Skip to main content

Supervised Classification

In the context of Remote Sensing (RS) and Digital Image Processing (DIP), supervised classification is the process where an analyst defines "training sites" (Areas of Interest or ROIs) representing known land cover classes (e.g., Water, Forest, Urban). The computer then uses these training samples to teach an algorithm how to classify the rest of the image pixels.

The algorithms used to classify these pixels are generally divided into two broad categories: Parametric and Nonparametric decision rules.


Parametric Decision Rules

These algorithms assume that the pixel values in the training data follow a specific statistical distribution—almost always the Gaussian (Normal) distribution (the "Bell Curve").

  • Key Concept: They model the data using statistical parameters: the Mean vector ($\mu$) and the Covariance matrix ($\Sigma$).

  • Analogy: Imagine trying to fit a smooth hill over your data points. If a new point lands high up on the hill, it belongs to that class.

Nonparametric Decision Rules

These algorithms make no assumptions about the statistical distribution of the data. They do not care if the data fits a bell curve.

  • Key Concept: They classify based on discrete geometric shapes (polygons, boxes) or the relative position of the data points themselves.

  • Analogy: Imagine drawing a literal box or fence around your data points. If a new point falls inside the fence, it belongs to that class.


A. Minimum-Distance-to-Means (MDM)

  • Classification: Generally considered a simple Parametric classifier (as it relies on the mean parameter), though it operates geometrically.

  • How it works:

    1. The algorithm calculates the spectral mean vector (the center point or centroid) for each training class.

    2. For every unclassified pixel in the image, it calculates the Euclidean distance to the mean of every class.

    3. The pixel is assigned to the class with the shortest distance.


  • Pros: Very fast computationally; mathematically simple.

  • Cons: It is insensitive to the variance (spread) of the data.

    • Example: If "Urban" data is very scattered (high variance) and "Water" is very tight (low variance), a pixel far from the Urban center might actually belong to Urban, but MDM might classify it as Water just because the Water mean is slightly closer geometrically.

B. Parallelepiped Classification

  • Classification: Nonparametric.

  • How it works:

    1. The algorithm looks at the training data and finds the minimum and maximum brightness values for each band.

    2. It creates a rectangular box (a parallelepiped in multi-dimensional space) defined by these limits.

    3. If a pixel's value falls within the box, it is assigned to that class.

  • Pros: Extremely fast; easy to understand conceptually.

  • Cons:

    • The Correlation Problem: Real remote sensing data (like vegetation in Red vs. NIR bands) is often correlated (diagonal distribution). A rectangular box cannot fit a diagonal data cloud efficiently, leading to large "empty corners" in the box that capture noise/wrong pixels.

    • Overlapping: Pixels often fall into the overlapping area of two boxes, leaving the computer unable to decide.

C. Gaussian Maximum Likelihood (GML/MLC)

  • Classification: Parametric (The standard industry workhorse).

  • How it works:

    1. It assumes the data for each class is normally distributed.

    2. It uses both the Mean vector AND the Covariance matrix to calculate the probability density function.

    3. It calculates the statistical probability of a pixel belonging to each class.

    4. It constructs ellipsoidal equiprobability contours (rather than circles or boxes).

  • Pros: Highly accurate because it accounts for the variance (spread) and covariance (correlation/direction) of the data. It handles "diagonal" data clouds perfectly.

  • Cons: Computationally expensive (slow on massive images); requires a large number of training pixels per class to compute a stable covariance matrix (usually $10N$ to $100N$ pixels, where $N$ is the number of bands).


