Hai, we meet again in this new post..
In conjunction with Labor Day next week, Image Processing class has been cancelled. But, our lovely lecturer has an ASSIGNMENT for us on that HOLIDAY.
Thus, in this post, we gonna discuss about REGION SEGMENTATION.
What is a Region?
- Basic definition : a group of connected pixels with similar properties.
- Important in interpreting an image because they may correspond to objects in a scene.
- For correct interpretation, image must be partitioned into regions that correspond to objects or parts of an object.
What is Segmentation?
- Another way of extracting and representing information from an image is to group pixels together into regions of similarity.
- If an image has been preprocessed appropriately to remove noise and artifacts, segmentation is often the key step in interpreting the image.
- Image segmentation is a process in which regions or features sharing similar characteristics are identified and grouped together.
- Image segmentation may use statistical classification, thresholding, edge detection, region detection, or any combination of these techniques.
- The output of the segmentation step is usually a set of classified elements.
- Most segmentation techniques are either region-based or edge-based.
- Edge-based techniques rely on discontinuities in image values between distinct regions, and the goal of the segmentation algorithm is to accurately demarcate the boundary separating these regions.
- Region-based techniques rely on common patterns in intensity values within a cluster of neighboring pixels.
- The cluster is referred to as the region, and the goal of the segmentation algorithm is to group regions according to their anatomical or functional roles.
- Important principles:-
- Value similarity - Gray value differences
- Spatial Proximity - Euclidean distance
- Region-based segmentation methods attempt to partition or group regions according to common image properties. These image properties consist of :
- Gray value variance
- Compactness of a region
- Intensity values from original images, or computed values based on an image operator
- Textures or patterns that are unique to each type of region
- Spectral profiles that provide multidimensional image data
- Elaborate systems may use a combination of these properties to segment images, while simpler systems may be restricted to a minimal set on properties depending of the type of data available.
- There are three basic approaches to segmentation:
- Region Merging - recursively merge regions that are similar.
- Combine regions considered similar based on a few region characteristics.
- Determining similarity between two regions is most important step.
- Approaches for judging similarity based on:
- Gray values
- Color
- Texture
- Size
- Shape
- Spatial proximity and connected
- Region Splitting - recursively divide regions that are heterogeneous.
Original image Region Merging
Original image Region Merging
Original image Region Splitting
- The opposite approach to region growing is region splitting.
- It is a top-down approach and it starts with the assumption that the entire image is homogeneous
- If this is not true, the image is split into four sub images
- This splitting procedure is repeated recursively until we split the image into homogeneous regions
- If the original image is square N x N, having dimensions that are powers of 2(N = 2n)
- All regions produced but the splitting algorithm are squares having dimensions M x M, where M is a power of 2 as well.
- Since the procedure is recursive, it produces an image representation that can be described by a tree whose nodes have four sons each.
- Such a tree is called a Quad tree.
- The disadvantage, they create regions that may be adjacent and homogeneous, but not merged.
- Split and merge - iteratively split and merge regions to form the “best” segmentation.
Original image Split and merge
Original image Split and merge
- If a region R is inhomogeneous (P(R)= False) then is split into four sub regions
- If two adjacent regions Ri,Rj are homogeneous (P(Ri U Rj) = TRUE), they are merged The algorithm stops when no further splitting or merging is possible
- The split and merge algorithm produces more compact regions than the pure splitting algorithm
What is Quad Tree?
Definition:
A quad tree is a tree whose nodes either are leaves or have 4 children. The children are ordered 1, 2, 3, 4.
Strategy:
- The strategy behind using quad trees as a data structure for pictures is to "Divide and Conquer".
- Let's divide the picture area into 4 sections. Those 4 sections are then further divided into 4 subsections. Then continue this process, repeatedly dividing a square region by 4.
- It is important to set a limit to the levels of division otherwise we could go on dividing the picture forever. Generally, this limit is imposed due to storage considerations or to limit processing time or due to the resolution of the output device.
- A pixel is the smallest subsection of the quad tree.
- To summarize, a square or quadrant in the picture is either:
- In terms of a quad tree, the children of a node represent the 4 quadrants. The root of the tree is the entire picture.
- To represent a picture using a quad tree, each leaf must represent a uniform area of the picture. If the picture is black and white, we only need one bit to represent the color in each leaf; for example, 0 could mean black and 1 could mean white.
- Note that no node may allow all its descendants to have the same color. A minimum level of division must be maintained.
a. entirely one color
b. composed of 4 smaller sub-squares
What is 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
| Property |
Control Type: Options
|
The method used to select pixels that are similar to the current selection. Choose from these values:
By threshold: The expanded region includes neighboring pixels that fall within the range defined by the Threshold minimum and Threshold maximum values.
By standard deviation: The expanded region includes neighboring pixels that fall within the range of the mean of the region's pixel values plus or minus the given multiplier times the sample standard deviation as follows:
Mean +/- StdDevMultiplier * StdDev
where Mean is the mean value of the selected pixels, StdDevMultiplier is the value specified by the Standard Deviation Multiplier property, and StdDev is the standard deviation of the selected pixels.
Default = By threshold
|
|
Specifies which pixels should be considered during region growing. Four-neighbor searching searches only the neighbors that are exactly one unit in distance from the current pixel; Eight-neighbor searching searches all neighboring pixels.
Choose from these values:
4-neighbor
8-neighbor
Default = 4-neighbor
|
|
Specifies the threshold values to use. Choose from these values:
Source ROI/Image threshold: Base the threshold values on the pixel values in the currently selected region.
Explicit: Specify the threshold values using the Threshold minimum and Threshold maximum properties.
Default = Source ROI/Image threshold
|
|
The explicitly specified minimum threshold value. Default = 0
|
|
The explicitly specified maximum threshold value. Default = 256
|
|
The number of standard deviations to use if the region growing method is By standard deviation. Default = 1
|
|
If the image has separate color channels, use the selected channel when growing the region. Choose from these values:
Luminosity: Luminosity values
Red Channel: Red values
Green Channel: Green values
Blue Channel: Blue values
Alpha Channel: Transparency values
Default = Luminosity
|
References:
