Posted: July 13th, 2022

6302ENG/7510ENG Image Processing and Machine Vision | Assignment Help Services

Image Processing and Machine Vision
6302ENG/7510ENG
Project Information
Project Overview
For the major project in this course, you are required to complete one of the three tasks described in
the following sections. Regardless of the task chosen, these requirement apply:
• You may work either individually or in pairs. If you work in pairs, a higher standard will be
expected. This means more features should be added to your program, and the report
should be more detailed. Examples of this will be given in the lab classes. The amount of
work to be done by each person will be similar for individual and group projects.
• Lab demonstrators will be able to guide you as to the required level of complexity of your
project. More complex projects will be eligible for higher marks, but will be more difficult to
complete.
• The project should be completed in Python using OpenCV.
• The project will be demonstrated during the final laboratory session of the trimester (week
12)
• The final report is due on Friday of week 12 (midnight).
• Although sample data may be supplied, you are also responsible for collecting additional
training and testing images for your project.
• Equipment required will be a PC running Python/OpenCV as well as an optional video
camera for capturing live images. If a suitable high quality video capture device is
unavailable, you may use either pre-recorded video files or individual images.
Report Structure
Your report should be structured as a normal laboratory report, with an introduction outlining the
aims and objectives, a brief literature review of the relevant theory, methodology describing your
approach, then results, discussion and conclusion. References should be included, in the IEEE format.
Particular focus should be put on the design methodology, clearly explaining the machine vision
techniques you have employed to create your program. Results should be both quantitative and
qualitative and have proper statistics to describe the accuracy of your designed system. Ensure that
training and testing parameters are well specified, and all relevant information on the images used is
provided.
Full program code should not be put in your report, but instead included as an appendix (and
submitted as separate files). However the general algorithms used should be described, and any
particularly complex or important pieces of code can be listed in full.
If working in pairs, you should also clearly indicate which team members worked on which sections
of the project.
Project Option 1: Automatic Detection and Classification of Objects
Aim
The aim of this project is design and implement a system which can detect and identify objects of
various shapes, as well as providing various metrics for each detected shape.
Procedure
Complete the following procedure and write a report to explain the theory, implementation and
debug details, and results. Submit your report together with your code before the due date. Show
the demonstrator your working system to be signed off.
Design and build a simple industry parts detection and classification system for assembly lines. The
system must be able to inspect/capture the movable objects (such as, tins, balls, cubes and others)
on the table, detect the objects with a shape specified by the user (e.g. circular shape, rectangular
shape, and triangular shape), count the number of such objects and mark their locations in the
image.
Extra Features
Consider adding one or more of the following features to your program. Those doing the project in
pairs should include at least 1-2 of these in order to be eligible for full marks in the project.
• Invariance to colour, translation, rotation, and scale.
• Texture analysis to distinguish between objects of similar shape.
• Calculation of metrics for different shapes (size, colour, aspect ratio, other parameters).
• 3D shape detection, invariant to rotation in all three dimensions (hard).
Project Option 2: Face Detection in Live Video
Aim
The aim of this project is to design and implement a machine vision system which can reliably detect
faces in a video stream.
Procedure
Complete the following procedure and write a report to explain the theory, implementation and
debugging details, and results. Submit your essay writing help report together with your code before the due date. You
will also need to demonstrate your project in the last week of the couse.
Design and build a simple human face detection system for live video from the USB camera. The
system must be able to detect faces moving around in the field of view and mark their locations in
the image. (hint: use colour information for segmentation and morphological operations to
determine the shape, and other processing if necessary.) You can use the paper listed below as a
startling point, or use any other technique you think is appropriate.
N. Herodotou, K. N. Plataniotis and A. N. Venetsanopoulos, “Automatic Location and Tracking of
Facial Region in Color Video Sequence”, Signal Processing: Image Communication 14 (1999) 359-388.
Extra Features
Consider adding one or more of the following features to your program. Those doing the project in
pairs should include at least 1-2 of these in order to be eligible for full marks in the project.
• The ability to detect multiple faces in the video.
• Overlay an image over each detected face (similar to a snapchat filter, etc). This overlay
should be sized and positioned correctly to fit the detected face(s).
• Determine some basic properties of the face such as eye separation distance, face aspect
ratio, and other common biometric markers.
• Identification of previously trained faces as well as detection (harder).
Project Option 3: Leaf Recognition
Aim
The aim of this project is to develop a machine vision system capable of identifying leaves from
images, by matching the image with a database of known leaf images.
Procedure
Complete the following procedure and write a report to explain the theory, implementation and
debugging details, and results. Submit your report together with your code before the due date. You
will also need to demonstrate your project in the last week of the couse.
Design and implement the functions to extract and match shape features of leaf images using
OpenCV and Python. You can download the database of sample leaf images from the course
website, and use these for matching purposes. Your program should then display the top 15 match
results from this database for the supplied image. You will also need to implement a function to
calculate the rank-1 accuracy of your method on the feature dataset (use leave-one-out approach).
The technique to match leaf images should be based on the paper below. An example of this
software in action can be seen at:
https://www.youtube.com/watch?v=BL5oQ48NUs4&feature=youtu.be
Wang, B., Brown, D., Gao, Y. and La Salle, J., 2015 – Research Paper Writing Help Service. MARCH: Multiscale-arch-height description for
mobile retrieval of leaf images. Information Sciences, 302, pp.132-148.
Extra Features
Consider adding one or more of the following features to your program. Those doing the project in
pairs should include at least 1-2 of these in order to be eligible for full marks in the project.
• Implement a function to display the bullseye retrieval score of your method on the feature
dataset. Only count the first 12 features in each class.
• Investigate the rotation and affine transform invariance of the technique, and develop
mechanisms to improve performance in the presence of such transformations.

Order | Check Discount