Difference between revisions of "learning Hierarchical Features for Scene Labeling"

From statwiki
Jump to: navigation, search
(Introduction)
(Introduction)
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