|
|
International Journal of Computer Vision & Signal Processing
(ISSN: 2186-1390)
A Novel Wavelet Based Image Fusion for Brain Tumor Detection
Vivek Angoth, CYN Dwith, Amarjot Singh, National Institute of Technology, Warangal, India
|
A Real-time Scheme of Video Stabilization for Mobile Surveillance Robot
Saksham Keshri, National Institute of Technology Karnataka, India
S.N. Omkar, IISc, Bangalore, India
Amarjot Singh, National University of Singapore, Singapore
Vinay Jeengar, Maneesh Kumar Yadav,
National Institute of Technology Karnataka, India
|
Wireless Capsule Endoscopy Segmentation using
Global-Constrained Hidden Markov Model and
Image Registration
Yiwen Wan, Prakash Duraisamy, University of North Texas, USA
Mohammad S Alam, University of South Alabama, USA
Bill Buckles, University of North Texas, USA
|
Choosing Appropriate Homography Transformation
for Building Panoramic Images
Prakash Duraisamy, Yassine Belkhouche, Stephen Jackson, Kamesh Namuduri, Bill Buckles,
University of North Texas, USA
|
Abstract:
Accurate detection of size and location of brain tumor plays a vital
role in the diagnosis of tumor. In this paper, we propose an efficient
wavelet based algorithm for tumor detection which utilizes the complementary and redundant information from the Computed Tomography (CT) image and Magnetic Resonance Imaging (MRI) images. Hence this algorithm effectively uses the information provided by the CT image and MRI images there by providing a resultant fused image which increases the eciency of tumor detection. We also evaluate the effectiveness of proposed algorithm on varying the wavelet fusion parameters
like number of decompositions, type of wavelet used for the decomposition. The experimental results of the simulation on MRI and CT images show the performance efficiency of the proposed approach.
Full Paper (in PDF)
|
Abstract:
The purpose of this research is to develop a mobile surveillance robot capable
of capturing and transmitting video on rough terrains. Recorded
video is affected by jitters resulting into significant error between the
desired and captured video flow. Image registration with a contrario
RANSAC variant has been used to minimize the error between present
and desired output video as it has proved to be a fast algorithm for
video stabilization as compared to the conventional stabilization methods.
This is the first paper which makes use of this method to design
mobile wireless robot for surveillance applications. The video captured
by the robot is stabilized and transmitted to the controller in the control
room. Once the video is stabilized the controller moves the objects from
one place to another with the help of robotic arm mounted to the robot
using a wireless transmitter and receiver. The surveillance capabilities of
the system are also tested in low illumination situations as spying in dark
is an important requirement of todays advanced surveillance systems.
Full Paper (in PDF)
|
Abstract:
This paper describes about analysis of wireless capsule endoscopy (WCE) using
pattern recognition and statistical analysis. Specifically, we introduce a
novel approach to discriminate between oesophagus, stomach, small intestine,
and colon tissue present in WCE. Automatic image analysis can expedite this
task by supporting the clinician and speeding up this process. Video segmentation
of WCE into the four parts of the gastrointestinal tract is one way to aid
the physician. The segmentation approach described in this paper integrates
pattern recognition with statistical analysis. Initially, a support vector machine
is applied to classify video frames into four classes using a combination of
multiple color and texture features as the feature vector. A Poisson cumulative
distribution, for which the parameter depends on the length of segments, models
a prior knowledge. A priori knowledge together with inter-frame difference
serves as the global constraints driven by the underlying observation of each
WCE video, which is fitted by Gaussian distribution to constrain the transition
probability of hidden Markov model. We also used image registration method
to confirm our segmentation results. Experimental results demonstrated effectiveness
of the approach.
Full Paper (in PDF)
|
Abstract:
In building panoramic images, the selection of appropriate homography plays
a crucial role in reducing the error and in registering the images accurately. In
this paper, we demonstrate a method for selecting the appropriate homography
for building the panoramic image based on information extracted from the
images. It is shown that using homographies from the appropriate subgroup,
the undesirable distortions can be reduced which improves the quality of the
panoramic image. We tested our method both on synthetic and real world images.
We also discussed and compared several error metrics to evaluate the
accuracy of registration.
Full Paper (in PDF)
|
|
