Automatic generation of morphological set recognition algorithms
著者
書誌事項
Automatic generation of morphological set recognition algorithms
（Springer series in perception engineering）
Springer-Verlag, c1989
- : us. alk. paper
- : gw
大学図書館所蔵 件 / 全16件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Bibliography: p. [263]-266
Includes index
内容説明・目次
内容説明
Since the early days of computers, machine learning and automatic programming have attracted researchers in computer science and related fields, particularly pattern recognition and automatic control theory. Most of the learning concepts in machine perception have been inspired by pattern recognition approaches that rely on statistical techniques. These statistical techniques have applicability in limited recognition tasks. Automatic programming in perception systems has generally been limited to interfaces that allow easy specification of the task using natural language. Clearly, machine learning and automatic programming can make percep- tion systems powerful and easy to use. Vogt's book addresses both these tasks in the context of machine vision. He uses morphological operations to implement his approach which was developed for solving the figure-ground problem in images. His system selects the correct se- quence of operators to accept or reject pixels for fmding objects in an image. The sequence of operators is selected after a user specifies what the correct objects are.
On the surface it may appear that the problem solved by the system is not very interesting, however, the contribution ofVogt' s work should not be judged by the images that the system can segment. Its real contribution is in demonstrat- ing, possibly for'the frrst time, that automatic programming is possible in computer vision systems. The selection of morphological operators demonstrates that to implement an automatic programming-based approach, operators whose behavior is clearly defined in the image space are required.
目次
1 Introduction.- 1.1 Problem Definition and Characterization.- 1.2 Mathematical Morphology.- 1.3 Related Work.- 1.4 Goals and Objectives.- 1.5 Organization of the Book.- 2 Review of Mathematical Morphology.- 2.1 Types of Image Data.- 2.2 Images as Sets in Space.- 2.3 Operation Classes and Properties.- 2.4 Criteria.- 2.5 Set Operations.- 2.6 Positional Masking and Thresholding Operations.- 2.7 Translation-Based Morphology Operations.- 2.8 Structuring Element Decomposition.- 2.9 Common Structuring Elements.- 2.10 Erosions and Dilations.- 2.11 Openings and Closings.- 2.12 Residues.- 2.13 Band Operations.- 2.14 Particle and Hole Operations.- 2.15 Grey Level Operations.- 2.16 Summary of Problem Domain.- 3 Theory of Automatic Set Recognition.- 3.1 Basic Terminology.- 3.2 Example Problems.- 3.3 Formal Description of Problems.- 3.4 Algorithms as Graphs.- 3.5 The Algorithm Development Process.- 3.6 Search Strategies and Completeness.- 4 REM System Implementation.- 4.1 Representation of Algorithms.- 4.1.1 Machine Level-C4PL Language.- 4.1.2 Lisp Executable Level-MM Language.- 4.1.3 Algebraic Level-IA Language.- 4.1.4 Target Level-IC Language.- 4.1.5 Operation Database.- 4.1.6 Algorithm Representation Summary.- 4.2 Overview of System Design.- 4.2.1 Program Components.- 4.2.2 Data Structures.- 4.2.3 Activity.- 4.3 Search Management.- 4.4 Problem Solving.- 4.4.1 Subproblem Instantiation.- 4.4.2 Subproblem Evaluation.- 4.4.3 Operator Testing and Proposal.- 4.4.4 Data Collection.- 4.4.5 Data Analysis and Solution Generation.- 4.4.6 Selection and Dispatching of Solutions.- 4.5 System Output.- 5 Results.- 5.1 Summary of System Capabilities.- 5.2 Examples of Problems Solved by REM.- 5.3 Example Program Run.- 6 Conclusion.- 6.1 Primary Accomplishments.- 6.2 Summary and Discussion.- 6.3 Future Directions.- A Partial List of Example Problems Solved by REM.- B Algebraic Definitions of IC Band Operations.- C Terminal Output for Example Problem 'TCODSK_RT'.- D Band Operators Defined in the IC Target Language.- E Selected Bibliography.
「Nielsen BookData」 より