Abstract: H.264/AVC offers a considerably higher improvement
in coding efficiency compared to other compression standards such
as MPEG-2, but computational complexity is increased significantly.
In this paper, we propose selective mode decision schemes for fast
intra prediction mode selection. The objective is to reduce the
computational complexity of the H.264/AVC encoder without
significant rate-distortion performance degradation. In our proposed
schemes, the intra prediction complexity is reduced by limiting the
luma and chroma prediction modes using the directional information
of the 16×16 prediction mode. Experimental results are presented to
show that the proposed schemes reduce the complexity by up to 78%
maintaining the similar PSNR quality with about 1.46% bit rate
increase in average.
Abstract: This paper propose the robust character segmentation method for license plate with topological transform such as twist,rotation. The first step of the proposed method is to find a candidate region for character and license plate. The character or license plate
must be appeared as closed loop in the edge image. In the case of
detecting candidate for character region, the evaluation of detected
region is using topological relationship between each character. When
this method decides license plate candidate region, character features
in the region with binarization are used. After binarization for the detected candidate region, each character region is decided again. In
this step, each character region is fitted more than previous step. In the
next step, the method checks other character regions with different
scale near the detected character regions, because most license plates
have license numbers with some meaningful characters around them.
The method uses perspective projection for geometrical normalization.
If there is topological distortion in the character region, the method
projects the region on a template which is defined as standard license
plate using perspective projection. In this step, the method is able to
separate each number region and small meaningful characters. The
evaluation results are tested with a number of test images.
Abstract: In this paper, a novel algorithm based on Ridgelet
Transform and support vector machine is proposed for human action
recognition. The Ridgelet transform is a directional multi-resolution
transform and it is more suitable for describing the human action by
performing its directional information to form spatial features
vectors. The dynamic transition between the spatial features is carried
out using both the Principal Component Analysis and clustering
algorithm K-means. First, the Principal Component Analysis is used
to reduce the dimensionality of the obtained vectors. Then, the kmeans
algorithm is then used to perform the obtained vectors to form
the spatio-temporal pattern, called set-of-labels, according to given
periodicity of human action. Finally, a Support Machine classifier is
used to discriminate between the different human actions. Different
tests are conducted on popular Datasets, such as Weizmann and
KTH. The obtained results show that the proposed method provides
more significant accuracy rate and it drives more robustness in very
challenging situations such as lighting changes, scaling and dynamic
environment
Abstract: Information of nodes’ locations is an important
criterion for lots of applications in Wireless Sensor Networks. In the
hop-based range-free localization methods, anchors transmit the
localization messages counting a hop count value to the whole
network. Each node receives this message and calculates its own
distance with anchor in hops and then approximates its own position.
However the estimative distances can provoke large error, and affect
the localization precision. To solve the problem, this paper proposes
an algorithm, which makes the unknown nodes fix the nearest anchor
as a reference and select two other anchors which are the most
accurate to achieve the estimated location. Compared to the DV-Hop
algorithm, experiment results illustrate that proposed algorithm has
less average localization error and is more effective.
Abstract: The rapid improvement of the microprocessor and network has made it possible for the PC cluster to compete with conventional supercomputers. Lots of high throughput type of applications can be satisfied by using the current desktop PCs, especially for those in PC classrooms, and leave the supercomputers for the demands from large scale high performance parallel computations. This paper presents our development on enabling an automated deployment mechanism for cluster computing to utilize the computing power of PCs such as reside in PC classroom. After well deployment, these PCs can be transformed into a pre-configured cluster computing resource immediately without touching the existing education/training environment installed on these PCs. Thus, the training activities will not be affected by this additional activity to harvest idle computing cycles. The time and manpower required to build and manage a computing platform in geographically distributed PC classrooms also can be reduced by this development.
Abstract: The vast amount of information hidden in huge
databases has created tremendous interests in the field of data
mining. This paper examines the possibility of using data clustering
techniques in oral medicine to identify functional relationships
between different attributes and classification of similar patient
examinations. Commonly used data clustering algorithms have been
reviewed and as a result several interesting results have been
gathered.
Abstract: This paper attempts to model and design a simple
fuzzy logic controller with Variable Reference. The Variable
Reference (VR) is featured as an adaptability element which is
obtained from two known variables – desired system-input and actual
system-output. A simple fuzzy rule-based technique is simulated to
show how the actual system-input is gradually tuned in to a value
that closely matches the desired input. The designed controller is
implemented and verified on a simple heater which is controlled by
PIC Microcontroller harnessed by a code developed in embedded C.
