Abstract: In recent years, rapid advances in software and hardware in the field of information technology along with a digital imaging revolution in the medical domain facilitate the generation and storage of large collections of images by hospitals and clinics. To search these large image collections effectively and efficiently poses significant technical challenges, and it raises the necessity of constructing intelligent retrieval systems. Content-based Image Retrieval (CBIR) consists of retrieving the most visually similar images to a given query image from a database of images[5]. Medical CBIR (content-based image retrieval) applications pose unique challenges but at the same time offer many new opportunities. On one hand, while one can easily understand news or sports videos, a medical image is often completely incomprehensible to untrained eyes.
Abstract: This paper proposes a copyright protection scheme for color images using secret sharing and wavelet transform. The scheme contains two phases: the share image generation phase and the watermark retrieval phase. In the generation phase, the proposed scheme first converts the image into the YCbCr color space and creates a special sampling plane from the color space. Next, the scheme extracts the features from the sampling plane using the discrete wavelet transform. Then, the scheme employs the features and the watermark to generate a principal share image. In the retrieval phase, an expanded watermark is first reconstructed using the features of the suspect image and the principal share image. Next, the scheme reduces the additional noise to obtain the recovered watermark, which is then verified against the original watermark to examine the copyright. The experimental results show that the proposed scheme can resist several attacks such as JPEG compression, blurring, sharpening, noise addition, and cropping. The accuracy rates are all higher than 97%.
Abstract: In this paper, we present local image descriptor using
VQ-SIFT for more effective and efficient image retrieval. Instead of
SIFT's weighted orientation histograms, we apply vector quantization
(VQ) histogram as an alternate representation for SIFT features.
Experimental results show that SIFT features using VQ-based local
descriptors can achieve better image retrieval accuracy than the
conventional algorithm while the computational cost is significantly
reduced.
Abstract: Personal name matching system is the core of
essential task in national citizen database, text and web mining,
information retrieval, online library system, e-commerce and record
linkage system. It has necessitated to the all embracing research in
the vicinity of name matching. Traditional name matching methods
are suitable for English and other Latin based language. Asian
languages which have no word boundary such as Myanmar language
still requires sounds alike matching system in Unicode based
application. Hence we proposed matching algorithm to get analogous
sounds alike (phonetic) pattern that is convenient for Myanmar
character spelling. According to the nature of Myanmar character, we
consider for word boundary fragmentation, collation of character.
Thus we use pattern conversion algorithm which fabricates words in
pattern with fragmented and collated. We create the Myanmar sounds
alike phonetic group to help in the phonetic matching. The
experimental results show that fragmentation accuracy in 99.32% and
processing time in 1.72 ms.
Abstract: We present a method to create special domain
collections from news sites. The method only requires a single
sample article as a seed. No prior corpus statistics are needed and the
method is applicable to multiple languages. We examine various
similarity measures and the creation of document collections for
English and Japanese. The main contributions are as follows. First,
the algorithm can build special domain collections from as little as
one sample document. Second, unlike other algorithms it does not
require a second “general" corpus to compute statistics. Third, in our
testing the algorithm outperformed others in creating collections
made up of highly relevant articles.
Abstract: This paper outlines the development of a learning retrieval agent. Task of this agent is to extract knowledge of the Active Semantic Network in respect to user-requests. Based on a reinforcement learning approach, the agent learns to interpret the user-s intention. Especially, the learning algorithm focuses on the retrieval of complex long distant relations. Increasing its learnt knowledge with every request-result-evaluation sequence, the agent enhances his capability in finding the intended information.
Abstract: Users of computer systems may often require the
private transfer of messages/communications between parties across
a network. Information warfare and the protection and dominance of
information in the military context is a prime example of an
application area in which the confidentiality of data needs to be
maintained. The safe transportation of critical data is therefore often
a vital requirement for many private communications. However,
unwanted interception/sniffing of communications is also a
possibility. An elementary stealthy transfer scheme is therefore
proposed by the authors. This scheme makes use of encoding,
splitting of a message and the use of a hashing algorithm to verify the
correctness of the reconstructed message. For this proof-of-concept
purpose, the authors have experimented with the random sending of
encoded parts of a message and the construction thereof to
demonstrate how data can stealthily be transferred across a network
so as to prevent the obvious retrieval of data.
Abstract: XML files contain data which is in well formatted manner. By studying the format or semantics of the grammar it will be helpful for fast retrieval of the data. There are many algorithms which describes about searching the data from XML files. There are no. of approaches which uses data structure or are related to the contents of the document. In these cases user must know about the structure of the document and information retrieval techniques using NLPs is related to content of the document. Hence the result may be irrelevant or not so successful and may take more time to search.. This paper presents fast XML retrieval techniques by using new indexing technique and the concept of RXML. When indexing an XML document, the system takes into account both the document content and the document structure and assigns the value to each tag from file. To query the system, a user is not constrained about fixed format of query.
