Docstoc

4btechcse1100026

Document Sample
4btechcse1100026 Powered By Docstoc
					CSE/IT 326         COMPUTER VISION                                    L T P       M
                                                                      4   1   0   100



UNIT ‐ I


Recognition Methodology: Conditioning, Labeling, Grouping, Extracting, and
Matching. Edge detection, Gradient based operators, Morphological operators,
Spatial operators for edge detection. Thinning, Region growing, region shrinking,
Labeling of connected components.
Binary Machine Vision: Thresholding, Segmentation, Connected component labeling,
Hierarchal segmentation, Spatial clustering, Split & merge, Rule‐based
Segmentation, Motionbased segmentation.



UNIT ‐ II


Area Extraction: Concepts, Data‐structures, Edge, Line‐Linking, Hough transform,
Line fitting, Curve fitting (Least‐square fitting).
Region Analysis: Region properties, External points, Spatial moments, Mixed spatial
gray‐level moments, Boundary analysis: Signature properties, Shape numbers.



UNIT ‐ III


Facet Model Recognition: Labeling lines, Understanding line drawings, Classification
of shapes by labeling of edges, Recognition of shapes, consisting labeling problem,
Back‐tracking, Perspective Projective geometry, Inverse perspective Projection,
Photogrammetry. From 2D to 3D, Image matching : Intensity matching of ID signals,
Matching of 2D image, Hierarchical image matching.
Object Models and Matching: 2D representation, Global vs. Local features.



UNIT ‐ IV


General Frame Works For Matching: Distance relational approach, Ordered
structural matching, View class matching, Models database organization.
General Frame Works: Distance .relational approach, Ordered .Structural matching,
View class matching, Models database organization.
Knowledge Based Vision: Knowledge representation, Control‐strategies,
InformationIntegration.


                                         76
Text Books:
1. David A. Forsyth, Jean Ponce, .Computer Vision: A Modern Approach.
2. R. Jain, R. Kasturi, and B. G. Schunk, .Machine Vision., McGraw‐Hill.

References:
1. Milan Sonka,Vaclav Hlavac, Roger Boyle, .Image Processing, Analysis, and
Machine Vision. Thomson Learning
2. Robert Haralick and Linda Shapiro, .Computer and Robot Vision., Vol I, II,
Addison‐Wesley, 1993.




CSE/IT 361           MINI PROJECT                                       L T P         M
                                                                         0   0    3   100
                                           CYCLE - 1

1.    Problem Statement
      ANALYSIS
2.    Requirements elicitation
3.    System Requirements Specification
      USECASE VIEW
4.    Identification of Actors
5.    Identification of Use cases
6.    Flow of Events
7.    Construction of Use case diagram
8.    Building a Business Process model using UML activity diagram
                                           CYCLE - 2
      LOGICAL VIEW
9.    Identification of Analysis Classes
10.   Identification of Responsibilities of each class
11.   Construction of Use case realization diagram
12.   Construction of Sequence diagram
13.   Construction of Collaboration diagram
14.   Identification of attributes of each class
15.   Identification of relationships of classes
16.   Analyzing the object behavior by constructing the UML State Chart diagram
17.   Construction of UML static class diagram
                                           CYCLE - 3

                                              77
         DESIGN
18.      Design the class by applying design axioms and corollaries
19.      Refine attributes, methods and relationships among classes


                                        MINI PROJECT
         The above three cycles are to be carried out in the context of a problem / system
choosen by the Project batch and a report is to be submitted at the semester end by the
batch.




CSE 362                COMPILER DESIGN LAB                                   L T P       M
                                                                             0   0   3   75

1. Design a Lexical analyzer for a language. The lexical analyzer should ignore
redundant spaces, tabs and newlines. It should also ignore comments. Although the
syntax specification states that identifiers can be arbitrarily long, you may restrict the
length to some reasonable value.

2. Implement the lexical analyzer using JLex, flex or lex or other lexical analyzer
generating tools.

3. Design Predictive parser for the given language

4. Design LALR bottom up parser for a language.

5. Convert the BNF rules into Yacc form and write code to generate abstract syntax
tree.

6. Write program to generate machine code from the abstract syntax tree generated
by the parser.




                                              78

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:0
posted:2/14/2013
language:Latin
pages:3