logging in or signing up CV2007 1Lec01 Jade Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 281 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: December 18, 2007 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... Premium member Presentation Transcript Introduction to Computer Vision: Introduction to Computer Vision Lecture 1 Dr. Roger S. GaborskiWhere to Find Me: Where to Find Me Office: 70 – 3647 Office Hours: Tuesday 3:00 - 4:00pm (I will be in either my office or my lab, 70-3400) Thursday 2:00 - 3:00pm (I will be either in my lab 70-3400 or my office) Other times by appointment (No appointments on Mondays and Fridays) Often in my lab or office Wednesdays after 11:00am Goals of Computer Vision: Goals of Computer Vision Image Enhancement Reduce noise in an image thereby revealing features in the image Image Processing Operations Segment the image into objects Label individual objects Image Understanding Understand the ‘content’ of an image or sequence of images (video) Extract meaning of the image Course Outline: Course Outline Optional Textbook Online MATLAB tutorial Topics Homework Exams Projects (4005-757 only) Grading Webpage: www.cs.rit.edu/~rsg (includes course calendar on CV page)Grading (with Final): Grading (with Final) Homework 30%(457) 20%(757) Quizzes 50% 50% Project* --- 10% Final 20% 20% No Project for 4003-457 *Project: 757 Individual only, also, presentation Grading (without Final) : Grading (without Final) 4003-457 Homework 40% Quizzes 60% 4005-757 Homework 30% Quizzes 60% Project 10% Course Grade: Course Grade 90%-100% A* 80%-89% B 70%-79% C 60%-69% D <60% F * Note: For example, 89.4 is a ‘B’, 89.5 is rounded to 90 which is an ‘A’Project: Project Choose from a list of projects provided on course Project Page Lecture 10 – One page Project Proposal on your webpage* Weekly updates* starting with Lecture 11 – see course calendar *Project grading includes proposal and weekly update progressComputer Vision – Interpretation of Images: Computer Vision – Interpretation of Images Digital photographs Medical radiographic images Functional magnetic resonance imaging (fMRI) Medical ultrasound Industrial radiographic images Digital video images Satellite images Astronomy Digital Image: Digital ImageDigital Image: Digital ImageDigital Image: Digital ImageMedical Related Images: Medical Related Images Information obtained from images: Bone structure Soft Tissue Brain ActivityMedical Radiographic Image: Medical Radiographic Image www.4umi.com/image/x-ray.jpgMedical Ultrasound: Medical Ultrasound http://keystone.stanford.edu/~huster/photos/i/ultrasound.640.jpgFunctional MRI: Functional MRI www.alcoholism2.com/ Response to the spatial working memory task. Brain activation is shown in bright colors. A 20-year old female drinker A 20-year old female nondrinker Industrial Applications: Industrial Applications Non Destructive Testing Inspection / SecurityIndustrial Radiographic Image: Industrial Radiographic Image www.vidisco.com/ CabinetXrayMic80A_01.htm Industrial Radiographic Image: Industrial Radiographic Image www.vidisco.com/ CabinetXrayMic80A_01.htm Pseudo- colorSatellite Images and Astronomy: Satellite Images and Astronomy Satellite Images: Satellite Images www.noaa.govAstronomy Images: Astronomy Images www.sdsc.edu/ sciencegroup/astronomy/ Astronomy Images: Astronomy Images astro.martianbachelor.com/ Image Database Problem: Image Database Problem Assume you have taken pictures with your digital camera the last three years You now have 4000 pictures stored on your computer’s hard drive How do you sort them?Sample Images: Sample ImagesSlide27: How do you find a particular object in an image? Faces Cars Buildings etcImage Models: Image Models Task: “Look for an object in an image” Assume the task is to find rectangle and washer objects Image models, continued: Image models, continued Image Models: Image Models Task: “Look for an object in an image” Assume the task is to find rectangle and washer objects Find outlines of objects in the image Create a model of the object Rectangle: Four straight lines, Opposite lines equal in length, 90 degree angles, lines connected Washer: Two concentric circlesImage models, edges: