


Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Community
Ask the community for help and clear up your study doubts
Discover the best universities in your country according to Docsity users
Free resources
Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors
An exam paper covering image processing topics like segmentation, frequency domain, matching, and application-based problems. The 6-question exam is open-book, without calculators or computers. It tests a wide range of concepts, including compression, diffusion, color spaces, inpainting, pyramids, and robust features. The application-based questions focus on object tracking in video and measuring photovoltaic potential using aerial/satellite imagery.
Typology: Cheat Sheet
1 / 4
This page cannot be seen from the preview
Don't miss anything!
National Exams 04-Bio-B4 —Image Processing^ May, 2015
Final Examination
Exam Notes
NationalExams 04-Bio-B4—ImageProcessing May,^2015
1.BasicDefinitions Foreachofthefollowingconcepts,giveabriefdefinition (2-4sentences)and a descriptionofwhere the conceptisusedorapplied,inpractice: (a)LossyCompression (b) AnisotropicDiffusion (c)YUVColourSpace (d)ImageInpainting (e)LaplacianPyramids (~ImageSegmentation (g)RobustImageFeatures, suchasSIFTorSURF
2.Lnage Segmentation Giveshortanswerstoeachofthefallowing: (a)Giveacarefulmathematicaldefinitionofimagesegmentation. (b) Whatsortsofassumptions are wemakingabout theimage, essentiallyits priormodel,indoing segmentation? (c) Manymethods have been proposedforimagesegmentation.Givethenamesofat least three methods, and summarizetheirrespective assumptions, strengths, andweaknesses. (d)Whereisimage segmentation useful?Suggest threespecific image processing applicationsthat benefitfromthe useofimagesegmentation. (e)Foreachofthefollowingcircumstances,howdoesthe circumstance add challengestotheseg- mentationprocess, and whatstepsmightone needto doto have a successful segmentation?
NationalExams 04-Bio-B4—ImageProcessing May,^2015
5.Application Supposethatyouhaveaquad-copter—aflyinghelicopterwithfourmotors onwhichitiseasyto mountavideocamera. Becauseofwindandthemovement/vibrationofthequad-copter,the video sequencecomingfromthecameraissomewhatjittery,causing the axisofthecamera tomovefrom frametoframebyupto 10 pixels. Wewouldliketo be abletouse thequad-coptertofollowanobject,suchasacar. Your Task: Assume that thereisaseparatesystemforcontrollingtheactualmotionofthequad-copter,this isnot your problem. Youneedto designasystem thattracksanobject overtime:
6.Application Youwork forthe geography departmentofamajorCanadiancity. The mayorofthecitywishes toassessthephotovoltaic(solar energy)potentialofthecity,andhas askedyou tocomeupwitha strategyfor measuring thetotal rooftopareaofbuildingsandhousesinthecity. Ofcourse themostaccurate approachwouldbe have peopletake a survey,walking from buildingto buildingandmeasuringtheroofarea,however thatwouldbefar tooexpensive. Instead,yotihave goodquality airplane/satelliteimagery available,incolouratlOcm resolution,fortheentire city. Withthis imagery you wish totrytomeasureroofareausing image processing. The imagerywasacquired duringthe daytime,nearnoon onasunny day,inthe summer. So lawns are green and shadows areminimized. Your Task: Describe your strategy, eitherinpseudo-codeformorasablock diagram.^ You mayalsoinclude sketches and other informationto make youranswer understandable toaprogrammer.^ State any assumptionsyou make.