COMP3007/COMP4106 Computer Vision Coursework Description
Computer Vision Coursework Description
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
COMP3007/COMP4106
Computer Vision Coursework Description
1 Introduction
Face recognition has always been one of the hottest topics in computer vision for
decades. It is extremely useful in real-world applications, such as security, surveillance,
robotics, etc. With the advanced algorithm development in computer vision, more and
better methods have been proposed to address challenging face recognition problems,
such as poor lighting, different facial poses, occlusions, etc.
In this coursework, you will be provided with a public face database that contains
multiple face images from 100 subjects. The face images were captured in different
conditions (e.g. pose, lighting, time, place, etc.). You will use only ONE face image
from each subject to train/build a computer program and recognise the remaining face
images of these subjects.
2 Key dates
Submission deadline of Matlab code and report: 11th May 2022. (More details
given in the Module Assessment Sheet in Moodle. Note that COMP3007 and
COMP4106 have different assessment sheets)
3 Detailed requirements
Dataset:
You will be provided a face database from 100 subjects for developing and
evaluating your face recognition computer program. You will need to use the
training dataset (one face image per subject) to train your method. It is allowed
to use other face datasets or pre-trained deep learning models for feature
extraction purpose, as long as it does not require installation of third party
libraries outside Matlab environment. The test dataset (total of 1344 images) is
used for evaluation purpose only, which should not be used during the training
process. The true face IDs for the test dataset are saved in ‘testLabel.mat’.
When assessing your method, we will use an independent (hidden from you)
dataset (include both training and test sets) that has the same image format
and folder structure to test your methods.
Method:
You will be guided in a lab session (lab 5) to build a simple face recognition
program, which is a baseline method. You will then be asked to implement an
alternative method which is expected to achieve better recognition accuracy
than the baseline method. Potential methods will be introduced in tutorial 5.
Matlab code:
You need to implement the algorithm using Matlab only. Example files
“Evaluation.m” and “FaceRecognition.m” for the baseline method will be
provided. You must design your main files following the format in the example
files. When assessing your code, we will run the “Evaluation.m” file. Implement
your face recognition method as a function with the format of:
outputIDNew= FaceRecognitionNew(trainImgSet, trainPersonID, testImgSet)
Following this format is important in order for your work to be properly marked.
See the example files of the baseline method. Any build-in Matlab functions can
be used. Save all .m files into a single folder and compress it into a single .zip
file for submission in Moodle. Do not need to submit the face images.
Report:
You also need to submit a report that describes your work. A template in word
and Latex are provided in Moodle, which is an IEEE conference paper format.
You need to follow the template format in terms of font size and layout (double
column). In the report, you must include the following sections: Abstract,
Introduction, Methodology, Method Evaluation, Conclusion and Reference. You
are expected to present a detailed analysis of the result of your method. The
length of the report needs to be minimum of 3 pages but no more than 4
pages (Reference could be in the 5th page). Scientific writing will be
introduced in one of the tutorials. The report needs to be submitted in .pdf
format in Moodle. Turnitin will be used for checking report similarities.
4 Marking Criteria
Matlab code 40%
Recognition accuracy
20%
The mark is objectively produced that is proportional to the
recognition accuracy.
Computational speed
15%
The mark is objectively produced that is proportional to the
computational speed. Computational speed mark is also dependent
on accuracy. Accuracy is more important.
Coding style
5%
Robustness of code and coding style.
Report 60%
20% Description of methodology
15% Explanation and presentation of the results obtained.
15% Discussion of the strengths and weaknesses of the chosen
approach and methods
10% Scientific writing and clarity
5 Plagiarism
Copying code or report from other students, from previous students, from any other source, or soliciting code or
report from online sources and submitting it as your own is plagiarism and will be penalized as such. FAILING TO
ATTRIBUTE a source will result in a mark of zero – and can potentially result in failure of coursework, module or
degree. All submissions are checked using both plagiarism detection software and manually for signs of cheating.