Difference between revisions of "Evaltex"
From LRDE
| Line 5: | Line 5: | ||
=== Input === |
=== Input === |
||
The framework takes as input XML files containing the coordinates of the bounding boxes surrounding the text objects and compares it to another XML file representing the ground truth (GT). The GT XML format differs slightly from the result format. Its attributes are: |
The framework takes as input XML files containing the coordinates of the bounding boxes surrounding the text objects and compares it to another XML file representing the ground truth (GT). The GT XML format differs slightly from the result format. Its attributes are: |
||
| − | * name |
+ | * name the image name |
| − | * size |
+ | * size image size |
| − | * region |
+ | * region 1st level components |
Revision as of 12:37, 8 January 2016
EvaLTex (Evaluating Text Localization) is an evaluation tool used to measure the performance of text detection algorithms. It takes as input text detection results that can be represented either by coordinates or by masks and outputs performance scores.
EvaLTex framework
Input
The framework takes as input XML files containing the coordinates of the bounding boxes surrounding the text objects and compares it to another XML file representing the ground truth (GT). The GT XML format differs slightly from the result format. Its attributes are:
- name the image name
- size image size
- region 1st level components
Mask representation
In addition to bounding boxes, text objects can also be represented using masks. EvaLTex takes as input binary images (white corresponds to text).