Abstract: Real-time object tracking is a problem which involves extraction of critical information from complex and uncertain imagedata. In this paper, we present a comprehensive methodology to design an artificial neural network (ANN) for a real-time object tracking application. The object, which is tracked for the purpose of demonstration, is a specific airplane. However, the proposed ANN can be trained to track any other object of interest. The ANN has been simulated and tested on the training and testing datasets, as well as on a real-time streaming video. The tracking error is analyzed with post-regression analysis tool, which finds the correlation among the calculated coordinates and the correct coordinates of the object in the image. The encouraging results from the computer simulation and analysis show that the proposed ANN architecture is a good candidate solution to a real-time object tracking problem.
Abstract: Linear approximation of point spread function (PSF) is a new method for determining subpixel translations between images. The problem with the actual algorithm is the inability of determining translations larger than 1 pixel. In this paper a multiresolution technique is proposed to deal with the problem. Its performance is evaluated by comparison with two other well known registration method. In the proposed technique the images are downsampled in order to have a wider view. Progressively decreasing the downsampling rate up to the initial resolution and using linear approximation technique at each step, the algorithm is able to determine translations of several pixels in subpixel levels.
Abstract: The scientific community has invested a great deal of effort in the fields of discrete wavelet transform in the last few decades. Discrete wavelet transform (DWT) associated with the vector quantization has been proved to be a very useful tool for the compression of image. However, the DWT is very computationally intensive process requiring innovative and computationally efficient method to obtain the image compression. The concurrent transformation of the image can be an important solution to this problem. This paper proposes a model of concurrent DWT for image compression. Additionally, the formal verification of the model has also been performed. Here the Symbolic Model Verifier (SMV) has been used as the formal verification tool. The system has been modeled in SMV and some properties have been verified formally.
Abstract: In the present paper, we propose numerical methods for solving the Stein equation AXC - X - D = 0 where the matrix A is large and sparse. Such problems appear in discrete-time control problems, filtering and image restoration. We consider the case where the matrix D is of full rank and the case where D is factored as a product of two matrices. The proposed methods are Krylov subspace methods based on the block Arnoldi algorithm. We give theoretical results and we report some numerical experiments.
Abstract: Minor problems arising from optimizations by
welding of fixed prostheses frameworks can be identified by
macroscopic and microscopic visual inspection. The purpose of this
study was to highlight the visible discontinuities present in the laser
welds of dental Ni-Cr alloys. Ni-Cr base metal alloys designated for
fixed prostheses manufacture were selected for the experiments.
Using cast plates, preliminary tests were conducted by laser welding.
Macroscopic visual inspection was done carefully to assess the
defects of the welding rib. Electron microscopy images allowed
visualization of small discontinuities, which escapes visual
inspection. Making comparison to Ni-Cr alloys taken in the
experiment and laser welded, after visual analysis, the best welds
appear for Heraenium NA alloy.
Abstract: This research attempts to study the feasibility of
augmenting an augmented reality (AR) image card on a Quick
Response (QR) code. The authors have developed a new visual tag,
which contains a QR code and an augmented AR image card. The new
visual tag has features of reading both of the revealed data of the QR
code and the instant data from the AR image card. Furthermore, a
handheld communicating device is used to read and decode the new
visual tag, and then the concealed data of the new visual tag can be
revealed and read through its visual display. In general, the QR code is
designed to store the corresponding data or, as a key, to access the
corresponding data from the server through internet. Those reveled
data from the QR code are represented in text. Normally, the AR
image card is designed to store the corresponding data in
3-Dimensional or animation/video forms. By using QR code's
property of high fault tolerant rate, the new visual tag can access those
two different types of data by using a handheld communicating device.
The new visual tag has an advantage of carrying much more data than
independent QR code or AR image card. The major findings of this
research are: 1) the most efficient area for the designed augmented AR
card augmenting on the QR code is 9% coverage area out of the total
new visual tag-s area, and 2) the best location for the augmented AR
image card augmenting on the QR code is located in the bottom-right
corner of the new visual tag.
Abstract: In this paper a fast motion estimation method for
H.264/AVC named Triplet Search Motion Estimation (TS-ME) is
proposed. Similar to some of the traditional fast motion estimation
methods and their improved proposals which restrict the search points
only to some selected candidates to decrease the computation
complexity, proposed algorithm separate the motion search process to
several steps but with some new features. First, proposed algorithm try
to search the real motion area using proposed triplet patterns instead of
some selected search points to avoid dropping into the local minimum.
Then, in the localized motion area a novel 3-step motion search
algorithm is performed. Proposed search patterns are categorized into
three rings on the basis of the distance from the search center. These
three rings are adaptively selected by referencing the surrounding
motion vectors to early terminate the motion search process. On the
other hand, computation reduction for sub pixel motion search is also
discussed considering the appearance probability of the sub pixel
motion vector. From the simulation results, motion estimation speed
improved by a factor of up to 38 when using proposed algorithm than
that of the reference software of H.264/AVC with ignorable picture
quality loss.
