learning Hierarchical Features for Scene Labeling: Difference between revisions

From statwiki
Jump to navigation Jump to search
Line 3: Line 3:
'''Test input''': The input into the network was a static image such as the one below:
'''Test input''': The input into the network was a static image such as the one below:


[[File:Example.jpg]]
[[File:cows_in_field.png]]


'''Training data and desired result''': The desired result (which is the same format as the training data given to the network for supervised learning) is an image with large features labelled.
'''Training data and desired result''': The desired result (which is the same format as the training data given to the network for supervised learning) is an image with large features labelled.


<gallery>
<gallery>
Image:Example.jpg|Caption1
Image:labeled_cows.png|Labeled Result
Image:Example.jpg|Caption2
Image:cow_legend.jpg|Legend
</gallery>
</gallery>



Revision as of 14:39, 2 November 2015

Introduction

Test input: The input into the network was a static image such as the one below:

File:cows in field.png

Training data and desired result: The desired result (which is the same format as the training data given to the network for supervised learning) is an image with large features labelled.

Methodology

Pre-processing

Network Architecture

Post-Processing

Results