Ppt

IMAGE SEGMENTATION

INTRODUCTION APPLICATIONS CLASSIFICATION

WHAT IS IMAGE SEGMENTATION ??

Segmentation refers to the process of partitioning a digital Image into multiple segments (sets of pixels, also known as super pixels).

More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics.

The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze.

BEFORE

AFTER

BEFORE AFTER

BEFORE AFTER

BEFORE AFTER

APPLICATIONS

MEDICAL IMAGING

BIOMETRICS APPLICATIONS

AGRICULTURAL IMAGING

LOCATE OBJECTS IN SATELLITE IMAGES

3-D IMAGING

TRAFFIC CONTROL SYSTEMS, ROBOTICS

MEDICAL IMAGING

Locate tumors and other pathologies

Measure tissue volumes

Computer-guided surgery

Diagnosis

Treatment planning

Study of anatomical structure

MEDICAL

IMAGING

BIOMETRICS APPLICATIONS

FACE RECOGNITION SYSYTEMS

A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. One of the ways to do this

is by comparing selected facial features from the image and a facial database.

It is typically used in security systems and can be compared to other biometrics

such as fingerprint or eye iris recognition systems.

AGRICULTURAL IMAGING

With increasing population pressure throughout the world

and the need for increased agricultural production

there is a definite need for improved management of the world's agricultural resources.

To make this happen it is first necessary to obtain

reliable data on not only the types, but also the quality, quantity and location of these resources..

LOCATE OBJECTS IN SATELLITE IMAGES

Image segmentation is an important task in image processing and analysis.

Many segmentation methods have been used to segment satellite images.

The success of each method depends on the characteristics of the acquired

image such as resolution limitations and on the percentage of imperfections in the process of image acquisition due to noise.

Some of them are parametric statistical methods that use many parameters

which are dependent on image property.

A basic task in 3-D image processing is the segmentation of

an image which classifies voxels/pixels into objects or groups.

3-D image segmentation makes it possible to create 3-D rendering for multiple objects and perform quantitative analysis for the size, density and other parameters of detected objects.

3D – IMAGING

TRAFFIC CONTROLLING, ROBOTICS

Image Segmentation is being widely used by most of the traffic systems these days. Basically it plays a great role in controlling the level of traffic on specific routes and thereby accordingly managing the traffic.

Image segmentation is also being used in the field of robotics. The robots are

programmed to extract the image of interest from the data available and send the information about that situation.

TYPES OF IMAGE SEGMENTATION

IMAGE SEGMENTATIONHISTOGRAM

EDGE DETECTION

CLUSTERING

REGION GROWING

SPLIT & MERGE

HISTOGRAM METHOD

In this technique , a histogram is computed from all the pixels in the image, and the peaks and valleys in the histogram are used to locate the clusters in the image, colour and intensity can be used as a measure.

Vertical axis: Frequency (i.e., pixel counts for each bin)

Horizontal axis: Response variable

EDGE DETECTION METHOD

The edge represents the step changes in the intensity values of adjacent pixels.

Detects abrupt change in image features within a small neighborhood.

Identifying & locating sharp discontinuities in an image.

It is used to obtain information from the frames for feature

extraction and object segmentation.

EDGE DETECTION METHOD

Derivative approach

The backbone of many algorithms is the discrete approximation of derivative operations representing the significant gradient of intensity (edge).

First order derivative Second order derivative

CLUSTERING METHOD

Clustering is basically grouping together pixels that have similar properties such as color, texture, motion, etc

Each pixels can be treated as a data point in the feature space

An image will be represented in terms of clusters of pixels that belong together

The specific criterion to be used depends on the application

Pixels may belong together because they have the same color, same texture, they are nearby, and so on.

CLUSTERING METHOD

Some clustering algorithms:

DIVISION CLUSTERING:the entire dataset is considered as a cluster, and then

clusters are recursively split to yield good clustering

AGGLOMERATIVE CLUSTERING: each data point is considered as a clustered, then clusters

are recursively merged to yield good clustering.

K-MEANS CLUSTERING: grouping the dataset into K clusters center locations

SEGMENTATION BY CLUSTERING – KMEANS

KMEANS: ITERATIVE ALGORITHM

1. Initialisation: ◮ choose K

◮ randomly guess K cluster center locations

2. Allocation: each data point finds out which center it is closest to, and is assigned to the corresponding cluster

3. Center calculation: recompute the cluster centres by averaging all the pixels in the cluster.

4. Repeat 2-3 until terminated (centers do not move any more)

SEGMENTATION BY CLUSTERING

SEGMENTATION BY CLUSTERING

SEGMENTATION BY CLUSTERING – KMEANS RESULTS

INFLUENCE OF THE CHOICE OF K

REGION GROWING

A simple approach to image segmentation is to start from some pixels (seeds) representing distinct image regions and to grow them, until they cover the entire image.

For region growing we need a rule describing a growth mechanism and a rule checking the homogeneity of the regions after each growth step.

This method starts at the root of the tree that represents the whole image. If it is found non-uniform (not

homogeneous), then it is split into four son-squares (the splitting process), and so on so forth.

Conversely, if four son-squares are homogeneous, they can be merged as several connected components (the

merging process).

SPLIT AND MERGE METHOD

Split-and-merge segmentation is based on a quadtree partition of an image. It is sometimes called quadtree

segmentation.

QUADTREE

R0 R1

R2R3

R0

R1

R00 R01 R02 R04

Split and Merge method is an iterative algorithm that includes both splitting and merging at each iteration.

RESULTS – REGION GROW

RESULTS – REGION SPLIT

RESULTS – REGION SPLIT AND MERGE

CONCLUSION THUS WE HAVE SEEN THE VARIOUS APPLICATIONS AND

METHODS OF IMAGE SEGMENTATION. THE PURPOSE OF VARIOUS METHODS IS THE SAME THAT IS IMAGE SEGMENTATION BUT THE APPROACH IS SOMEWHAT DIFFERENT.

WE HAVE SEEN THE VARIOUS APPLICATIONS OF IMAGE SEGMENTATION IN VARIOUS FIELDS. THOUGH DIRECTLY WE

CANNOT OBSERVE THE USE OF THIS TECHNIQUE BUT IN ONE WAY OR THE OTHER IT IS BEING EXTENSIVELY USED IN

VARIOUS FIELDS STARTING FROM MEDICAL TO THE TRAFFIC, AGRICULTURE AND SO ON.

SO WE CAN SAY THAT IMAGE SEGMENTATION FINDS A LOT OF APPLICATION IN VARIOUS FIELDS AND VARIOUS

RESEARCHES AND EXPERIMENTS ARE GOING ON THIS TECHNIQUE FOR ITS BETTER, SCIENTIFIC AND IMPROVED APPROACH..