Abstract: The colors of the human skin represent a special
category of colors, because they are distinctive from the colors of
other natural objects. This category is found as a cluster in color
spaces, and the skin color variations between people are mostly due
to differences in the intensity. Besides, the face detection based on
skin color detection is a faster method as compared to other
techniques. In this work, we present a system to track faces by
carrying out skin color detection in four different color spaces: HSI,
YCbCr, YES and RGB. Once some skin color regions have been
detected for each color space, we label each and get some
characteristics such as size and position. We are supposing that a face
is located in one the detected regions. Next, we compare and employ
a polling strategy between labeled regions to determine the final
region where the face effectively has been detected and located.
Abstract: In this paper we present a novel technique for data
hiding in binary document images. We use the concept of entropy in
order to identify document specific least distortive areas throughout
the binary document image. The document image is treated as any
other image and the proposed method utilizes the standard document
characteristics for the embedding process. Proposed method
minimizes perceptual distortion due to embedding and allows
watermark extraction without the requirement of any side information
at the decoder end.
Abstract: In recent five decades, textured yarns of polyester fiber produced by false twist method are the most
important and mass-produced manmade fibers. There are
many parameters of cross section which affect the physical and mechanical properties of textured yarns. These parameters
are surface area, perimeter, equivalent diameter, large
diameter, small diameter, convexity, stiffness, eccentricity, and hydraulic diameter. These parameters were evaluated by
digital image processing techniques. To find trends between production criteria and evaluated parameters of cross section, three criteria of production line have been adjusted and different types of yarns were produced. These criteria are
temperature, drafting ratio, and D/Y ratio. Finally the relations between production criteria and cross section parameters were
considered. The results showed that the presented technique can recognize and measure the parameters of fiber cross section in acceptable accuracy. Also, the optimum condition
of adjustments has been estimated from results of image analysis evaluation.
Abstract: This paper deals with the application for contentbased
image retrieval to extract color feature from natural images
stored in the image database by segmenting the image through
clustering. We employ a class of nonparametric techniques in which
the data points are regarded as samples from an unknown probability
density. Explicit computation of the density is avoided by using the
mean shift procedure, a robust clustering technique, which does not
require prior knowledge of the number of clusters, and does not
constrain the shape of the clusters. A non-parametric technique for
the recovery of significant image features is presented and
segmentation module is developed using the mean shift algorithm to
segment each image. In these algorithms, the only user set parameter
is the resolution of the analysis and either gray level or color images
are accepted as inputs. Extensive experimental results illustrate
excellent performance.
Abstract: Bleeding in the digestive duct is an important diagnostic parameter for patients. Blood in the endoscopic image can be determined by investigating the color tone of blood due to the degree of oxygenation, under- or over- illumination, food debris and secretions, etc. However, we found that how to pre-process raw images obtained from the capsule detectors was very important. We applied various image process methods suitable for the capsule endoscopic image in order to remove noises and unbalanced sensitivities for the image pixels. The results showed that much improvement was achieved by additional pre-processing techniques on the algorithm of determining bleeding areas.
Abstract: Cardiovascular diseases, principally atherosclerosis, are responsible for 30% of world deaths. Atherosclerosis is due to the formation of plaque. The fatty plaque may be at risk of rupture, leading typically to stroke and heart attack. The plaque is usually associated with a high degree of lumen reduction, called a stenosis.It is increasingly recognized that the initiation and progression of disease and the occurrence of clinical events is a complex interplay between the local biomechanical environment and the local vascular biology. The aim of this study is to investigate the flow behavior through a stenosed artery. A physical experiment was performed using an artery model and blood analogue fluid. An axisymmetric model constructed consists of contraction and expansion region that follow a mathematical form of cosine function. A 30% diameter reduction was used in this study. The flow field was measured using particle image velocimetry (PIV). Spherical particles with 20μm diameter were seeded in a water-glycerol-NaCl mixture. Steady flow Reynolds numbers are 250. The area of interest is the region after the stenosis where the flow separation occurs. The velocity field was measured and the velocity gradient was investigated. There was high particle concentration in the recirculation zone. High velocity gradient formed immediately after the stenosis throat created a lift force that enhanced particle migration to the flow separation area.
Abstract: Although lots of research work has been done for
human pose recognition, the view-point of cameras is still critical
problem of overall recognition system. In this paper, view-point
insensitive human pose recognition is proposed. The aims of the
proposed system are view-point insensitivity and real-time processing.
