Download Safari Books Online apps: Apple iOS | Android

Entire Site

Safari Books Online

    Free Trial

    Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.


    Copyright
    Preface
    Acknowledgment
    Ch. I. Fusion of Segmentation Strategies for Off-Line Cursive Handwriting Recognition
    Ch. II. Elastic Matching Techniques for Handwritten Character Recognition
    Ch. III. State of the Art in Off-Line Signature Verification
    Ch. IV. An Automatic Off-Line Signature Verification and Forgery Detection System
    Ch. V. Introduction to Speech Recognition
    Ch. VI. Seeking Patterns in the Forensic Analysis of Handwriting and Speech
    Ch. VII. Image Pattern Recognition-Based Morphological Structure and Applications
    Ch. VIII. Robust Face Recognition Technique for a Real-Time Embedded Face Recognition System
    ABSTRACT
    INTRODUCTION
    BACKGROUND OF FACE RECOGNITION
    HEAD POSE COMPENSATION
    RESULTS FROM EXPERIMENTS
    REAL-TIME AUTOMATED FACE RECOGNITION SYSTEMS
    CONCLUSION AND FUTURE WORK
    ACKNOWLEDGMENT
    REFERENCES
    ENDNOTE
    Ch. IX. Occlusion Sequence Mining for Activity Discovery from Surveillance Videos
    Ch. X. Human Detection in Static Images
    Ch. XI. A Brain-Inspired Visual Pattern Recognition Architecture and Its Applications
    Ch. XII. Significance of Logic Synthesis in FPGA-Based Design of Image and Signal Processing Systems
    Ch. XIII. A Novel Support Vector Machine with Class-Dependent Features for Biomedical Data
    Ch. XIV. A Unified Approach to Support Vector Machines
    Ch. XV. Cluster Ensemble and Multi-Objective Clustering Methods
    Ch. XVI. Implementing Negative Correlation Learning in Evolutionary Ensembles with Suitable Speciation Techniques1
    Ch. XVII. A Recurrent Probabilistic Neural Network for EMG Pattern Recognition
    Compilation of References
    About the Contributors
    Index
    • Create BookmarkCreate Bookmark
    • Create Note or TagCreate Note or Tag
    • DownloadDownload
    • PrintPrint
    Share this Page URL
    Help

    RESULTS FROM EXPERIMENTS

    Training of Frontal Face Models

    To train the frontal face model, we collected face image samples from 40 individuals for the training set. For each person, we had three im ages in three pose views (left 15°, frontal, right 15°); all these images are extracted from the Feret database (NIST, 2001). We labeled each of these 120 face images with 58 points around the main features, including eyes, mouth, nose, eyebrows, and chin. Some labeled training face images can be seen in Figure 8.

    Figure 9. Active shape models (ASMs) search results on Feret database (NIST, 2001)



      

    You are currently reading a PREVIEW of this book.

                                                                                            

    Get instant access to over
    $1 million worth of books and videos.

      

    Start a Free Trial