Di it l I P i A R t S i P tiDigital Image Processing: A Remote Sensing PerspectiveFW5560Lecture 16 Expert Classification.A knowledge-based expert system is defined as: “ttht h kldtl bl“a system that uses human knowledge to solve problems that normally would require human intelligence”.It is the ability to “solve problems efficiently and effectively in a narrow problem area” and “to perform at the level of an expert”Expert systems represent the expert’sdomain(ieexpert. Expert systems represent the expert s domain (i.e., subject matter) knowledge base as data and rules within the computer.The expert classification software provides a rules-basedapproach to multispectral image classification postapproach to multispectral image classification, post-classification refinement, and GIS modeling.In essence, an expert classification system is a hierarchy of rules, or a decision tree, that describes the conditions under which a set of low levelconstituent information getsabstracted into a set of highlevel informational classeslevel informational classes.The constituent information consists of user-defined ibl di ld t i tvariables and includes raster imagery, vector coverages, spatial models, external programs, and simple scalars.A rule is a conditional statement, or list of conditional statements, about the variable’s data values and/or attributes that determine an informational component orattributes that determine an informational component or hypotheses.M lti l l d h th b li k d t th i tMultiple rules and hypotheses can be linked together into a hierarchy that ultimately describes a final set of target informational classes or terminal hypotheses. ypConfidence values associated with each condition arealso combined to provide a confidence imagealso combined to provide a confidence image corresponding to the final output classified image.30 30 ×× 30 USGS DEM30 USGS DEM Shaded ReliefShaded Relief ContoursContours SlopeSlope AspectAspectETM PanchromaticETM Panchromatic ETM RGB = 5,4,2ETM RGB = 5,4,2 ETM RGB = 4,3,2ETM RGB = 4,3,2 ETM NDVIETM NDVIKnowledge representation process involves encoding information from verbal descriptions rules of thumbinformation from verbal descriptions, rules of thumb, images, books, maps, charts, tables, graphs, equations, etc. Hopefully, the knowledge base contains sufficient high-quality rules to solve the problem under investigation.A typical remote sensing rule might be: IF blue reflectance is (Condition) < 15%IF blue reflectance is (Condition) < 15% AND green reflectance is (Condition) < 25% AND red reflectance is (Condition) < 15%AND near‐infrared reflectance is (Condition) > 45% THEN there is strong suggestive evidence (0.8) that the pixel is vegetated.p gRules are normally expressed in the form of one or more “IF condition THEN action” statements. The conditionportion of a rule statement is usually a fact, e.g., theportion of a rule statement is usually a fact, e.g., the pixel under investigation must reflect > 45% of the incident near-infrared energy. When certain rules are applied various operations may take place such asapplied, various operations may take place such as adding a newly derived derivative fact to the database or firing another rule. Rules can be implicit (slope is high) or explicit (e.g., slope > 70%). It is possible to chain together rules, e.g., IF c THEN d; IF d THEN e; therefore IF c THEN e. It is also possible to attach pconfidences (e.g., 80% confident) to facts and rules.Heuristic Knowledge-based Expert System Approaches to Problem SolvingApproaches to Problem SolvingKnowledge-based expert systems collect many small fragments of human knowhow for a specific applicationfragments of human know-how for a specific application area (domain) and place them in a knowledge base that is used to reason through a problem, using the knowledge that is most appropriate.Heuristic knowledge is defined as “involving or serving as an aid to learning, discovery, or problem solving by e perimental and especiall b trialanderror methodsexperimental and especially by trial-and-error methods. Heuristic computer programs often utilize exploratory problem-solving and self-educating techniques (as the evaluation of feedback) to improve performance”.Decision TreesThe best way to conceptualize an expert system is to useThe best way to conceptualize an expert system is to use a decision-tree structure where rules and conditions are evaluated in order to test hypotheses.When decision trees are organized with hypotheses, rules, and conditions, each hypothesis may be thoughtrules, and conditions, each hypothesis may be thought of as the trunk of a tree, each rule a limb of a tree, and each condition a leaf. This is commonly referred to as ahierarchical decisiontree classifiera hierarchical decision-tree classifierThe purpose of using a hierarchical structure for labeling objects is to gain a more comprehensive understanding of relationships among objects at different scales of observation or at different levels of d e e sca es o obse a o o a d e e e e s odetail.A humanderived decisiontree expert system with a rule andA human‐derived decision‐tree expert system with a rule and conditions to be investigated by an inference engine to test Hypothesis 1: the terr ain (pixel) is suitable for residential development that makes maximum use of solar energy (i.e., I will be able to put solar panels on my roof ).An Expert Classifier is composed of two parts:pppKnowledge Engine and the Knowledge Classifier. The Knowledge Engine provides the interface for an expert with first-hand knowledge of the data and the application to id tif th i bl l d t t l f i t tidentify the variables, rules, and output classes of interest and create the hierarchical decision tree.The Knowledge Classifier provides an interface for anonexpert to apply the knowledge base and create the output classificationoutput classification.Th K l d i i t t th l i thThe Knowledge engine interprets the rules in the knowledge base to draw conclusions. The inference engine may use backward- or forward-chaining gygstrategies or both. Both backward and forward inference processes consist of a chain of steps that can be traced by the expert systembe traced by the expert system.This