1Ellen L. Walker Recognizing Objects in Computer Images Ellen L. Walker Mathematical Sciences Dept Hiram College Hiram, OH 44234

Slides:



Advertisements
Similar presentations
Chapter 10 Constructions.
Advertisements

Computational Geometry & Collision detection
Each pixel is 0 or 1, background or foreground Image processing to
Chapter 23 Mirrors and Lenses.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
1Ellen L. Walker Edges Humans easily understand “line drawings” as pictures.
Workshop on Earth Observation for Urban Planning and Management, 20 th November 2006, HK 1 Zhilin Li & Kourosh Khoshelham Dept of Land Surveying & Geo-Informatics.
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
CS 376b Introduction to Computer Vision 04 / 14 / 2008 Instructor: Michael Eckmann.
Orthographic Drawing.
Transformations, Constructions and 3D Drawings
Copyright © 2011 Pearson Education, Inc. Publishing as Prentice Hall. Chapter 8 Geometry and Measurement.
Geometry is everywhere by : Laura González  Solid figures are 3D figures that have length, width and heigth.  For example :  Sphere Faces:0 Vertices:0.
Basic geometric FIGURES
Basic Geometry Vocabulary Review.
Objective: To describe properties of solid shapes such as perpendicular and parallel lines, faces and edges.
Geometry Vocabulary Chapter 9.
October 8, 2013Computer Vision Lecture 11: The Hough Transform 1 Fitting Curve Models to Edges Most contours can be well described by combining several.
 Phones Cindy Ly 3A. Point  A point is a location without shape of size. It has no dimensions.  The silver button represents a “point” T.
Chapter 8 Geometry.
Reagan’s unit 5 math vocab
GEOMETRY 6.G.1 VOCABULARY Mrs. Thompson Level 1. Review Words Side: A line bounding a geometric figure: one of the faces forming the outside of an object.
Geometry The strand of math that deals with measurement and comparing figures, both plane and solid .
Attributes A quality that is characteristic of someone or something.
The Geometry of Solids Section 10.1.
A solid figure 3 dimensional figure.
Objective 1.01 Apply the properties and definitions of lines and angles to model and solve problems. Vocabulary Acute: an angle that measure less than.
Chapter 36 Image Formation.
PART 1 SOLID SHAPES Two-dimensional Shapes (2D) These shapes are flat and can only be drawn on paper. They have two dimensions – length and width.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
Geometry and Measurement Chapter Nine Lines and Angles Section 9.1.
Geometry Vocabulary Introduction to Classifying Angles.
Surface Area of Prisms and Cylinders 12.2 California State Standards 8, 9: Solve problems involving the surface area lateral area of geometric solids and.
An introduction to 3D Figures
Basic Geometry Vocabulary Review.
I go on and on in both directions What am I?. A line.
Geometric Construction Notes. Table of Contents How to navigate this presentation Geometric Construction Introduction Drawing Guidelines Parts of the.
Attributes A quality that is characteristic of someone or something.
Slide 1 Copyright © 2015, 2011, 2008 Pearson Education, Inc. Lines and Angles Section9.1.
To find the perimeter of a rectangle, just add up all the lengths of the sides: Perimeter = L + w + L + w         = 2L + 2w To find the area of a rectangle,
Chapter 8 Engineering Geometry
Geometry 1 st Grade Geometry Lesson. Content Strand Addressed Geometry Strand Students will: use visualization and spatial reasoning to analyze characteristics.
Descriptive Geometry. Introduction  What is Descriptive Geometry? →It is the study of points, lines, and planes in space to determine their locations.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Vocabulary Word: Supplementary Angles Definition: Two angles whose sum is 180°.
Course 3 Binary Image Binary Images have only two gray levels: “1” and “0”, i.e., black / white. —— save memory —— fast processing —— many features of.
Geometric Lines. You Can Find Geometric Lines in the Real World On Roads In Art On Our Flag In Games On Maps.
Lines and Angles Ray Congruent Equal in size and shape.
Points, Lines, and Planes SWBAT identify collinear and noncollinear points, lines, line segments, rays, angles, parallel lines, and skew lines; read and.
8.1 Building Blocks of Geometry Point: an exact location [notation] Line: a straight path with no thickness, extending forever in opposite directions [notation]
Orthographic Projection
Vocabulary for the Common Core Sixth Grade.  base: The side of a polygon that is perpendicular to the altitude or height. Base of this triangle Height.
GEOMETRY!!!. Points  A point is an end of a line segment.  It is an exact location in space.   It is represented by a small dot. Point A A.
Orthographic Projection Review: -Projections -Orthographic projections Home work: -Glass Box Unfolded -Multiview Projection Simple (duplicate) - Lettering.
Leaves Recognition By Zakir Mohammed Indiana State University Computer Science.
Polygons, Cones, Right Circular Cylinders, and Right Rectangular Prisms UMI: July 13, 2016.
Polygons, Cones, Right Circular Cylinders, and Right Rectangular Prisms UMI: July 13, 2016.
plane shape A shape in a plane that is formed by curves, line segments, or both. These are some plane figures 12.1.
Basic Geometry Vocabulary Review.
May look at figures in box to give you some ideas. Geometric Solid:
Bitmap Image Vectorization using Potrace Algorithm
Grade Seven – Pre-Algebra - Unit 9
Geometric Constructions
INTRODUCTION TO GEOMETRIC SOLIDS.
GEOMETRY.
Orthographic Projection
Introduction to Artificial Intelligence Lecture 22: Computer Vision II
Presentation transcript:

