vehicle classification

8
VEHICLE CLASSIFICATION Owais Chishti Zerk Shaban Shaleem John Faisal Usman Farman Ali

Upload: syed-owais-ali-chishti

Post on 13-Apr-2017

64 views

Category:

Education


1 download

TRANSCRIPT

Page 1: Vehicle Classification

VEHICLE CLASSIFICATION

Owais ChishtiZerk ShabanShaleem JohnFaisal UsmanFarman Ali

Page 2: Vehicle Classification

USING EDGE DETECTION img = imfilter(img, fspecial('laplacian')); Black and white image with edges

img = imfilter(img, fspecial('sobel')); High horizontal edges

img = threshold(img, 200, 0); Apply threshold at 200

img = bwareaopen(img, 30); Remove noise in 30x30 grid

We get a image with shadow highlighted.

Page 3: Vehicle Classification

USING BAG OF FEATURES What is bag of words/features? Image features as words Occurrence

Processing Steps Feature detection Feature description - SURF Codebook/Dictionary

bagOfFeatures.m Extract image features

Types Find Texture – Similar chunk of images Point of Interest

Page 4: Vehicle Classification

FREQUENCY IN ARTICLE

Page 5: Vehicle Classification

GENERATING IMAGE CLASSIFIER SVM – Support Vector Machine Supervised learning Bag of features Plot features to graph Separate features through a line

Page 6: Vehicle Classification

SOURCE CODE imgSets = imageSet('c:/data-set', 'recursive'); [trainingSets, testSets] = partition(imgSets, 0.3, 'randomize'); bag = bagOfFeatures(trainingSets); categoryClassifier = trainImageCategoryClassifier(trainingSets, bag); confMatrix = evaluate(categoryClassifier, testSets)

Taken from: https://www.mathworks.com/help/vision/ref/trainimagecategoryclassifier.html

Page 7: Vehicle Classification