| |
 Programme
Overview
Detailed
Programme
| Computer Vision
and Image Processing (CVIP) |
CHAIR: PAULO CARVALHO
Wednesday, March 23rd, 11h00-12h40
| CVIP-1 |
| |
| Title: |
|
|
Simulating binocular eye movements
based on 3-D short-term memory image in reading |
| Author(s): |
Satoru Morita |
| Abstract: |
We simulate binocular eye movements in reading.
We introduce the 3-D edge features reconstructed from the
foveated visions of two eyes to determine the next fixation
point in reading. The next fixation point is determined statistically
from the feature points in the 3-D short-term memory edge
image. We show the effectiveness of simulating binocular eye
movements based on 3-D short-term memory image. |
 |
| CVIP-2 |
| |
| Title: |
|
|
An Algorithm For Face Pose Adjustment
Based On Eye Location |
| Author(s): |
Wenming Cao,
Chunyan Xu,
Shoujue Wang |
| Abstract: |
Face pose adjustment, as a loop of human face
location, is very important in computer face recognition.
In this paper, we present a new approach to automatic face
pose adjustment on gray-scale static images with a single
face. In the first stage, we make every little image with
the degree of mediacy, then ask for one piece of image including
two eyes using match degree. Finally ad-just this piece correctly.
In the second stage, the inclination angle is calculated and
the face position is redressed. The experimentations show
that the algo-rithm performs very well both in terms of rate
and of efficiency. |
|
| CVIP-3 |
| |
| Title: |
|
|
Learning Image Filtering from a
Gold Sample Based on Genetic Optimization of Morphological
Processing |
| Author(s): |
S. Rahnamayan,
H.R. Tizhoosh,
M. Salama |
| Abstract: |
This paper deals with designing a semi-automated
noise filtering approach, which receives just original noisy
image and corresponding gold(user manipulated) image to learn
filtering task. It tries to generate optimized mathematical
morphology procedure for image filtering by applying genetic
algorithm as an optimizer. After training and generating morphological
procedure, the approach is ready to apply the learned procedure
on new noisy images. It takes just one gold sample to learn
filtering and dose not need any prior context knowledge; that
is the main advantage of this approach. Using the morphological
operators makes filtering procedure robust, effective, and
computationally efficient. Furthermore, the proposed filter
shows little distortion on noise free parts of image, so it
can extract objects from heavily noisy environments. Architecture
of the system and details of implementation are presented.
The approach feasibility is tested by well-prepared synthetic
noisy images; results are given and discussed |
|
|
|