Kurzyński M., Puchała E., Woźniak M., Żołnierek A. (eds.) Computer Recognition Systems 2

Springer, 2007. — 873.The papers included into this book concern the pattern recognition principles and their practical applications. However, this classification is to a certain degree arbitrary, the concepts of novel methods very often being illustrated by practical examples and some pattern recognition applications including original modifications of the corresponding algorithms. In the, above-mentioned, first group of papers design and evaluation of effective pattern recognition algorithms is a dominating problem. The methods based on Support Vector Machines (SVM), mathematical statistics, formal grammars, fuzzy sets, decision trees, etc. are presented. The problems and methods of input data acquisition, selection, image enhancement and segmentation also have been presented in a group of papers. Among the pattern recognition applications the problems of computer-aided medical diagnosis are the most frequently presented. Early cancer detection, analysis of ECG, EEG and AMG signals, stem cells and biomolecular structures analysis, 3D human organs modeling, etc. are in the center of interest of authors of numerous papers. A large group of papers also concerns speech and handwritten characters recognition and textual data analysis. The list of other pattern recognition applications presented in the book is also large. The road traffic analysis, assessment and prediction of situation of enterprises, personal identification based on human face analysis, etc. as selected examples can be mentioned. This short r´esum´e of the book contents shows that pattern recognition is a vital and very fruitful from the point of view of practical applications research area.
The perspectives of further development of pattern recognition are closely connected with a progress in computer-aided observed data understanding and assessment methods. Let us remark that on the lower levels of recognition the elements of domain knowledge are provided in the form of adjusted parameters of recognizing algorithms, of weights of inter-neuronal connections in artificial neural networks or of the reference data sets in learning systems. In higherlevel recognition systems using more advanced domain knowledge representation methods are necessary. Among them various forms of statistical or functional models, domain ontologies, formal grammars, etc. can be mentioned. Each of the above-mentioned forms leads, respectively, to a specific approach to advanced recognition and interpretation of observed objects. It seems that a fusion of knowledge representation methods, data mining and logical inference based on incomplete or uncertain data methods will chart the main pattern recognition directions of development in the future.Part I: Image Processing and Computer Vision
Strategies of Shape and Color Fusions for Content Based Image Retrieval
Determining the Contour of Cylindrical Biological Objects Using the Directional Field
Trajectory Fusion for Multiple Camera Tracking
Object Selection Based on Clustering and Border Objects
Multi-directional Multi-resolution Transforms for Zoom-Endoscopy Image Classification
Image Retrieval for Image Theft Detection
Practical Evaluation of the Basic Concepts for Face Localization
Hybrid Fuzzy Clustering Method
Structural Image Analysis Based on Ontological Models
Homogeneity of Pixel Neighborhoods in Gray Level Images Investigated by the Grade Correspondence Analysis
Comparison of Hierarchical Cluster Analysis Methods Applied to Image Segmentation by Watershed Merging
Modified Diffusion to Image Denoising
New Results in Generation of Accurate 3D Multiview Representation of Monotonous Polyhedrons
On the Application of Distance Transformation in Digital Image Colorization
Local Analysis of Stereo Image Pairs with Polynomial Series
The Architecture of the Face and Eyes Detection System Based on Cascade Classifiers
Morphological Edge Detection Algorithm and Its Hardware Implementation
Numerical Complexity Reduction in Live-Wire Algorithm
Image Segmentation Using Adaptive Potential Active ontours
Towards an Exploration of GCA Ordered Pixels
A Simple Method of Multiple Camera Calibration for the Joint Top View Projection
Spiral Scanning of Faces to Obtain Complete 3D View Representation of Monotonous Polyhedra
Face Detection in Color Images Using Primitive Shape Features
Detection of Near-Duplicated Image Regions
Automatic Merging of 3D Attribute Meshes
Part II: Features, Learning and Classifiers
Learning Machines Information Distribution System with Example Applications
Maximum Margin Classification on Convex Euclidean Metric Spaces
Optimization of the SVM Screening Kernel– Application to Hit Definition in Compound Screening
Estimation of the Preference Relation on the Basis of Medians from Pairwise Comparisons in the Form of Difference of Ranks
Feature Selection for High-Dimensional Data – A Pearson Redundancy Based Filter
Some Approximation Algorithms for Minimum Vertex Cover in a Hypergraph
Reference Set Reduction Algorithms Based on Double Sorting
Using Graph Mining Methods in Searching for Frequent Patterns in Graph-Based Design Representation
Stability of Feature Points Defined by Approximating Quadric Surfaces
Generalisation of a Language Sample for Grammatical Inference of GDPLL(k) Grammars
Pattern Classification Using Efficient Linear Classifiers with Small Number of Weights
Markov Chain Model for Tree-Based Genetic Algorithm Used in Computer Aided Design
