android automatic object detection

12
ANDROID AUTOMATIC OBJECT DETECTION CV Project – 2014 By Ohad Zadok .

Upload: tatiana-yeva

Post on 02-Jan-2016

29 views

Category:

Documents


5 download

DESCRIPTION

Android Automatic object detection. CV Project – 2014 By Ohad Zadok. Introduction. Motivation - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Android Automatic object  detection

ANDROID AUTOMATIC OBJECT DETECTION

CV Project – 2014By Ohad Zadok.

Page 2: Android Automatic object  detection

INTRODUCTION

MotivationAutomatic Object Detection can be used to detect small objects in a photo and classify them. It can have security usages when trying to detect enemy units in a satellite images or weapons in security cameras. It can also be used to determine the context in which an image is taken by the objects in it.

Page 3: Android Automatic object  detection

INTRODUCTION

Project GoalThe project goal is to successfully identify objects from a given set after training a model.

Page 4: Android Automatic object  detection

APPROACH AND METHOD

Extracting Descriptors of an image to a vector of descriptors. Creating an SVM model from the set of images. Taking a photo of the new, unidentified object. creating again the same vector of descriptors and run the model on the vector.

More on that at the Doc.

Page 5: Android Automatic object  detection

Algorithms

GrabCut

http://grabcut.weebly.com/uploads/1/3/7/5/13757421/2018613.jpg?1351369992

Page 6: Android Automatic object  detection

Algorithms

GrabCut

Before After

Page 7: Android Automatic object  detection

Algorithms

SVM

http://www.thebookmyproject.com/cars/intrusion-detection-technique-using-k-means-fuzzy-neural-network-svm-classifiers/

Page 8: Android Automatic object  detection

IMPLEMENTATION

• Android System.• Photos from device's native camera. • A vector of descriptors was than calculated

using opencv extension.• SVM model was created using LibSVM library. • The Entire project is run on a device with no

need for external resources.

Page 9: Android Automatic object  detection

IMPLEMENTATION

Page 10: Android Automatic object  detection

IMPLEMENTATION

Page 11: Android Automatic object  detection

CONCLUSION

When applying the system to relatively small number of training sets the results are pretty accurate. When we apply it to a bigger set of objects it become unreliable, Future versions of the system can try to use different descriptors such as contours and get even more reliable results.

Page 12: Android Automatic object  detection

REFERENCES

• http://www.csie.ntu.edu.tw/~cjlin/libsvm/• https://en.wikipedia.org/wiki/Support_vector_machine• http://www.cs.ru.ac.za/research/g02m1682/