The output response of the PIC-controlled heater is analyzed and
compared to the performances by conventional fuzzy logic
controllers. The novelty of this work lies in the fact that it gives
better performance by using less number of rules compared to
conventional fuzzy logic controllers.
Abstract: An automatic method for the extraction of feature points for face based applications is proposed. The system is based upon volumetric feature descriptors, which in this paper has been extended to incorporate scale space. The method is robust to noise and has the ability to extract local and holistic features simultaneously from faces stored in a database. Extracted features are stable over a range of faces, with results indicating that in terms of intra-ID variability, the technique has the ability to outperform manual landmarking.
Abstract: We created the tool, which combines the powerful
GENESIS (GEneral NEural SImulation System) simulation language
with the up-to-date visualisation and internet techniques. Our
solution resides in the connection between the simulation output from
GENESIS, which is converted to the data-structure suitable for
WWW browsers and VRML (Virtual Reality Modelling Language)
viewers. The selected GENESIS simulations are once exported into
the VRML code, and stored in our neurovisualisation portal
(webserver). There, the loaded models, demonstrating mainly the
spread of electrical signal (action potentials, postsynaptic potentials)
along the neuronal membrane (axon, dendritic tree, neuron) could be
displayed in the client-s VRML viewer, without interacting with
original GENESIS environment. This enables the visualisation of
basic neurophysiological phenomena designed for GENESIS
simulator on the independent OS (operation system).
Abstract: This paper discusses the Urdu script characteristics,
Urdu Nastaleeq and a simple but a novel and robust technique to
recognize the printed Urdu script without a lexicon. Urdu being a
family of Arabic script is cursive and complex script in its nature, the
main complexity of Urdu compound/connected text is not its
connections but the forms/shapes the characters change when it is
placed at initial, middle or at the end of a word. The characters
recognition technique presented here is using the inherited
complexity of Urdu script to solve the problem. A word is scanned
and analyzed for the level of its complexity, the point where the level
of complexity changes is marked for a character, segmented and
feeded to Neural Networks. A prototype of the system has been
tested on Urdu text and currently achieves 93.4% accuracy on the
average.
Abstract: A word recognition architecture based on a network
of neural associative memories and hidden Markov models has been
developed. The input stream, composed of subword-units like wordinternal
triphones consisting of diphones and triphones, is provided
to the network of neural associative memories by hidden Markov
models. The word recognition network derives words from this input
stream. The architecture has the ability to handle ambiguities on
subword-unit level and is also able to add new words to the
vocabulary during performance. The architecture is implemented to
perform the word recognition task in a language processing system
for understanding simple command sentences like “bot show apple".
Abstract: We developed a vision interface immersive projection system, CAVE in virtual rea using hand gesture recognition with computer vis background image was subtracted from current webcam and we convert the color space of the imag Then we mask skin regions using skin color range t a noise reduction operation. We made blobs fro gestures were recognized using these blobs. Using recognition, we could implement an effective bothering devices for CAVE. e framework for an reality research field vision techniques. ent image frame age into HSV space. e threshold and apply from the image and ing our hand gesture e interface without
Abstract: This paper proposes a location-aware system for
household robots which allows users to paste predefined paper tags at
different locations according to users- comprehension of the house. In this system a household robot may be aware of its location and the
attributes thereof by visually recognizing the tags when the robot is moving. This paper also presents a novel user interface to define a
moving path of the robot, which allows users to draw the path in the air
with a finger so as to generate commands for following motions.
Abstract: The approaches to make an agent generate intelligent actions in the AI field might be roughly categorized into two ways–the classical planning and situated action system. It is well known that each system have its own strength and weakness. However, each system also has its own application field. In particular, most of situated action systems do not directly deal with the logical problem. This paper first briefly mentions the novel action generator to situatedly extract a set of actions, which is likely to help to achieve the goal at the current situation in the relaxed logical space. After performing the action set, the agent should recognize the situation for deciding the next likely action set. However, since the extracted action is an approximation of the action which helps to achieve the goal, the agent could be caught into the deadlock of the problem. This paper proposes the newly developed hybrid architecture to solve the problem, which combines the novel situated action generator with the conventional planner. The empirical result in some planning domains shows that the quality of the resultant path to the goal is mostly acceptable as well as deriving the fast response time, and suggests the correlation between the structure of problems and the organization of each system which generates the action.