Binary Shape Characterization Using Morphological Boundary Class Distribution Functions
Fuzzy-aided Parsing for Pattern Recognition
On Speeding Up the Learning Process of Neuro-fuzzy Ensembles Generated by the Adaboost Algorithm
Active Hypercontour as Information Fusion Method
Effective Ad Recognition Using Schur-type Signal Parametrization
Feature Extraction of Gray-Scale Handwritten Characters Using Gabor Filters and Zernike Moments
Pattern Discovery Through Separable Data Projections
Support Vector Machine Classifier with Feature Extraction Stage as an Efficient Tool for Atrial Fibrillation Detection Improvement
Classification Accuracy in Local Optimal Strategy of Multistage Recognition with Fuzzy Data
Experiments on Classifiers Obtained Via Decision Tree Induction Methods with Different Attribute Acquisition Cost Limit
Fast Adaptive Fourier Transform for Fourier Descriptor Based Contour Classification
Separable Decomposition of Graph Using α-cliques
A Feature Selection Approach in Problems with a Great Number of Features
Part III: Speech and Word Recognition
Normalisation of Confidence Voting Methods Applied to a Fast Handwritten OCR Classification
Extraction of the Visual Features from the Audio-Visual Speech Signal and the Utilization of These Features for the Speaker Identification
Different Approaches to Class-Based Language Models Using Word Segments
Recognition of Ultra Low Resolution Word Images Using HMMs
Manageable Phrase-Based Statistical Machine Translation Models
Automatic Detection of Disorders in a Continuous Speech with the Hidden Markov Models Approach
The Polish Finger Alphabet Hand Postures Recognition Using Elastic Graph Matching
Character Recognition Based on Fourier Transfrom and CDWT in Postal Applications
Preprocessing for Real-Time Handwritten Character Recognition
Handwritten Word Recognition with Combined Classifier Based on Tri-grams
Semi-automatic Handwritten Word Segmentation Based on Character Width Approximation Via Maximum Likelihood Method and Regression Model
Sentence Boundary Verification in Polish Text
Part IV: Medical Applications
Synthesis of Static Medical Images – An Example of Melanocytic Skin Lesions
Morphological Spectra as Tools for Texture Analysis
Breast Contour Detection for the Aesthetic Evaluation of Breast Cancer Conservative Treatment
Simple EEG Driven Mouse Cursor Movement
The Prediction of Fetal Outcome by Applying Neural Network for Evaluation of CTG Records
Determining Weights of Symptoms in a Diagnostic Inference
Hough Transform, (1+1) Search Strategy and Watershed Algorithm in Segmentation of Cytological Images
Preliminary Investigations Regarding the Blood Volume Estimation in Pneumatically Controlled Ventricular Assist Device by Pattern Recognition
‘Sonar’ – Region of Interest Identification and Segmentation Method for Cytological Breast Cancer Images
Validation of Automatic ECG Processing Management in Adaptive Distributed Surveillance System
Estimation of a Muscle Force from a Mechanomyographic Signal During a Contraction of a Single Motor Unit
Automatic Segmentation of EMG Signals Based on Wavelet Representation
Elimination of Linear Structures as an Attempt to Improve the Specificity of Cancerous Mass Detection in Mammograms
Automatic Counting of Neural Stem Cells Growing in Cultures
Value of Digital Image Analysis in Research and Diagnosis of Urine Bladder Cancer
Movement Tracking of Coronary Artery Segment in Angiographic Images Sequences by Template Matching Method
Computer Ultrasonic Imaging of the Tongue Shape Changes in the Process of Articulation of Vowels
The Biometric Signals Processing
Digital Dental Models and 3D Patient Photographs Registration for Orthodontic Documentation and Diagnostic Purposes
Gait Motor Disturbances in Neurological Diseases Diagnosis
Analysis of Head-Mounted Wireless Camera Videos for Early Diagnosis of Autism
Automatic Generation of 3D Lung Model
Control of Dexterous Hand Via Recognition of EMG Signals Using Combination of Decision-Tree and Sequential Classifier
Posterior Cruciate Ligament – 3D Visualization
Part V: Various Applications
A Self-training Approach for Automatically Labeling IP Traffic Traces
A Case-Base Reasoning System for Predicting the Economic Situation of Enterprises – Tacit Knowledge Capture Process (Externalization)
A Structural Pattern Analysis Approach to Iris Recognition
Enhancing Real-Time Human Detection Based on Histograms of Oriented Gradients
Decisive Factors in the Annotation of Emotions for Spoken Dialogue Systems
A Hybrid Big Rock Detection Algorithm Based on Multiple Images Fusion and Watershed
Design Description Hypergraph Language
Articulation Rate Recognition by Using Artificial Neural Networks
Recognition of Cycles of Repeated Hypoxia on the Basis of Time Periods in Biological Model
Fingerprint Reference Point Detection Using Neighbourhood Influence Method
Gene Expression Programming-Based Method of Optimal Frequency Set Determination for Purpose of Analogue Circuits’ Diagnosis
Prediction of Economic Situation of Small and Medium Enterprises Using Bayesian Network
Ensembles of Artificial Neural Networks for Predicting Economic Situation of Small and Medium Enterprises
The Performance of the Haar Cascade Classifiers Applied to the Face and Eyes Detection
FPGA Implementation of the Gradient Adaptive Lattice Filter Structure for Feature Extraction
Adaptive Selection of Feature Set Dimensionality for Classification of DNA Microarray Samples
Human Lips Recognition
Model Based Vehicle Extraction and Tracking for Road Traffic Control
Optimization of Linear Fuzzy Gene Network Model Searching