computer vision & digital image...

Dr. D. J. Jackson Lecture 1-1Electrical & Computer Engineering

Computer Vision &Digital Image Processing

Introduction to Digital Image Processing


Background

• Interest comes from two primary backgrounds– Improvement of pictorial information for human perception

• How can an image/video be made more aesthetically pleasing• How can an image/video be enhanced to facilitate extraction of

useful information– Processing of data for autonomous machine perception

• One of the earliest applications was improving digitized newspaper pictures sent by transatlantic cable (early 1920s)– Bartlane cable picture transmission reduced the time to

send transatlantic images from more than a week to less than 3 hours


Example Bartlane transmitted image

• Specialized printing equipment coded pictures for transmission

• Received and printed on a telegraph printer fitted with type faces to simulate a halftone pattern

• Initial problems– Poor visual quality related to

printing process and the distribution of brightness levels

• Image produced in 1921 from a coded tape by a telegraph printer with special type faces


Improved Bartlane transmitted image

• Replace the printing process• New technique used

photographic reproduction made from a perforated tape at the telegraph receiving terminal

• Improvements– tonal quality– resolution

• Digital picture made in 1922 from a tape punched after the signals had crossed the Atlantic twice


15 level Bartlane image

• Early images were transmitted using 5 distinct brightness levels

• The process was improved in 1929 to 15 levels

• A system for developing a film plate (as opposed to printing) from the coded picture tape improved the reproduction process considerably

• Cable picture of Generals Pershing and Foch, transmitted in 1929 by 15-tone equipment from London to New York


Growth in image processing

• Made possible by the advent of large-scale digital computers• Often motivated by requirements of the space program

– Pre-Apollo and Apollo moon missions: typical requirement was to correct various types of image distortion inherent in on-board television cameras

– Mariner Mars flyby missions, etc.

• Image processing now used to solve many problems• Commonly require methods capable of enhancing pictorial

information for human interpretation and analysis


Example image processing applications

• Medical field: X-ray (or other biomedical) image enhancement

• Aerial and satellite image enhancement: agriculture, weather and military

• Industrial applications: computer-based product inspection• Law enforcement: fingerprint processing, surveillance

camera processing• Defense applications: recognizing an enemy tank in foliage,

guiding a missile in flight• Science: enhancing an electron microscope image for

readability


Example: a cell

• Image of a cell corrupted by electronic noise

• Result after averaging several noisy images (a common technique for noise reduction)


Example: an x-ray

• An original x-ray image

• Result possible after contrast and edge enhancement


Example: image deblurring

• Image of a human face blurred by uniform motion during exposure

• Resulting image after application of a deblurring algorithm


Electromagnetic Spectrum


Vivible/Infrared Imaging Example (LANDSAT)


LANDSAT Images of Washington D.C. Area


Machine perception

• Previous examples illustrate processing results intended for human interpretation

• A second class of image processing applications is solving problems dealing with machine perception

• In this case, interest focuses on methods for extracting information in a form suitable for computer processing– Statistical moments– Fourier transform coefficients– Distance measures– Eigenvectors and Eigenvalues


Typical problems in machine perception

• Automatic character recognition• Industrial machine vision for product assembly and

inspection• Military recognizance• Automatic processing of fingerprints• Screening of x-rays and blood samples• Machine processing of aerial and satellite imagery

for weather prediction and crop assessment


Digital image representation

• Monochrome image (or simply image) refers to a 2-dimensional light intensity function f(x,y)– x and y denote spatial coordinates– the value of f(x,y) at (x,y) is proportional to the brightness

(or gray level) of the image at that point

y

x

Origin

f(x,y)


Digital image

• A digital image is an image f(x,y) that has been discretized both in spatial coordinates and in brightness

• Considered as a matrix whose row and column indices represent a point in the image

• The corresponding matrix element value represents the gray level at that point

• The elements of such an array are referred to as:– image elements– picture elements (pixels or pels)


Steps in image processing

• The problem domain in this example consists of pieces of mail and the objective is to read the address on each piece

• Step 1: image acquisition– Acquire a digital image using an image sensor

• a monochrome or color TV camera: produces an entire image of theproblem domain every 1/30 second

• a line-scan camera: produces a single image line at a time, motion pastthe camera produces a 2-dimensional image

– If not digital, an analog-to-digital conversion process is required– The nature of the image sensor (and the produced image) are

determined by the application• Mail reading applications rely greatly on line-scan cameras• CCD and CMOS imaging sensors are very common in many applications


Steps in image processing (continued)

• Step 2: preprocessing– Key function: improve the image in ways that increase the

chance for success of the other processes– In the mail example, may deal with contrast

enhancement, removing noise, and isolating regions whose texture indicates a likelihood of alphanumeric information



• Step 3: segmentation– Broadly defined: breaking an image into its constituent parts– In general, one of the most difficult tasks in image processing

• Good segmentation simplifies the rest of the problem• Poor segmentation make make the task impossible

– Output is usually raw pixel data: may represent region boundaries, points in the region itself, etc.

• Boundary representation can be useful when the focus is on external shape characteristics (e.g. corners, rounded edges, etc.)

• Region representation is appropriate when the focus is on internal properties (e.g. texture or skeletal shape)

– For the mail problem (character recognition) both representations can be necessary



• Step 4: representation & description– Representation: transforming raw data into a form

suitable for computer processing– Description (also called feature extraction) deals with

extracting features that result in some quantitative information of interest or features which are basic for differentiating one class of objects from another

– In terms of character recognition, descriptors such as lakes (holes) and bays help differentiate one part of the alphabet from another



• Step 5: recognition & interpretation– Recognition: The process which assigns a label to an

object based on the information provided by its descriptors

may be the alphanumeric character A

– Interpretation: Assigning meaning to an ensemble of recognized objects

35487-0286 may be a ZIP code



KnowledgeBase

Preprocessing

ImageAcquisition

Segmentation Representation& description

Recognition& Interpretation

Result

ProblemDomain


Image Processing Steps(according to text chapters)


The knowledge base

• Knowledge about a problem domain is coded into an image processing system in the form of a knowledge database– May be simple:

• detailing areas of an image expected to be of interest

– May be complex• A list of all possible defects of a material in a vision inspection

system

– Guides operation of each processing module– Controls interaction between modules– Provides feedback through the system


Steps in an image processing system

• Not all image processing systems would require all steps/processing modules– Image enhancement for human visual perception may not

go beyond the preprocessing stage• A knowledge database may not be required• Processing systems which include recognition and

interpretation are associated with image analysis systems in which the objective is autonomous (or at least partially automatic)


Organization of the book and course

• Three broad topic areas:– Background

• Introduction• Visual perception, resolution, imaging geometry• Image transforms

– Preprocessing• Image enhancement techniques• Image restoration techniques

– Analysis• Segmentation• Representation & description• Recognition & interpretation


Assignment for next class period

• Read Chapter 1• Surf the internet and find one good site devoted to

image processing and email the site URL to [email protected]– Provide a brief, one paragraph, summary of the site

• Make sure your Bama email account is functioning properly

• Secure PC and/or workstation account from the college of engineering– Should already be active

computer vision & digital image...

Documents