Classifying the Visibility of ID Cards in Photos - Report Writing IT Assignment Help

Assignment Task:
 

To guide you through this challenge, you should refer to the following sub-tasks:

1. Image loading and pre-processing

   1. Write a script that loads the data into a numpy array or pandas data frame. As you will be using a CNN to classify this data, I recommend you to load the images in one variable and the target (i.e. the class of each image, FULL_VISIBILITY, PARTIAL_VISIBILITY or NO-VISIBILITY) in a separate variable.

   2. Analyse the dataset (number of samples per class, size of images, values etc.) and give some initial insights or intuitions on how to approach to this problem (max. 100 words). I recommend you to actually open the image repository and examine the images from different classes so that you can get a better grasp on the problem.

2. Feature Engineering

   1. To counter the bad quality of the mages, you need to apply ANY pre-processing method that you consider suitable (noise removal, colour saturation, image augmentation, class decomposition, data augmentation, etc.) to create a new numpy or pandas data frame which contains a second version of the dataset. In case that you use an augmentation technique, consider that you need to create a new target!

   2. Use stratified train_test_split to partition your two datasets into a 70 (training) / 30 (testing) split.

3. Model Selection/Validation

   1. Implement a CNN which classifies the visibility (FULL_VISIBILITY, PARTIAL_VISIBILITY, NO_VISIBILITY) of the card in the photo. This model must take a grayscale image as input. Justify the choices behind the parameters used (max. 100 words) and assess the quality using accuracy of each class.

   2. Show a table with the comparison of the values obtained and reflect on your findings, indicating which dataset has the best trade-off (max. 100 words).

Guidelines:

1. All answers and code should be put in a jupyter notebook which each section clearly identified.

2. Once you are finished, run all the code from start to finish and produce a html or pdf from the jupyter notebook

3. Submit both the .ipynb file and the html/pdf to the corresponding dropbox by the specified deadline.

This IT Assignment has been solved by our IT Experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.

Be it a used or new solution, the quality of the work submitted by our assignment experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.