1Ellen L. Walker Recognizing Objects in Computer Images Ellen L. Walker Mathematical Sciences Dept Hiram College Hiram, OH

2Ellen L. Walker Why Recognize Objects? n “Put the clothing on the bed” n “Turn left at the apartment building”

3Ellen L. Walker Steps in Object Recognition

4Ellen L. Walker Formation of a 2D Image

5Ellen L. Walker Images are Composed of Pixels Image has 138 x 255 pixels (35190 total) Pixel values range from 0 (black) to 255 (white)

6Ellen L. Walker Edge Detection Use a technique called convolution to detect edges The 3x3 convolution of a pixel is the sum of the products of the pixel and its 8 neighbors with a 3x3 mask The convolution of the shaded cell with the mask is Abs(4x-1 + 3x0 + 2x1+ 4x-2 + 3x0 + 2x2 + 4x-1 + 3x0 + 2x1) = 8

7Ellen L. Walker Edge Detection with Convolution horiz. conv. vert. conv. both convolutions

8Ellen L. Walker Edges from Test Image After convolution and thresholding This is still an image … next find endpoints of straight segments

9Ellen L. Walker Fitting Line Segments to Edge Pixels n For each path of connected edge pixels: l draw a segment between the endpoints of the path l find the point farthest from the line l if it’s too far, then make that point an endpoint and recurse

10Ellen L. Walker Segments from Test Image n Circles denote endpoints n Note “broken” segments

11Ellen L. Walker Grouping Collinear Line Segments n Line segments are collinear if: angle between them is small enough (  ) l distance between them is small enough (PD) l “gap” between them is small enough (G)

12Ellen L. Walker Grouped Segments from Test Image n Long vertical and horizontal segments were found

13Ellen L. Walker Higher Levels of Grouping n Junctions n Curves & Polygons (no T-Junctions allowed)

14Ellen L. Walker Groups from the Test Image? n After grouping curves and polygons, and combining polygons that share an edge and no T-junctions n Finally, we’re ready to recognize!

15Ellen L. Walker Types of Models n Exact Models — Describe single objects l e.g. CAD models for factory parts l the object is needed to construct the model! n Generic Models —Describe classes of objects l Exact models with parameters (e.g length, width, radius) l Structural constraints n describe how the object is constructed l Functional constraints n describe how the object is used

16Ellen L. Walker Matching Method Depends on Model Level n Image l when objects are hard to describe (e.g. faces) l match by correlation (like convolution) n Features, Groups l good for geometric objects l match by finding correspondences between image and model features (or groups) n Complete Objects l good for classes of objects l match by applying constraints from model to objects derived from the image

17Ellen L. Walker Sample Object Model (Box) n Constraints l Adjacent faces are perpendicular (12 constraints) l Adjacent edges are perpendicular (8 constraints) l Opposite faces are parallel (3 constraints) l Opposite edges are parallel (6 constraints)

18Ellen L. Walker Finding Correspondences n Search the interpretation tree l each node is a correspondence l each path to a leaf is an interpretation l “prune” the tree based on constraints

19Ellen L. Walker Structural Constraints n Buildings — structural constraints l Buildings have rectangular walls and flat horizontal roofs l Each outer wall of a building intersects exactly two other walls, forming a closed ring l Each edge of the roof is the perpendicular intersection of the roof and a wall

20Ellen L. Walker Functional Constraints n Beds — functional constraints l A bed has a surface to sleep on that is relatively flat. l A bed has physical means of supporting the sleeping surface at a comfortable height. l A bed has clearance above and to at least one side of the sleeping surface.

21Ellen L. Walker Considering Occlusion in the Interpretation n Include names & parameters of objects n Include hypotheses for hidden parts when feasible n Specify only what is guaranteed!

22Ellen L. Walker Toward Real World Solutions n Increasingly complex models n Large number of alternatives to choose from n Uncertainty at all levels n Recognizing partially-visible objects n Recognition must be fast enough n Generating models automatically (learning!)