Recognition system consists of feature extraction module, neural
network and real-time feed forward calculation. First, histogram-based
method is used to extract feature from silhouette image and it is
suitable for represent the shape of human pose. To reduce the
dimension of feature vector, Principle Component Analysis(PCA) is
used. Second, real-time processing is implemented by using Compute
Unified Device Architecture(CUDA) and this architecture improves
the speed of feed-forward calculation of neural network. We
demonstrate the effectiveness of our approach with experiments on
real environment.
Abstract: This paper presents a novel template-based method to
detect objects of interest from real images by shape matching. To
locate a target object that has a similar shape to a given template
boundary, the proposed method integrates three components: contour
grouping, partial shape matching, and boundary verification. In the
first component, low-level image features, including edges and
corners, are grouped into a set of perceptually salient closed contours
using an extended ratio-contour algorithm. In the second component,
we develop a partial shape matching algorithm to identify the
fractions of detected contours that partly match given template
boundaries. Specifically, we represent template boundaries and
detected contours using landmarks, and apply a greedy algorithm to
search the matched landmark subsequences. For each matched
fraction between a template and a detected contour, we estimate an
affine transform that transforms the whole template into a hypothetic
boundary. In the third component, we provide an efficient algorithm
based on oriented edge lists to determine the target boundary from
the hypothetic boundaries by checking each of them against image
edges. We evaluate the proposed method on recognizing and
localizing 12 template leaves in a data set of real images with clutter
back-grounds, illumination variations, occlusions, and image noises.
The experiments demonstrate the high performance of our proposed
method1.
Abstract: This paper introduces an intelligent system, which can be applied in the monitoring of vehicle speed using a single camera. The ability of motion tracking is extremely useful in many automation problems and the solution to this problem will open up many future applications. One of the most common problems in our daily life is the speed detection of vehicles on a highway. In this paper, a novel technique is developed to track multiple moving objects with their speeds being estimated using a sequence of video frames. Field test has been conducted to capture real-life data and the processed results were presented. Multiple object problems and noisy in data are also considered. Implementing this system in real-time is straightforward. The proposal can accurately evaluate the position and the orientation of moving objects in real-time. The transformations and calibration between the 2D image and the actual road are also considered.
Abstract: There are many issues that affect modeling and designing real-time databases. One of those issues is maintaining consistency between the actual state of the real-time object of the external environment and its images as reflected by all its replicas distributed over multiple nodes. The need to improve the scalability is another important issue. In this paper, we present a general framework to design a replicated real-time database for small to medium scale systems and maintain all timing constrains. In order to extend the idea for modeling a large scale database, we present a general outline that consider improving the scalability by using an existing static segmentation algorithm applied on the whole database, with the intent to lower the degree of replication, enables segments to have individual degrees of replication with the purpose of avoiding excessive resource usage, which all together contribute in solving the scalability problem for DRTDBS.
Abstract: To increase reliability of face recognition system, the
system must be able to distinguish real face from a copy of face such
as a photograph. In this paper, we propose a fast and memory efficient
method of live face detection for embedded face recognition system,
based on the analysis of the movement of the eyes. We detect eyes in
sequential input images and calculate variation of each eye region to
determine whether the input face is a real face or not. Experimental
results show that the proposed approach is competitive and promising
for live face detection.
Abstract: In this paper, a vision based system has been used for
controlling an industrial 3P Cartesian robot. The vision system will
recognize the target and control the robot by obtaining images from
environment and processing them. At the first stage, images from
environment are changed to a grayscale mode then it can diverse and
identify objects and noises by using a threshold objects which are
stored in different frames and then the main object will be
recognized. This will control the robot to achieve the target. A vision
system can be an appropriate tool for measuring errors of a robot in a
situation where the experimental test is conducted for a 3P robot.
Finally, the international standard ANSI/RIA R15.05-2 is used for
evaluating the path-related characteristics of the robot. To evaluate
the performance of the proposed method experimental test is carried
out.
Abstract: We present in this paper an acquisition and treatment system designed for semi-analog Gamma-camera. It consists of a nuclear medical Image Acquisition, Treatment and Display chain(IATD) ensuring the acquisition, the treatment of the signals(resulting from the Gamma-camera detection head) and the scintigraphic image construction in real time. This chain is composed by an analog treatment board and a digital treatment board. We describe the designed systems and the digital treatment algorithms in which we have improved the performance and the flexibility. The digital treatment algorithms are implemented in a specific reprogrammable circuit FPGA (Field Programmable Gate Array).interface for semi-analog cameras of Sopha Medical Vision(SMVi) by taking as example SOPHY DS7. The developed system consists of an Image Acquisition, Treatment and Display (IATD) ensuring the acquisition and the treatment of the signals resulting from the DH. The developed chain is formed by a treatment analog board and a digital treatment board designed around a DSP [2]. In this paper we have presented the architecture of a new version of our chain IATD in which the integration of the treatment algorithms is executed on an FPGA (Field Programmable Gate Array)