Are you grappling with the challenging task of handling a comprehensive computer vision project, such as the one outlined below? Are you seeking expert guidance to navigate through the intricacies of Harris Corner Detection and Deep Learning classification tasks? Whether you're a student aiming to master image processing techniques or a professional looking to enhance your computer vision skills, CodersArts is here to assist you.
What We Offer
At CodersArts, we understand the complexities involved in computer vision projects, and we specialize in providing tailored solutions to address specific challenges. In the Harris Corner Detection task, we delve into the intricacies of corner detection using both Matlab and Python. Our experts guide you in completing and optimizing the provided code, ensuring functionality and robustness. We also conduct thorough testing on a set of test images, comparing results with built-in functions to provide a comprehensive analysis.
In the Deep Learning Classification task, we guide you through the process of training a Convolutional Neural Network (CNN) using the Fashion-MNIST dataset. Our step-by-step approach covers data preprocessing, network architecture design, loss function setup, and optimization using the Adam optimizer. We emphasize the importance of efficiency, performance, and thoughtful model design, encouraging you to draw key plots to visualize and analyze the training and validation process.
Get Assignment Solution
For the Harris Corner Detection task, we provide complete source code with detailed comments, corner detection results, and thorough comparisons for each test image. In the Deep Learning Classification task, we offer a well-documented report with source code, training and validation accuracy plots, and a trained model for verification. We also provide solutions for other similar Assignments.
Sample Assignment
CLab-2 Tasks
Task 1 Harris Corner Detector. (6 marks)
For Matlab Users:
1. Read and understand the corner detection code ‘harris.m’ in Fig 1.
2. Complete the missing parts, rewrite ‘harris.m’ into a Matlab function, and design appropriate function signature (1 mark).
3. Please provide comments on line #13 and every line of your solution after line #20 (0.5 mark). Specifically, you need to provide short comments on your code, which should make your code readable.
4. Test this function on the provided four test images (Harris-[1,2,3,4].jpg, they can be downloaded from Wattle). Display your results by marking the detected corners on the input images (using circles or crosses, etc) (0.5 mark for each image, (2 marks) in total).
Please make sure that your code can be run successfully on a local machine and generate results. If your submitted code cannot replicate your results, you may need to explain and demonstrate the results in person to tutors.
5. Compare your results with that from Matlab’s built-in function corner() (0.5 mark), and discuss the factors that affect the performance of Harris corner detection (1 mark) .
In your Lab Report, you need to list your complete source code with detailed comments and show corner detection results and their comparisons for each of the test images.
6. Test your built function on ‘Harris-5.jpg’ (Harris-5.jpg can be downloaded from wattle.). Analyse the results why we cannot get corners by discussing and visualising your corner response scores of the image. (0.5mark)
7. Test your built function on ‘Harris-6.jpg’ (Harris-6.jpg can be downloaded from wattle.). Plot your harris corner detector results in your report and propose a solution to obtain the salient corners which is robust to noise. (0.5mark)
For Python users:
1. Read and understand the above corner detection code (Fig. 2).
2. Complete the missing parts, rewrite them to ‘harris.py’ as a python script, and design appropriate function signature (1 mark).
3. Comment on block #5 in the python file (which is corresponding to line #13 in “harris.m”) and every line of your solution in block #7 (0.5 mark). Specifically, you need to provide short comments on your code, which should make your code readable.
4. Test this function on the provided four test images (Harris-[1,2,3,4].jpg, they can be downloaded from Wattle). Display your results by marking the detected corners on the input images (using circles or crosses, etc) (0.5 mark for each image, 2 marks in total).
Please make sure that your code can be run successfully on a local machine and generate results. If your submitted code cannot replicate your results, you may need to explain and demonstrate the results in person to tutors.
5. Compare your results with that from python’s built-in function cv2.cornerHarris() (0.5 mark), and discuss the factors that affect the performance of Harris corner detection (1 mark).
6. Test your built function on ‘Harris-5.jpg’ (Harris-5.jpg can be downloaded from wattle.). Analyse the results why we cannot get corners by discussing and visualising your corner response scores of the image. (0.5mark)
7. Test your built function on ‘Harris-6.jpg’ (Harris-6.jpg can be downloaded from wattle.). Plot your harris corner detector results in your report and propose a solution to obtain the salient corners which is robust to noise. (0.5mark) In your Lab Report, you need to list your complete source code with detailed comments and show corner detection results and their comparisons for each of the test images.