Image models, edges Image models, continued: Image models, continued One object partially overlaps anotherObjects are 3 Dimensional: Objects are 3 Dimensional Rotating Disk Frame 1 Frame 2 Frame 3License Plate Model: License Plate Model Rectangular (depending on viewpoint) Aspect ratio 2:1 Textures (characters on license plate)Face Model: Face Model http://www.faceresearch.org/Face Model: Face Model http://www.faceresearch.org/ Face Model: Face Model Features: eyes, nose, mouth, shape of face (oval) Spatial orientation of features Issues to investigate: how do we detect features? Normalize for different faces? Scale? Orientation? Cluttered background?Finding Cars in Images Training: Finding Cars in Images TrainingTesting: TestingDeformable Objects in Video: Deformable Objects in VideoSimple Eye Model: Simple Eye Model http://www.ap.stmarys.ca/demos/content/astronomy/eye_model/eye_model.htmlPin Hole Camera Model: Pin Hole Camera Model pi( xi, yi, zi ) p0( x0, y0, z0 ) f ( z0-f ) z0 y0 z y yi=? tan = yi / f tan = y0 / ( z0 – f ) therefore, yi / f = y0 / ( z0 – f ) => yi = ( f * y0 ) / ( z0 – f ) SENSORLoss of z Information All points of line p0-pi project to same point: Loss of z Information All points of line p0-pi project to same point pi( xi, yi, zi ) p0( x0, y0, z0 ) f ( z0-f ) z0 y0 z y yi=? tan = yi / f tan = y0 / ( z0 – f ) therefore, yi / f = y0 / ( z0 – f ) => yi = ( f * y0 ) / ( z0 – f ) SENSORDigital Images: Digital Images Matrix of numbers Each number represents a picture element – ‘pixel’ Pixels are parameterized by x – y position intensity (color or monochrome) time MATLAB is designed for processing matrices (Matrix Laboratory)MATLAB: MATLAB Any issues concerning using MATLAB on the CS department computers contact Sam Waters or Jim Craig in the CS System Admin office: System Administrators James "Linus" Craig; Username: jmc; 3599; 475-5254 Sam Waters; Username: srw; 3596; 475-4934MATLAB Tutorial: MATLAB Tutorial Complete MATLAB tutorial (not SIMULINK): http://www.mathworks.com/academia/student_center/tutorials/ You do not have the permission to view this presentation. In order to view it, please contact the author of the presentation.
CV2007 1Lec01 Jade Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 281 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: December 18, 2007 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... Premium member Presentation Transcript Introduction to Computer Vision: Introduction to Computer Vision Lecture 1 Dr. Roger S. GaborskiWhere to Find Me: Where to Find Me Office: 70 – 3647 Office Hours: Tuesday 3:00 - 4:00pm (I will be in either my office or my lab, 70-3400) Thursday 2:00 - 3:00pm (I will be either in my lab 70-3400 or my office) Other times by appointment (No appointments on Mondays and Fridays) Often in my lab or office Wednesdays after 11:00am Goals of Computer Vision: Goals of Computer Vision Image Enhancement Reduce noise in an image thereby revealing features in the image Image Processing Operations Segment the image into objects Label individual objects Image Understanding Understand the ‘content’ of an image or sequence of images (video) Extract meaning of the image Course Outline: Course Outline Optional Textbook Online MATLAB tutorial Topics Homework Exams Projects (4005-757 only) Grading Webpage: www.cs.rit.edu/~rsg (includes course calendar on CV page)Grading (with Final): Grading (with Final) Homework 30%(457) 20%(757) Quizzes 50% 50% Project* --- 10% Final 20% 20% No Project for 4003-457 *Project: 757 Individual only, also, presentation Grading (without Final) : Grading (without Final) 4003-457 Homework 40% Quizzes 60% 4005-757 Homework 30% Quizzes 60% Project 10% Course Grade: Course Grade 90%-100% A* 80%-89% B 70%-79% C 60%-69% D <60% F * Note: For example, 89.4 is a ‘B’, 89.5 is rounded to 90 which is an ‘A’Project: Project Choose from a list of projects provided on course Project Page Lecture 10 – One page Project Proposal on your webpage* Weekly updates* starting with Lecture 11 – see course calendar *Project grading includes proposal and weekly update progressComputer Vision – Interpretation of Images: Computer Vision – Interpretation of Images Digital photographs