Ask Your Question
1

Flora Detection in Images

asked 2012-10-18 12:44:19 -0500

anonymous user

Anonymous

My image dataset is from http://www.image-net.org. There are various synsets for different things like flora, fauna,persons, etc I have to train a classifier which predicts 1 if an image contains flora, like trees, leaves, flowers and 0, otherwise. Images belonging to floral synset can be viewed at http://www.image-net.org/explore, by clicking on the plant,flora,plant life option in the left pane.

These images include wide variety of flora - like trees, herbs, shrubs, flowers etc. I am not able to figure out what features to use to train the classifier. There is a lot of greenery in these images, but there are many flower images, which dont have much green component. Another feature is the shape of the leaves and the petals.

It would be helpful if anyone could suggest how to extract this shape feature and use it to train the classifier. Also suggest what other features could be used to train the classifier. And after extracting features, which algorithm is to be used to train the classifier ?

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
0

answered 2013-02-05 22:00:09 -0500

xamox gravatar image

I would suggest taking a look at our nuts vs. bolts classifier example: https://github.com/ingenuitas/SimpleCV/blob/develop/SimpleCV/examples/machine-learning/machine-learning_nuts-vs-bolts.py

In that we're only using the area, width, and height, but you could easily pick any other features, such as color, keypoint features, etc. With computer vision there is no real canonical way, so as it goes I suggest testing as many methods as you can and use some form of statistics to monitor your performance. As always we would love any methodologies or examples people come up with contributed to the project as it helps other people learn. So whatever method you come up with, we are always interested in seeing your approach. If you'd like to contribute, just see the contribute section on the website.

edit flag offensive delete link more

Comments

Hrm, it appears github may have removed it. I can't seem to find the files on my PC anywhere so may just have to update the example. Stay tuned.

xamox gravatar imagexamox ( 2014-08-07 07:50:34 -0500 )edit

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

Stats

Asked: 2012-10-18 12:44:19 -0500

Seen: 173 times

Last updated: Feb 05 '13