Image Processing and Pattern Recognition (Google eBook)
Image Processing and Pattern Recognition covers major applications in the field, including optical character recognition, speech classification, medical imaging, paper currency recognition, classification reliability techniques, and sensor technology. The text emphasizes algorithms and architectures for achieving practical and effective systems, and presents many examples. Practitioners, researchers, and students in computer science, electrical engineering, andradiology, as well as those working at financial institutions, will value this unique and authoritative reference to diverse applications methodologies.
* Coverage includes:
* Optical character recognition
* Speech classification
* Medical imaging
* Paper currency recognition
* Classification reliability techniques
* Sensor technology
Algorithms and architectures for achieving practical and effective systems are emphasized, with many examples illustrating the text. Practitioners, researchers, and students in computer science, electrical engineering, and radiology, as wellk as those working at financial institutions, will find this volume a unique and comprehensive reference source for this diverse applications area.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Chapter 2 Comparison of Statistical and Neural Classifiers and Their Applications to Optical Character Recognition and Speech Classification
Chapter 3 Medical Imaging
Chapter 4 Paper Currency Recognition
Problems and Applications
Solving Regularization Problems with Architecture Inspired by the Vertebrate Retinal Circuit
adaptation analysis applications approach architecture arteriogram Artiﬁcial Neural Networks back-propagation bipolar cell character recognition circuit classiﬁcation reliability classiﬁer component Computer connections convergence data set deﬁned deﬁnition density digits discriminant eigenvalue error function estimate evaluation feature extraction feedforward Figure ﬁlter ﬁnal ﬁnd ﬁnding ﬁrst ﬁxed gradient hidden layer hidden units horizontal cell IEEE IEEE Trans Image Processing implementation iteration k-NN Kobayashi learning algorithms learning rate linear mask set matrix medical imaging method minimization misclassiﬁcation multilayer neurons node nonlinear number of hidden optical character recognition optimal output unit paper currency parameters pattern recognition perceptron performance pixel problem pruning receptive ﬁeld reject option response Section segmentation selected shown in Fig sigmoid function signal signiﬁcant slab value spatial speciﬁc speech recognition statistical supervised learning technique threshold tion Touretzky training samples training set unsupervised Vision Chips voltage Yagi zero