Image classification md. yousuf gazi

Md. Yousuf Gazi, Lecturer, Department of Geology, University of Dhaka (yousuf.geo@du.ac.bd)
Image Classification

▪ The process of sorting pixels into a finite
number of individual classes, or categories
of data, based on their spectral response
(the measured brightness of a pixel across
the image bands, as reflected by the pixel’s
spectral signature).

The underlying assumption of image classification is that spectral response of a
particular feature (i.e., land-cover class) will be relatively consistent throughout the
image.
General Approaches to Image Classification
1. Unsupervised
2. Supervised

Unsupervised Classification
• Unsupervised classification (a.k.a., “clustering”) identifies groups of pixels that exhibit a
similar spectral response
• These spectral classes are then assigned “meaning” by the analyst (e.g., assigned to land-cover
categories)

Supervised Classification
Supervised classification uses image pixels representing regions of known, homogenous surface
composition -- training areas -- to classify unknown pixels.

Unsupervised: bulk of analyst’s work comes after
the classification process
Supervised: bulk of analyst’s work comes before the
classification process

Advantages
▪ No prior knowledge of the image area is required
▪ Human error is minimized
▪ Unique spectral classes are produced
▪ Relatively fast and easy to perform
Advantages and Disadvantages of Unsupervised Classification

Disadvantages of Unsupervised Classification
▪ Spectral classes do not represent features on the ground
▪ Does not consider spatial relationships in the data
▪ Can be very time consuming to interpret spectral classes
▪ Spectral properties vary over time, across images

Process of Unsupervised Classification
1. Determine a general classification scheme
2. Assign pixels to spectral classes (ISODATA)
3. Assign spectral classes to informational classes

• Depends upon the purpose of the classification
• With unsupervised classification, the scheme does not need to be very specific

• Group pixels into groups of similar values based on pixel value relationships in multi-
dimensional feature space (clustering)
• Iterative ISODATA technique is the most common

▪ Once the spectral clusters in the image are identified, the analyst must assign them to the
“informational” classes of the classification scheme (i.e., land cover)

Example: Image to be Classified Example: Image to be Classified
▪ Multiple clusters likely
represent a single type of
“feature” on the ground.
▪ Someone needs to assign a
landcover class to all of these
clusters; can be difficult and
time consuming.

Supervised classification uses image pixels
representing regions of known, homogenous surface
composition -- training areas -- to classify unknown
pixels.

The underlying assumption is that spectral
response of a particular feature (i.e., land-cover
class) will be relatively consistent throughout
the image.

Advantages
▪ Generates informational classes representing features on the ground
▪ Training areas are reusable (assuming they do not change; e.g. roads)

Disadvantages
▪ Information classes may not match spectral classes
(e.g., a supervised classification of “forest” may mask the
unique spectral properties of pine and oak stands that
comprise that forest)
▪ Homogeneity of information classes varies
▪ Difficulty and cost of selecting training sites
▪ Training areas may not encompass unique spectral
classes

Process of Supervised Classification
1. Determine a classification scheme
2. Create training areas
3. Generate training area signatures
4. Evaluate and refine signatures
5. Assign pixels to classes using a classifier (a.k.a., “decision rule”)

1 | Determine Classification Scheme
• Depends upon the purpose of the classification
• Make the scheme as specific as resources and available reference data allow
You can always generalize your classification scheme to make it less specific; making
it more specific involves starting over

2 | Create Training Areas
▪ Digitizing: drawing polygons around areas in the image
▪ Seeding: “grows” areas based on spectral similarity to seed pixel
▪ Using existing data: existing maps, field data (GPS, etc.), high-resolution imagery
▪ Feature space image training areas

Image classification md. yousuf gazi

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Image classification md. yousuf gazi

Similar to Image classification md. yousuf gazi (9)

More from Md. Yousuf Gazi

More from Md. Yousuf Gazi (18)

Recently uploaded

Recently uploaded (20)

Image classification md. yousuf gazi