Question

How Can I solve this problem in MATLAB by using a handcrafted image feature method with a classic machine learning approach and a deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network). Task: Your task is to implement and evaluate classifiers for the automatic classification of bird images from this dataset. Specifically, you are asked to implement (both!): 1. A handcrafted image feature method with a classic machine learning approach (e.g. SIFT features with a Support Vector Machine classifier). Assignment 1 - Computer Vision Concepts Implementation (Matlab) 8890 CVIA PG Version 1.1 2. A deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network). The choice of specific method/approach is up to you, as are the specific parameters (for example, will you resize the images first (note: strongly recommended!)? How many layers does your DL network have? What is the learning rate?). The results of the experiments should be described in the performance evaluation report (see below). Both types of approaches need to be evaluated in two scenarios (both!): 1. The entire images are used as input. 2. Only the image area marked by the bounding box information is used as input. Consequently, you will need to perform four experiments to evaluate the performance: Classic handcrafted feature + Deep learning feature and classic ML classifier 1. Whole image as input - Experiment 1 2. Bounding box image area as input - Experiment 2 Performance evaluation here means the class-weighted overall average accuracy and the individual class correct and incorrect recognition rates for the test partition of the data (include a table with these performance measures for all 200 classes). You will then need to run a fifth experiment that performs fivefold cross-validation on Experiment 2. Assume we partition the data in each class into five parts of 20% each. We can then run the experiment five times with different parts used for training, validation, and test, while maintaining the 60:20:20 split. For example: Run 1: Parts 1-3 for training, Part 4 for validation, Part 5 for test Run 2: Parts 2-4 for training, Part 5 for validation, Part 1 for test Run 3: Parts 3-5 for training, Part 1 for validation, Part 2 for test Run 4: Parts 4, 5, and 1 for training, Part 2 for validation, Part 3 for test Run 5: Parts 5, 1, and 2 for training, Part 3 for validation, Part 4 for test

          How Can I solve this problem in MATLAB by using a handcrafted image feature method with a classic machine learning approach and a deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network).

Task: Your task is to implement and evaluate classifiers for the automatic classification of bird images from this dataset. Specifically, you are asked to implement (both!):

1. A handcrafted image feature method with a classic machine learning approach (e.g. SIFT features with a Support Vector Machine classifier). Assignment 1 - Computer Vision Concepts Implementation (Matlab) 8890 CVIA PG Version 1.1

2. A deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network).

The choice of specific method/approach is up to you, as are the specific parameters (for example, will you resize the images first (note: strongly recommended!)? How many layers does your DL network have? What is the learning rate?).

The results of the experiments should be described in the performance evaluation report (see below).

Both types of approaches need to be evaluated in two scenarios (both!):

1. The entire images are used as input.
2. Only the image area marked by the bounding box information is used as input.

Consequently, you will need to perform four experiments to evaluate the performance:

Classic handcrafted feature + Deep learning feature and classic ML classifier
1. Whole image as input - Experiment 1
2. Bounding box image area as input - Experiment 2

Performance evaluation here means the class-weighted overall average accuracy and the individual class correct and incorrect recognition rates for the test partition of the data (include a table with these performance measures for all 200 classes).

You will then need to run a fifth experiment that performs fivefold cross-validation on Experiment 2. Assume we partition the data in each class into five parts of 20% each. We can then run the experiment five times with different parts used for training, validation, and test, while maintaining the 60:20:20 split. For example:

Run 1: Parts 1-3 for training, Part 4 for validation, Part 5 for test
Run 2: Parts 2-4 for training, Part 5 for validation, Part 1 for test
Run 3: Parts 3-5 for training, Part 1 for validation, Part 2 for test
Run 4: Parts 4, 5, and 1 for training, Part 2 for validation, Part 3 for test
Run 5: Parts 5, 1, and 2 for training, Part 3 for validation, Part 4 for test
        
Show more…
how can i solve this problem in matlab by using a handcrafted image feature method with a classic machine learning approach and a deep learning based approach where both features and classif 53066

Added by Amanda W.

