perception introduction pattern recognition image formation image processing summary

43
Perception Introduction Pattern Recognition Image Formation • Image Processing • Summary

Upload: mervyn-miles

Post on 29-Dec-2015

223 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Perception

• Introduction• Pattern Recognition• Image Formation• Image Processing• Summary

Page 2: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Introduction

• Perception is initiated by sensors.

• The focus is on vision (as opposed to hearing, sensing).

• How do we process info. provided by sensors?

• What can I infer about the world from this sequence of sensors?

Page 3: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Processing Sensor Data

It has several uses:

• Manipulation. • Navigation.• Object Recognition.

Page 4: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Perception

• Introduction• Pattern Recognition• Image Formation• Image Processing• Summary

Page 5: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Recognizing Patterns

Definition. Pattern recognition is the “act of taking in raw data and taking an action or category of the pattern”(Pattern Classification, Duda, Hart, and Stork).

ComputerComputer

Pattern RecognitionPattern Recognition

ActionActionInput SignalInput Signal

Page 6: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

A Particular Example

Fish packing plant Sort incoming fish on a belt according to two classes:

Salmon or Sea Bass

Steps:a) Preprocessing (segmentation)b) Feature extraction (measure features or properties)c) Classification (make final decision)

Page 7: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.1

Page 8: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.2

Page 9: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.3

Page 10: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Decision Theory

Most times we assume “symmetry” in the cost.(e.g., it is as bad to misclassify salmon as sea bass).

That is not always the case:

Case 1.

Case 2.

Sea bass can with pieces of salmon

X Salmon can with pieces of sea bass

Page 11: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Decision BoundaryWe will normally deal with several features at a time.

An object will be represented as a feature vector

X =

x1x2

Our problem then is to separate the space of feature valuesinto a set of regions corresponding to the number of classes.The separating boundary is called the decision boundary.

Page 12: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.4

Page 13: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

GeneralizationThe main goal of pattern classification is as follows:

To generalize or suggest the class or action of objectsas yet unseen.

Some complex decision boundaries are not good at generalization.Some simple boundaries are not good either.

One must look for a tradeoff between performance and simplicity

This is at the core of statistical pattern recognition

Page 14: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.5

Page 15: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.6

Page 16: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Designing Pattern Recognition Systems

Components in a system:

a) Sensing devicesOften a transducer such as a camera or microphone (features: bandwidth,resolution, sensitivity, distortion, latency, etc.)

b) Segmentation and groupingPatterns must be segmented (there may be overlapping).

c) Feature extractionExtract features that simplify classification.Ideally: values similar in same category and different among categories. That is we need distinguishing features (invariant to transformations).

Page 17: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Designing Pattern Recognition Systems

Components in a system:

d) ClassificationUse feature vectors to assign an object to the right category. Ideally: determine probability of category membership for an object.Learn to handle noise.

e) Post processingUse output of classifier to suggest an action.Classifier performance? Error rate?Minimize expected cost or “risk”.

Page 18: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Figure 1.7

Our focus of study today

Page 19: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Applying Pattern Recognition Systems

Steps:

1. Data CollectionUsually very time consuming

2. Feature ChoicePrior knowledge is crucial

3. Model ChoiceSwitch to new features, new classifier

4. TrainingLearn from example patterns

5. EvaluationAvoid overfitting

Page 20: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Perception

• Introduction• Image Formation• Image Processing• Summary

Page 21: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Image Formation

Consists of creating a 2-D image of a scene.

We can do this through a pinhole camera.

Image is inverted through “perspective projection”.

Page 22: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 23: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Translation of Coordinates

Let (x,y,z) be a point in the image.Let (X,Y,Z) be a point in the scene.

Then,

-x/f = X/Z -y/f = Y/z

x = -fX/Z y = -fY/Z

Page 24: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Lenses

Real cameras use a lens. More light comes in. (but not all can be in sharp focus).

Scene points within certain range Zo can be identified with sharp focus.

This is called the depth of the field.

Page 25: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

CCD Camera

The image plane is subdivided into pixels. (typically 512x512).

The signal is modeled by the variation in image brightness over time.

Page 26: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 27: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Fig. 24.4a

Page 28: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Fig. 24.4b

Page 29: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Photometry of Image Formation

The brightness of a pixel is proportional tothe amount of light directed toward the camera.

Light reflected can be of two types:a. Diffusely reflected (penetrates below the surface of the object and is re-emitted).b. Specularly reflected. Light is reflected from the outer surface of the object.

Page 30: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Photometry of Image Formation

Most surfaces have a combination of diffuselyspecularly reflected light.

This is the key to “modeling” in computer graphics

Page 31: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Perception

• Introduction• Image Formation• Image Processing• Summary

Page 32: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Image Processing

One important step is “edge detection”.

Motivation:

Edge contours correspond to scene contours.

Page 33: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 34: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Image Processing

Typically there are problems:

• missing contours• noise contours

Page 35: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Edge Detection

Edges are curves in the image plane where there is a clear change of brightness.

How do we detect edges?

Consider the profile of image brightness along a 1-D cross-section perpendicular to an edge.

Page 36: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 37: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Solutions

1. Look for places where the derivative is large.(many subsidiary peaks may show up).

2. Combine differentiation with smoothing.

Page 38: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 39: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Extracting 3-D Information

Normally divided into three steps:

a. Segmentation.b. Determining position and orientation.

Important for navigation and manipulation.c. Determining the shape of objects

Page 40: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Stereopsis

Idea is similar to motion parallax.We use images separated in space. Superposing the images would show a disparity in the location of image features.

Page 41: Perception Introduction Pattern Recognition Image Formation Image Processing Summary
Page 42: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Perception

• Introduction• Image Formation• Image Processing• Summary

Page 43: Perception Introduction Pattern Recognition Image Formation Image Processing Summary

Summary

• We need to extract information from sensor data for activities such as manipulation, navigation, and object recognition.• A signal is modeled by the variation in image brightness over time.• Light reflected can be diffusely reflected or specularly reflected.• Stereopsis is similar to motion parallax.