   1   1

  0   1   0

Structuring ElementOriginal Image Effect of Erosion

Morphological operations

Dilation

Every background pixel that is touching an object pixel is changed into an object pixel., and can break a single object into multiple objects.

Dilation makes the objects larger, and can merge multiple objects into one.

Effect of dilation using a 3×3 square structuring element

Opening

The opening is an erosion followed by dilation. Opening removes small islands and thin filaments of object pixels.

The opening of the dark-blue square by a disk, resulting in the light-blue

square with round corners. The opening of A by B is obtained by the

erosion of A by B, followed by dilation of the resulting image by B:

Closing

The closing operation is dilation followed by erosion. Closing removes

islands and thin filaments of background pixels.

This technique is useful for handling noisy images where some

pixels have wrong binary value.

MORPHOLOGICAL OPERATIONS ON IMAGE

(a) Original image f and marker g = Ɛ (f)

(b) original image f and marker g = δ (f)

(c) Opening by reconstruction using erosion as maker

(d) closing by reconstruction using dilation as marker

Detection of image background by using block analysis

Figure: Background condition obtained by block analysis

The image ‘f’ is divided into ‘n’ blocks

Each block is a sub image of the original image. The minimum and maximum intensity values in each sub image are denoted as

For each analyzed block, maximum and minimum values are used to determine the background criteria using

The value of represents a division line between clear f ˃ ) and dark (f < ) intensity levels. Once ( ) is calculated, this value is used to select the background parameter associated with the analyzed block.

Expression to enhance the contrast is proposed:

The background parameters depends on the value. If (f< ) (dark region). The background parameter takes the value of maximum intensity and minimum intensity for clear region.

and Maximum and minimum intensity values and expression for

and Values correspond to the morphological dilation and erosion.

Then expression for

Was substituted by

Expression for contrast operator is

SIMULATION RESULTS

Fig: Erosion operation

• qqqq

Fig: Dilation operation

------ Dilation image

Fig: Opening operation

Fig: Closing operation

(a) Original image

(b) Block analysis

(c) Output image

Image Background Using Opening by Reconstruction

In opening by reconstruction image background is detected without

dividing the original image into block and without using the

morphological erosion and dilation.

Morphological transformations generate new contours when the

structuring element is increased.

Opening by reconstruction allows the modification of the altitude of

regional maxima when the size of the structuring element increases.

The effect can be used to detect background criteria

Expression to enhance the contrast in image with poor lighting in opening by reconstruction

First, a methodology was introduced to compute an approximation to the

background using blocks analysis. This proposal was subsequently extended

using mathematical morphology operators. However, a difficulty was detected

when the morphological erosion and dilation were employed; therefore, a new

proposal to detect the image background was propounded, that is based on

the use of morphological connected transformations.

Also, morphological contrast enhancement transformations were introduced.

Such operators are based on Weber’s law notion.

CONCLUSIONS

REFERENCES[1].Z.Liu C.Zhang and Z.Zhang, “Learning –based perceptual image quality

improvement for video conferencing,” presented at the IEEE Int. conf. Multimedia and Expo (ICME), Beijing, China, Jul.2007.

[2].R.H.Sherrier and G.A.Johnson, “Regionally adaptive histogram equalization of the chest,” IEEE Trans.Med.Imag.,vol.MI-6, pp.1-7,1987.

[3].A.Majumder and S.Irani, “perception-based contrast enhancement of images,” ACM Trans.Appl.percpt.,vol.4, no.3, 2007, Article17.

[4].A.K.Jain Fundamentals of Digital Images Processing. Englewood cliffs, NJ:Prentice-Hall,1989.

[5].C.R.Gonzalez and E.Woods, Digitl Image Processing Englewood Cliffs, NJ:Prentice Hall,1992.

THANK YOU