Close

Computer Science and Information Technology
Computer Science and Information Technology
Trishna Knowledge Systems 2018 Edition
AceChat toggle button
Close icon
Ace pointing down

Please give Ace some feedback

Your feedback will help us improve your experience

Thumb up icon Thumb down icon
Thanks for your feedback!
Profile picture
How Can I solve this problem in MATLAB by using a handcrafted image feature method with a classic machine learning approach and a deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network). Task: Your task is to implement and evaluate classifiers for the automatic classification of bird images from this dataset. Specifically, you are asked to implement (both!): 1. A handcrafted image feature method with a classic machine learning approach (e.g. SIFT features with a Support Vector Machine classifier). Assignment 1 - Computer Vision Concepts Implementation (Matlab) 8890 CVIA PG Version 1.1 2. A deep learning-based approach, where both features and classifier are learned together (e.g. a Convolutional Neural Network). The choice of specific method/approach is up to you, as are the specific parameters (for example, will you resize the images first (note: strongly recommended!)? How many layers does your DL network have? What is the learning rate?). The results of the experiments should be described in the performance evaluation report (see below). Both types of approaches need to be evaluated in two scenarios (both!): 1. The entire images are used as input. 2. Only the image area marked by the bounding box information is used as input. Consequently, you will need to perform four experiments to evaluate the performance: Classic handcrafted feature + Deep learning feature and classic ML classifier 1. Whole image as input - Experiment 1 2. Bounding box image area as input - Experiment 2 Performance evaluation here means the class-weighted overall average accuracy and the individual class correct and incorrect recognition rates for the test partition of the data (include a table with these performance measures for all 200 classes). You will then need to run a fifth experiment that performs fivefold cross-validation on Experiment 2. Assume we partition the data in each class into five parts of 20% each. We can then run the experiment five times with different parts used for training, validation, and test, while maintaining the 60:20:20 split. For example: Run 1: Parts 1-3 for training, Part 4 for validation, Part 5 for test Run 2: Parts 2-4 for training, Part 5 for validation, Part 1 for test Run 3: Parts 3-5 for training, Part 1 for validation, Part 2 for test Run 4: Parts 4, 5, and 1 for training, Part 2 for validation, Part 3 for test Run 5: Parts 5, 1, and 2 for training, Part 3 for validation, Part 4 for test
Close icon
Play audio
Feedback
Powered by NumerAI
Jennifer Stoner Danielle Fairburn
Kathleen Carty verified

Aarya B and 54 other subject AP CS educators are ready to help you.

Ask a new question

*

Labs

-

Want to see this concept in action?

NEW

Explore this concept interactively to see how it behaves as you change inputs.

View Labs

*

Key Concepts

-
Key Concept
Premium Feature
Explore the core concept behind this problem.
Play button
Key Concept
Premium Feature
Explore the core concept behind this problem.
Your browser does not support the video tag.

*

Recommended Videos

-
1-in-the-previous-matlab-grader-problemswe-have-created-our-own-classifier-method-based-on-fitting-pca-models-to-different-classesnow-lets-trv-it-out-on-a-new-dataset-the-humanactivity-datas-82537

In the previous Matlab grader problems, we have created our own classifier method based on fitting PCA models to different classes. Now let's try it out on a new dataset! The humanactivity dataset contains thousands of samples of a known-class, 60 feature dataset. The 'class' is 1 of 5 possible human activities: sitting, walking, dancing, running, and standing. The 'features' are features derived from acceleration measurements from the accelerometer sensor of a smartphone located in the participant's pocket taken during the course of the recorded activity. If interested, you can find more information about this dataset here. Your goal is to create a classifier program that could be run on a smartphone to classify a person's activity from sensor measurements. Load the humanactivity dataset into MATLAB and divide it into a training and testing set using the following code. load humanactivity D_train = feat(1:2:end,:); class_train = actid(1:2:end); D_test = feat(2:2:end,:); class_test = actid(2:2:end); Use your my_fitpca function create a classification model with the training set. Use your classification model with your my_predictpca function to estimate classifications on the testing set What is your classification accuracy on the testing set (percent correct), accurate to 2 decimal places?