FeatureParallelepipedMinimum DistanceMaximum Likelihood
TypeNonparametricParametric (Simple)Parametric (Advanced)
GeometryRectangular BoxesCircles/SpheresEllipsoids
AssumptionsNone (Min/Max thresholds)Mean Center PointGaussian Distribution
SpeedVery FastFastSlow / Intensive
AccuracyLow to ModerateModerateHigh
Best Used ForQuick looks; Uncorrelated dataWell-separated classesComplex, correlated data


Comments

Post a Comment

Popular posts from this blog

CREATION OF SPATIAL DATA

Spatial data creation is the process of generating, organizing, and managing geographically referenced information in a Geographic Information System (GIS). It involves converting maps, satellite images, GPS observations, and field survey data into digital datasets that can be stored, analyzed, and visualized. The quality of GIS analysis depends largely on the accuracy of spatial data creation. 1. Creation of Shapefile and Geodatabase A. Shapefile A Shapefile is one of the most widely used vector data formats developed by Esri for storing geographic features. Definition A shapefile stores the geometry and attributes of geographic features such as points, lines, and polygons. Components of a Shapefile A shapefile consists of several files: .shp – Stores geometry (shape) .shx – Shape index .dbf – Attribute table .prj – Coordinate Reference System (CRS) .sbn/.sbx – Spatial index (optional) Geometry Types Point – W...
Post a Comment
Read more

Nature and Scope of Geography

Geography is the scientific study of the Earth's surface, its physical features, human populations, and the interactions between people and their environment. The word Geography is derived from the Greek words Geo (Earth) and Graphien (to describe or write), meaning "description of the Earth." Modern geography goes far beyond description; it seeks to explain where phenomena occur, why they occur there, how they are spatially distributed, and how they change over time. Geography is regarded as a spatial science , an environmental science , and an integrative discipline because it bridges natural sciences, social sciences, and geospatial technologies. Nature The nature of geography refers to the characteristics and fundamental features that define the discipline. 1. Geography as a Spatial Science Terminology: Spatial Science A discipline concerned with the location, distribution, arrangement, organization, and interaction of phenomena in ...
Post a Comment
Read more

Geography of Health or Medical Geography

Health Geography (also known as Medical Geography ) is a sub-discipline of Human Geography that studies the relationships between place, environment, society, and health . It examines how spatial location, environmental conditions, and social and economic factors influence human health, disease patterns, and access to healthcare services. Health geography integrates concepts from geography, epidemiology, medicine, public health, environmental science, sociology, and Geographic Information Systems (GIS) to understand and improve population health. Major Components of Health Geography Health geography is generally divided into two major branches : The Geography of Disease and Ill Health The Geography of Health Care 1. The Geography of Disease and Ill Health This branch studies the spatial distribution, determinants, and diffusion of diseases across different geographical scales, from neighborhoods to global regions. It seeks t...
Post a Comment
Read more

Historical Development of Geography in the Ancient Period

The Ancient Period marks the earliest stage in the evolution of geographical thought, extending from approximately 3000 BCE to the 5th century CE . During this period, geography evolved from simple descriptions of the Earth's surface to systematic scientific inquiry. Early civilizations developed geographical knowledge to meet practical needs such as navigation, trade, agriculture, military expansion, taxation, and administration . The greatest contributions came from the Mesopotamian, Egyptian, Indian, Chinese, Greek, and Roman civilizations , with the Greeks laying the foundations of scientific geography . Meaning Terminology: Historical Development Historical development refers to the gradual evolution of geographical knowledge, concepts, methods, and theories over time. Concept Geographical knowledge evolved through: Observation of the natural environment Exploration and travel Cartography (map-making) Astronomical observations ...
Post a Comment
Read more

Development of Health Geography

Health Geography (formerly Medical Geography ) is the branch of geography that studies the relationship between health, disease, environment, place, and healthcare systems . The discipline has evolved over more than 2,500 years through contributions from physicians, geographers, epidemiologists, microbiologists, and public health experts. The development of Health Geography can be divided into the following periods: Ancient Period Medieval Period Renaissance and Pre-Modern Period Nineteenth Century (Pre-World War Era) World War Period Post-World War Period Modern Health Geography 1. Ancient Period (5th Century BC – 500 AD) Characteristics Health closely linked with the natural environment. Diseases explained through climate, water, air, and seasons. No knowledge of microorganisms. Medical observations were descriptive. Major Concepts Environmental Determinism Disease Ecology Climate and Healt...
Post a Comment
Read more