Created
December 1, 2016 07:57
-
-
Save Zerk123/5b372b3f4da27be05b77b4d395de8613 to your computer and use it in GitHub Desktop.
Car Detection From an Image using SURF(Speeded Up Robust Feature) Matlab
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
% Team Owais, Zerk, Shaleem, Faisal, Farman | |
% Accuracy 0.9472 (94%) | |
% Uses bag of features for training. | |
% Path to data-set folder | |
path = 'data-set'; | |
imgSets = imageSet(path, 'recursive'); | |
% Partition our data to 30/70, Where 30% data is for training and 70 for | |
% test set. Increasing training set will increase accuracy. | |
[trainingSets, testSets] = partition(imgSets, 0.3, 'randomize'); | |
% Extract features from training set images. | |
bag = bagOfFeatures(trainingSets,'Verbose',false); | |
% Generate category classifier from training images. | |
categoryClassifier = trainImageCategoryClassifier(trainingSets, bag); | |
% Test classifier on test image. | |
confMatrix = evaluate(categoryClassifier, testSets) | |
% Show mean of diagnols, Diagnol contains success. | |
mean(diag(confMatrix)) | |
% Test classifier against our random input | |
img = imread('nv.png'); | |
[labelIdx, score] = predict(categoryClassifier, img); | |
% Result: Non Vehicle -> Success | |
categoryClassifier.Labels(labelIdx) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment