Fuzzy logic (FL) and case-based reasoning (CBR) are two well-known techniques for the implementation of intelligent classification systems. Each technique has its own advantages and drawbacks. FL, for example, provides an intuitive user interface, simplifies the process of knowledge representation, and minimizes the system’s computational complexity in terms of time and memory usage. On the other hand, FL has problems in knowledge elicitation which render it difficult to adopt for intelligent system implementation. CBR avoids these problems by making use of past input–output data to decide the system output for the present input. The accuracy of CBR system grows as the number of cases increase. However, more cases can mean added computational complexity in terms of space and time. In this paper we make the proposition that a hybrid system comprising a blend of FL and CBR can lead to a solution where the two approaches cover each other’s weaknesses and benefit from each other’s strengths. We support our claim by taking the problem of facial expression recognition from an input image. The facial expression recognition system presented in this paper uses a case base populated with fuzzy rules for recognizing each expression. Experimental results demonstrate that the system inherits the strengths of both methods. © 2008 Elsevier B.V. All rights reserved.
23 Figures and Tables
Table 2 FAE state extraction parameters
Fig. 3. The 2-D activation-evaluation space.
Fig. 4. Ekman’s basic expressions.
Fig. 5. (a) Input image, (b) skin pixels, and (c) detected face.
Table 5 Comparison of the proposed hybrid system with other systems in literature
Fig. 6. Feature points for feature estimation.
Fig. 7. Feature position detection using vertical projection.
Fig. 8. (a) Eye image, (b) threshold eye image, (c) contour traced eye image, and (d) detected points.
Fig. 9. CBR cycle for facial expression recognition.
Fig. 10. FRBS architecture.
Fig. 11. MFs plot for ‘expression’ showing overlap regions .
Fig. 12. Fuzzy case-based reasoning system.
Fig. 14. Model for overlapping expressions.
Fig. 15. The 2× 2 ROC confusion matrix (redrawn from ).
Fig. 16. tp rate, fp rate, and accuracy plots for CBR system.
Fig. 17. ROC plot for CBR system.
Fig. 18. tp rate, fp rate, and accuracy plots for fuzzy rule-based system.
Fig. 19. ROC plot for FRBS.
Fig. 20. tp rate, fp rate, and accuracy plots for FCBR system.
Fig. 21. ROC plot for FCBR system.
Download Full PDF Version (Non-Commercial Use)