Task 2 - Deep Learning Classification (10 Marks)
In this lab, we will train a CNN with the Fashion-MNIST using the PyTorch1 deep learning framework. The Fashion-MNIST dataset contains 70000 images: 60000 training images and validation images, 10000 testing images2 for fashion classification task. Note that we have 60000 training images with labels. You are required to split the 60k training data further by yourself to reserve 1000 images for validation (they should be from 10 classes). Images are of size 28×28 Greyscale, for 10 classes:
Label Description
0 T-shirt/top
1 Trouser
2 Pullover
3 Dress
4 Coat
5 Sandal
6 Shirt
7 Sneaker
8 Bag
9 Ankle boot
Complete the following exercises:
1. Download the Fashion-MNIST dataset from the following git link: link
1Let tutor know if you want to use tensorflow which is acceptable.
2The reference for the dataset is: Han Xiao, Kashif Rasul, and Roland Vollgraf. "Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms." arXiv preprint arXiv:1708.07747, 2017. 3
2. After loading the data using numpy, normalize the data to the range between (-1, 1). Also perform the following data augmentation when training:
randomly flip the image left and right.
zero-pad 4 pixels on each side of the input image and randomly crop 28x28 as input to the network.
3. Build a CNN with the following architecture:
• 5×5 Convolutional Layer with 32 filters, stride 1 and padding 2.
• ReLU Activation Layer.
• 2×2 Max Pooling Layer with a stride of 2.
• 3×3 Convolutional Layer with 64 filters, stride 1 and padding 1.
• ReLU Activation Layer.
• 2×2 Max Pooling Layer with a stride of 2.
• Fully-connected layer with 1024 output units.
• ReLU Activation Layer.
• Fully-connected layer with 10 output units.
4. Set up cross-entropy loss.
5. Set up Adam optimizer, with 1e-3 learning rate and betas=(0.9, 0.999). (3 marks to here)
6. Train your model.
Draw the following plots:
Training loss vs. epochs.
Training accuracy vs. epochs.
Validation loss vs. epochs.
Validation accuracy vs. epochs.
You can either use Tensorboard to draw the plots or you can save the data (e.g. in a dictionary) then use Matplotlib to plot the curve. (2 marks)
7. Train a good model. Marks will be awarded for high performance and high efficiency in training time and parameters (there may be a trade-off), good design, and your discussion.
You are not allowed to use a pre-trained model, you should train the model yourself. You need to describe what exactly you did to the base model to improve your results in your report, and your motivation for your approach (no more that 1 page of text). Please include plots as above for training and validation loss and accuracy vs. epochs, as well as the final accuracy on the test set. Please submit the code and your trained model for this. Your performance will be verified. Please ensure you follow the test/train splits as provided. You also must show your training and validation accuracy vs. epochs for this model in your report.
Note that you may be asked to run training of your model to demonstrate its training and performance. (4 marks)
8. The main dataset site on github (https://github.com/zalandoresearch/fashion-mnist) includes a series of results for other network models (under Benchmark). How does your model compare? Explain why the ResNet18 model may produce better results than yours (or the other way around if this is the case).(1 mark).
In your Lab Report, you need to list your complete source code with detailed comments.
Deliverables You Can Expect
We provide complete source code with detailed comments, corner detection results, and thorough comparisons for each test image. In the Deep Learning Classification task, we will provide a basic detailing report along with the workflow of the source code, training and validation accuracy plots, and a trained model for verification. We provide all the necessary information and resources for you to excel in this project.
How We Can Help You Overcome Challenges
Expert Guidance: Our experts in computer vision offer comprehensive guidance for tasks like Harris Corner Detection and CNN training.
Efficient Data Processing: We teach techniques to preprocess and augment data, optimizing your computer vision tasks for better performance.
Tailored Support: Our one-on-one support is tailored to your specific project needs, ensuring you have the resources and guidance necessary to succeed.
Why Choose CodersArts Expertise
Our Experts: Our team comprises experienced computer vision experts with a wealth of industry knowledge.
Tailored Solutions: We customize our support to your proficiency level and unique project requirements.
Timely Support: We prioritize meeting deadlines and provide swift assistance to keep your project on track.
In-Depth Understanding: Our commitment goes beyond completing assignments; we ensure you thoroughly comprehend core concepts.
If you're in search of a solution for these assignments or require assistance with similar projects, reach out to us via email at contact@codersarts.com. CodersArts is dedicated to being your trusted partner in conquering complex assignments and projects. Your success is our priority, and we look forward to making a difference in your academic and professional journey.