COMP 9517T1, 2020 Assignment 1: SpecificationMaximum marks achievable: 10 marksThis assignment is worth 10% of the total course marks.Deliverables: You will submit a report (maximum 5 pages) briefly explaining the approach youhave taken in Tasks 1, 2 and 3 and include some sample input images and the intermediate andfinal images obtained. You must also submit the Python source code files.Submission: The assignment files should be submitted online via WebCMS. Instructions forsubmission will be posted closer to the deadline.Tip: You are advised to use OpenCV 3+ with python 3+. Jupyter notebook files arepreferred as source files.Objectives:This assignment is aimed at familiarisation with basic image processing methods. It alsointroduces you to common image processing and analysis tasks using OpenCV. Aftercompleting this assignment, you will learn how to:1. Open and read image files2. Perform simple mathematical operations on images3. Construct and manipulate image pyramids4. Carry out translation-based alignment5. Perform image adjustment and restorationTask:Sergei Prokudin-Gorsky (1863-1944) was a Russian photographer and chemist whosecollection of colour photographs is the oldest surviving to this date. He used a camera that tooka sequence of three black and white exposures using blue, red and green filters. By projectingthe three images using colored light it was then possible to recover the original colours. Seehere for more details. At the beginning of the 20th century, Prokudin-Gorsky embarked on amulti-year project to systematically document the life of the Russian Empire by means of thenew colour imaging technology. He then took many of the resulting negatives with him onemigration following the revolution of 1917 and they were eventually purchased and digitizedby the US Library of Congress.The objective of this assignment is to produce high quality colour reconstructions fromThe assignment files should be submitted online.Instructions for submission will be posted closer to the deadline.Deadline for submission is week 4 Monday March 9th, 23:59:59Prokudin-Gorskys negatives using simple image processing techniques.You will need to extract images for the individual colour channels, align them and form a singlecolour image. For this assignment, it is sufficient to use an x, y translation-based transformbutfeel free to implement other methods. You must use OpenCV with Python to complete thisassignment.Instructions:Task 1 (4 marks)Download the high-resolution negatives from Webcms3 (Course Work → Assessments →A代写COMP 9517作业、代做WebCMS留学生作业、代写Python语言作业、Python编程设计作业调试 代做SPssignment 1 → Assignment 1 Images (20T1)). Write a program that takes any one of thesefiles as an input and produces a corresponding colour image as output. To do this you shoulddivide the original image into three channels and then align the second and third channels tothe first, displaying the resulting offsets for each channel.Figure 1: High quality colour reconstruction example.A simple way to perform the alignment is by searching through all possible offsets in somesuitable range (e.g. 20 pixels for low resolution images) and computing for each a scoremeasuring the quality of the match. Three suitable metrics include sum of squared differences(SSD), sum of absolute differences (SAD) and the normalized cross correlation (NCC).Task 2 (4 marks)Searching through all offsets can become computationally expensive for high resolutionimages. To speed up the search procedure you can use a so-called image pyramid. An imagepyramid is essentially the image at multiple scales, with scales varying by a factor of two.Alignment can then be done sequentially, starting with the highest level and incrementallyupdating your estimates as you go down the pyramid.You should first implement an algorithm that can perform reconstruction on low resolutionimages (Task 1) and only then try to modify your code to handle high resolution images (Task2). It should be easy to reuse much of the code.Task 3 (2 marks)Try to improve the visual quality of the results of the basic algorithm. Some possibilitiesinclude colour and contrast adjustments, using a more sophisticated alignment procedure andautomatically removing borders.Hint: For Task 3, you will need to choose images from the Library of Congress collection thatbest demonstrate your enhancements.This assignment is worth 10% of the course total. Tasks 1, 2 and 3 must be completed tocomplete the assignment and will be marked against the maximum mark achievable.Deliverables: You should submit a short report (up to 5 pages MAXIMUM) along withyour python code. This report should briefly explain the approach you have taken to aligncolour channelsfor Task 1, the modifications you performed to deal with high resolution imagesin Task 2, and the adjustments you made for Task 3. You may also include details of anyenhancements you have implemented. Include results for at least two (2) of the provided highresolutionnegatives.The instructions for uploading the report will be released before the submission date.Copyright: Arcot Sowmya, CSE, UNSW, with acknowledgements to COMP 9517 teachingteam past and present.21 February 2020转自：http://www.3zuoye.com/contents/3/4825.html