TreeLogy
Free App
Advertisements
About TreeLogy
“Treelogy” is a mobile application, which can perform leaf-based tree identification among
tree species in Turkey using one picture of a given leaf.
There is only handful of applications interested in tree identification and they are designed
primarily for detecting North American and European tree species. There is no application
which has a good performance and localization support for identifying tree species native to
Turkey. This project is aimed to fill this gap.
While we are constructing this application, we worked on supervised learning for classi-
fication task. We focused on both Deep Learning (specifically Deep Convolutional Neural
Networks) and Support Vector Machines. Tree identification process uses leaf image features
gathered from Caffe, a convolutional neural network framework, and our image processing
module.
After several experiments, we reached the optimal classification accuracy of 93.59% for 57
tree species. Experiments involve 16096 training and 3020 testing leaf images. According to
our findings, we come to the following conclusion. Certain image processing procedures for
extracting features such as shape and texture descriptors, which we have used in our project,
does not produce features as feasible as convolutional neural networks.
"Created by group paY inekereG"
tree species in Turkey using one picture of a given leaf.
There is only handful of applications interested in tree identification and they are designed
primarily for detecting North American and European tree species. There is no application
which has a good performance and localization support for identifying tree species native to
Turkey. This project is aimed to fill this gap.
While we are constructing this application, we worked on supervised learning for classi-
fication task. We focused on both Deep Learning (specifically Deep Convolutional Neural
Networks) and Support Vector Machines. Tree identification process uses leaf image features
gathered from Caffe, a convolutional neural network framework, and our image processing
module.
After several experiments, we reached the optimal classification accuracy of 93.59% for 57
tree species. Experiments involve 16096 training and 3020 testing leaf images. According to
our findings, we come to the following conclusion. Certain image processing procedures for
extracting features such as shape and texture descriptors, which we have used in our project,
does not produce features as feasible as convolutional neural networks.
"Created by group paY inekereG"
All Application Badges
Free
downl.
downl.
Android
2.3+
2.3+
Bug
buster
buster
Android app
App History & Updates
What's Changed
Machine learning and algorithms has been improved for more reliable results
Machine learning and algorithms has been improved for more reliable results
More downloads TreeLogy reached 10 000 - 50 000 downloads
What are users saying about TreeLogy
F
by F####:
by F####:
Not useful in US...not all, even basic, trees are listed
R
by R####:
by R####:
Doesn't work, errors, shuts down
R
by R####:
by R####:
It's useful In other areas.... Not U.s.
H
by H####:
by H####:
Poor leaf recognition. Camera easy to use.
R
by R####:
by R####:
Every tree I try to identify it suggests the same 5 trees which are not at all even close. One tree I tried to identify was an live oak just to test it out and it suggested some kind of flowering tree. Sad it was such a cool idea too!
P
by P####:
by P####:
IT'S A HORRIBLE APP I SUGGEST LEAF SNAP DON'T USE THIS APP EVER.
R
by R####:
by R####:
I looked up the leaves of 5 different trees. I received the same too 5 for each tree. None of the suggested leaves were a match. Trees like pecan and hickory are not even in the glossary.
Y
by Y####:
by Y####:
When I tried to perform a search via with a photo app crashed everytime.
R
by R####:
by R####:
I did one that I knew to test it and what it showed looked nothing like the leaf.
R
by R####:
by R####:
Crashed every time we tried to scan a leaf.
R
by R####:
by R####:
low level of data base
E
by E####:
by E####:
Not at all accurate
R
by R####:
by R####:
Not help everything the identification always wrong
R
by R####:
by R####:
Fast-m-fast
R
by R####:
by R####:
I tried with couple leaves. Both results were a wrong. I don't know if a single leaf could ever tell all the different trees. Good luck getting it to work, that would be neat. But I'm uminstalling it for now.
K
by K####:
by K####:
This is the worst app ever it doesn't give me the right leaf or anything.
R
by R####:
by R####:
Don't waste your time its crap and everything is a goldenrain lmao
R
by R####:
by R####:
Didn't even deserve one star
R
by R####:
by R####:
Very useless and no identify the leaf
R
by R####:
by R####:
Horribly inaccurate.
R
by R####:
by R####:
Wouldn't work
S
by S####:
by S####:
That's what I want
S
by S####:
by S####:
It is good for nature enthusiasts.
S
by S####:
by S####:
Great
by R####:
From a pecan tree to an ailanthus, the first answer given by this app was "wild olive"