Aarya B.

overview-in-this-analysis-you-will-develop-logistic-regression-model-based-on-the-data-set-provided-to-predict-whether-or-not-the-specimens-are-genuine-how-can-i-attach-a-data-file-data-set-32789

Title: Logistic Regression Model for Predicting Genuine Banknote-like Specimens Overview: In this analysis, you will develop a logistic regression model based on the data set provided to predict whether or not the specimens are genuine. Data Set Information: Data (A6DATA.csv) were extracted from images that were taken from genuine and forged banknote-like specimens. For digitization, an industrial camera usually used for print inspection was used. The final images have 400x400 pixels. Due to the object lens and distance to the investigated object, grayscale pictures with a resolution of about 660 dpi were gained. Wavelet Transform tools were used to extract features from images. Attribute Information: V1: variance of Wavelet Transformed image (continuous) V2: skewness of Wavelet Transformed image (continuous) V3: kurtosis of Wavelet Transformed image (continuous) V4: entropy of image (continuous) V5: class (0-forged, 1-genuine) PART 1 Read the A6DATA.csv data file into RStudio. Run set.seed(222) for partitioning of the dataset into training (50%) and testing (50%). Report on the number of forged and genuine banknote-like specimens in the training and testing data. PART 2 Develop a logistic regression model using the training data. Provide the final logistic regression model (with only significant variables), equation for calculating the probability that a specimen is genuine, confusion matrix for both training and testing data, misclassification error for both training and testing data, and comment on the performance of the model. PART 3 Develop logistic regression models with 60%/40%, 70%/30%, and 80%/20% partitioning into training and testing data sets using set.seed(222). Summarize training and testing accuracy, sensitivity, and specificity for each and compare with 50%/50% performance using the table below. Recommend and comment on the best model for future use. Partitioning Accuracy % Sensitivity % Specificity % Training - 50% Testing - 50% Training - 60% Testing - 40% Training - 70% Testing - 30% Training - 80% Testing - 20% PART 4 Compare the best and the worst logistic regression model in the previous question using ROC curve, AUC, and best threshold values based on testing data. Discuss your results.

Shyam P.

use-the-nonlinear-autoregressive-network-with-exogenous-inputs-narx-dataset-with-the-following-command-in-matlab-data-simplenarx_dataset-the-narx-dataset-has-a-1x100-cell-array-of-scalar-val-40837

Akash M.


*

Recommended Textbooks

-
Computer Science and Information Technology

Computer Science and Information Technology

Trishna Knowledge Systems 2018 Edition
achievement 1,358 solutions
Introduction to Programming Using Python

Introduction to Programming Using Python

Y. Daniel Liang 1st Edition
achievement 1,418 solutions
Computer Science - An Overview

Computer Science - An Overview

Glenn Brookshear, Dennis Brylow 12th Edition
achievement 1,269 solutions

*

Transcript

-
00:02 In this question, solution here is to determine the classification accuracy on testing set, you would need to use your my underscore predict pca function to classify the samples in the d underscore test matrix and then compare the predicted class labels to the true class labels in class test, you would then calculate, you would then calculate the percentage of samples that are classified correctly, it is not possible to give, it is not possible to give the exact accuracy without running the above code, above code and also it depends on the my fit pca and my predict pca function which are not provided…
Need help? Use Ace
Ace is your personal tutor. It breaks down any question with clear steps so you can learn.
Start Using Ace
Ace is your personal tutor for learning
Step-by-step explanations
Instant summaries
Summarize YouTube videos
Understand textbook images or PDFs
Study tools like quizzes and flashcards
Listen to your notes as a podcast
Continue solving this problem
Create a free account to:
  • View full step-by-step solution
  • Ask follow-up questions with Ace AI
  • Save progress and study later
Continue Free
Join the community

18,000,000+

Students on Numerade


Trusted by students at 8,000+ universities

Numerade

Get step-by-step video solution
from top educators

Continue with Clever
or



By creating an account, you agree to the Terms of Service and Privacy Policy
Already have an account? Log In

A free answer
just for you

Watch the video solution with this free unlock.

Numerade

Log in to watch this video
...and 100,000,000 more!


EMAIL

PASSWORD

OR
Continue with Clever