Abstract: The Continuously Adaptive Mean-Shift (CamShift)
algorithm, incorporating scene depth information is combined with
the l1-minimization sparse representation based method to form a
hybrid kernel and state space-based tracking algorithm. We take
advantage of the increased efficiency of the former with the
robustness to occlusion property of the latter. A simple interchange
scheme transfers control between algorithms based upon drift and
occlusion likelihood. It is quantified by the projection of target
candidates onto a depth map of the 2D scene obtained with a low cost
stereo vision webcam. Results are improved tracking in terms of drift
over each algorithm individually, in a challenging practical outdoor
multiple occlusion test case.
Abstract: This paper deals with automatic sentence modality
recognition in French. In this work, only prosodic features are
considered. The sentences are recognized according to the three
following modalities: declarative, interrogative and exclamatory
sentences. This information will be used to animate a talking head for
deaf and hearing-impaired children. We first statistically study a real
radio corpus in order to assess the feasibility of the automatic
modeling of sentence types. Then, we test two sets of prosodic
features as well as two different classifiers and their combination. We
further focus our attention on questions recognition, as this modality
is certainly the most important one for the target application.
Abstract: This paper presents a design method of self-tuning
Quantitative Feedback Theory (QFT) by using improved deadbeat
control algorithm. QFT is a technique to achieve robust control with
pre-defined specifications whereas deadbeat is an algorithm that
could bring the output to steady state with minimum step size.
Nevertheless, usually there are large peaks in the deadbeat response.
By integrating QFT specifications into deadbeat algorithm, the large
peaks could be tolerated. On the other hand, emerging QFT with
adaptive element will produce a robust controller with wider
coverage of uncertainty. By combining QFT-based deadbeat
algorithm and adaptive element, superior controller that is called selftuning
QFT-based deadbeat controller could be achieved. The output
response that is fast, robust and adaptive is expected. Using a grain
dryer plant model as a pilot case-study, the performance of the
proposed method has been evaluated and analyzed. Grain drying
process is very complex with highly nonlinear behaviour, long delay,
affected by environmental changes and affected by disturbances.
Performance comparisons have been performed between the
proposed self-tuning QFT-based deadbeat, standard QFT and
standard dead-beat controllers. The efficiency of the self-tuning QFTbased
dead-beat controller has been proven from the tests results in
terms of controller’s parameters are updated online, less percentage
of overshoot and settling time especially when there are variations in
the plant.
Abstract: A design of communication area for infrared
electronic-toll-collection systems to provide an extended
communication interval in the vehicle traveling direction and
regular boundary between contiguous traffic lanes is proposed.
By utilizing two typical low-cost commercial infrared LEDs with
different half-intensity angles Φ1/2 = 22◦ and 10◦, the radiation
pattern of the emitter is designed to properly adjust the spatial
distribution of the signal power. The aforementioned purpose
can be achieved with an LED array in a three-piece structure
with appropriate mounting angles. With this emitter, the influence
of the mounting parameters, including the mounting height and
mounting angles of the on-board unit and road-side unit, on the
system performance in terms of the received signal strength and
communication area are investigated. The results reveal that, for
our emitter proposed in this paper, the ideal ”long-and-narrow”
characteristic of the communication area is very little affected by
these mounting parameters. An optimum mounting configuration is
also suggested.
Abstract: The paper provides the basic overview of simulation optimization. The procedure of its practical using is demonstrated on the real example in simulator Witness. The simulation optimization is presented as a good tool for solving many problems in real praxis especially in production systems. The authors also characterize their own experiences and they mention the strengths and weakness of simulation optimization.
Abstract: Color printing proceeds with multiple halftone
separations overlay. Because of separation overlay misalignment in
printing, the percentage of different primary color combination may
vary and it will result in color shift. In traditional printing procedure
with AM halftone, every separation has different screening angle to
make the superposition pattern in a random style, which will reduce
the color shift. To evaluate the color shift of printing with hybrid
halftoning, we simulate printing procedure with halftone images
overlay and calculate the color difference between expected color and
color in different overlay misalignment configurations. The color
difference for hybrid halftone and AM halftone is very close. So the
color shift for hybrid halftone is acceptable with current color printing
procedure.