Medical radiographic images Functional magnetic resonance imaging (fMRI) Medical ultrasound Industrial radiographic images Digital video images Satellite images Astronomy Digital Image: Digital ImageDigital Image: Digital ImageDigital Image: Digital ImageMedical Related Images: Medical Related Images Information obtained from images: Bone structure Soft Tissue Brain ActivityMedical Radiographic Image: Medical Radiographic Image www.4umi.com/image/x-ray.jpgMedical Ultrasound: Medical Ultrasound http://keystone.stanford.edu/~huster/photos/i/ultrasound.640.jpgFunctional MRI: Functional MRI www.alcoholism2.com/ Response to the spatial working memory task. Brain activation is shown in bright colors. A 20-year old female drinker A 20-year old female nondrinker Industrial Applications: Industrial Applications Non Destructive Testing Inspection / SecurityIndustrial Radiographic Image: Industrial Radiographic Image www.vidisco.com/ CabinetXrayMic80A_01.htm Industrial Radiographic Image: Industrial Radiographic Image www.vidisco.com/ CabinetXrayMic80A_01.htm Pseudo- colorSatellite Images and Astronomy: Satellite Images and Astronomy Satellite Images: Satellite Images www.noaa.govAstronomy Images: Astronomy Images www.sdsc.edu/ sciencegroup/astronomy/ Astronomy Images: Astronomy Images astro.martianbachelor.com/ Image Database Problem: Image Database Problem Assume you have taken pictures with your digital camera the last three years You now have 4000 pictures stored on your computer’s hard drive How do you sort them?Sample Images: Sample ImagesSlide27: How do you find a particular object in an image? Faces Cars Buildings etcImage Models: Image Models Task: “Look for an object in an image” Assume the task is to find rectangle and washer objects Image models, continued: Image models, continued Image Models: Image Models Task: “Look for an object in an image” Assume the task is to find rectangle and washer objects Find outlines of objects in the image Create a model of the object Rectangle: Four straight lines, Opposite lines equal in length, 90 degree angles, lines connected Washer: Two concentric circlesImage models, edges: Image models, edges Image models, continued: Image models, continued One object partially overlaps anotherObjects are 3 Dimensional: Objects are 3 Dimensional Rotating Disk Frame 1 Frame 2 Frame 3License Plate Model: License Plate Model Rectangular (depending on viewpoint) Aspect ratio 2:1 Textures (characters on license plate)Face Model: Face Model http://www.faceresearch.org/Face Model: Face Model http://www.faceresearch.org/ Face Model: Face Model Features: eyes, nose, mouth, shape of face (oval) Spatial orientation of features Issues to investigate: how do we detect features? Normalize for different faces? Scale? Orientation? Cluttered background?Finding Cars in Images Training: Finding Cars in Images TrainingTesting: TestingDeformable Objects in Video: Deformable Objects in VideoSimple Eye Model: Simple Eye Model http://www.ap.stmarys.ca/demos/content/astronomy/eye_model/eye_model.htmlPin Hole Camera Model: Pin Hole Camera Model pi( xi, yi, zi ) p0( x0, y0, z0 ) f ( z0-f ) z0 y0 z y yi=? tan = yi / f tan = y0 / ( z0 – f ) therefore, yi / f = y0 / ( z0 – f ) => yi = ( f * y0 ) / ( z0 – f ) SENSORLoss of z Information All points of line p0-pi project to same point: Loss of z Information All points of line p0-pi project to same point pi( xi, yi, zi ) p0( x0, y0, z0 ) f ( z0-f ) z0 y0 z y yi=? tan = yi / f tan = y0 / ( z0 – f ) therefore, yi / f = y0 / ( z0 – f ) => yi = ( f * y0 ) / ( z0 – f ) SENSORDigital Images: Digital Images Matrix of numbers Each number represents a picture element – ‘pixel’ Pixels are parameterized by x – y position intensity (color or monochrome) time MATLAB is designed for processing matrices (Matrix Laboratory)MATLAB: MATLAB Any issues concerning using MATLAB on the CS department computers contact Sam Waters or Jim Craig in the CS System Admin office: System Administrators James "Linus" Craig; Username: jmc; 3599; 475-5254 Sam Waters; Username: srw; 3596; 475-4934MATLAB Tutorial: MATLAB Tutorial Complete MATLAB tutorial (not SIMULINK): http://www.mathworks.com/academia/student_center/tutorials/