Abstract: Automated material handling is given prime
importance in the semi automated and automated facilities since it
provides solution to the gigantic problems related to inventory and
also support the latest philosophies like just in time production JIT
and lean production. Automated storage and retrieval system is an
antidote (if designed properly) to the facility sufferings like getting
the right material , materials getting perished, long cycle times or
many other similar kind of problems. A working model of automated
storage and retrieval system (AS/RS) is designed and developed
under the design parameters specified by Material Handling Industry
of America (MHIA). Later on analysis was carried out to calculate
the throughput and size of the machine. The possible implementation
of this technology in local scenario is also discussed in this paper.
Abstract: Text categorization techniques are widely used to many Information Retrieval (IR) applications. In this paper, we proposed a simple but efficient method that can automatically find the relationship between any pair of terms and documents, also an indexing matrix is established for text categorization. We call this method Indexing Matrix Categorization Machine (IMCM). Several experiments are conducted to show the efficiency and robust of our algorithm.
Abstract: Warehousing is commonly used in factories for the
storage of products until delivery of orders. As the amount of
products stored increases it becomes tedious to be carried out
manually. In recent years, the manual storing has converted into fully
or partially computer controlled systems, also known as Automated
Storage and Retrieval Systems (AS/RS). This paper discusses an
ASRS system, which was designed such that the best storage location
for the products is determined by utilizing a fuzzy control system.
The design maintains the records of the products to be/already in
store and the storage/retrieval times along with the availability status
of the storage locations. This paper discusses on the maintenance of
the above mentioned records and the utilization of the concept of
fuzzy logic in order to determine the optimum storage location for
the products. The paper will further discuss on the dynamic splitting
and merging of the storage locations depending on the product sizes.
Abstract: One of object oriented software developing problem
is the difficulty of searching the appropriate and suitable objects for
starting the system. In this work, ontologies appear in the part of
supporting the object discovering in the initial of object oriented
software developing. There are many researches try to demonstrate
that there is a great potential between object model and ontologies.
Constructing ontology from object model is called ontology
engineering can be done; On the other hand, this research is aiming to
support the idea of building object model from ontology is also
promising and practical. Ontology classes are available online in any
specific areas, which can be searched by semantic search engine.
There are also many helping tools to do so; one of them which are
used in this research is Protégé ontology editor and Visual Paradigm.
To put them together give a great outcome. This research will be
shown how it works efficiently with the real case study by using
ontology classes in travel/tourism domain area. It needs to combine
classes, properties, and relationships from more than two ontologies
in order to generate the object model. In this paper presents a simple
methodology framework which explains the process of discovering
objects. The results show that this framework has great value while
there is possible for expansion. Reusing of existing ontologies offers
a much cheaper alternative than building new ones from scratch.
More ontologies are becoming available on the web, and online
ontologies libraries for storing and indexing ontologies are increasing
in number and demand. Semantic and Ontologies search engines have
also started to appear, to facilitate search and retrieval of online
ontologies.
Abstract: In this paper, a new robust audio fingerprinting
algorithm in MP3 compressed domain is proposed with high
robustness to time scale modification (TSM). Instead of simply
employing short-term information of the MP3 stream, the new
algorithm extracts the long-term features in MP3 compressed domain
by using the modulation frequency analysis. Our experiment has
demonstrated that the proposed method can achieve a hit rate of
above 95% in audio retrieval and resist the attack of 20% TSM. It has
lower bit error rate (BER) performance compared to the other
algorithms. The proposed algorithm can also be used in other
compressed domains, such as AAC.
Abstract: In the current age, retrieval of relevant information
from massive amount of data is a challenging job. Over the years,
precise and relevant retrieval of information has attained high
significance. There is a growing need in the market to build systems,
which can retrieve multimedia information that precisely meets the
user's current needs. In this paper, we have introduced a framework
for refining query results before showing it to the user, using ambient
intelligence, user profile, group profile, user location, time, day, user
device type and extracted features. A prototypic tool was also
developed to demonstrate the efficiency of the proposed approach.
Abstract: Needs of an efficient information retrieval in recent
years in increased more then ever because of the frequent use of
digital information in our life. We see a lot of work in the area of
textual information but in multimedia information, we cannot find
much progress. In text based information, new technology of data
mining and data marts are now in working that were started from the
basic concept of database some where in 1960.
In image search and especially in image identification,
computerized system at very initial stages. Even in the area of image
search we cannot see much progress as in the case of text based
search techniques. One main reason for this is the wide spread roots
of image search where many area like artificial intelligence,
statistics, image processing, pattern recognition play their role. Even
human psychology and perception and cultural diversity also have
their share for the design of a good and efficient image recognition
and retrieval system.
A new object based search technique is presented in this paper
where object in the image are identified on the basis of their
geometrical shapes and other features like color and texture where
object-co-relation augments this search process.
To be more focused on objects identification, simple images are
selected for the work to reduce the role of segmentation in overall
process however same technique can also be applied for other
images.
Abstract: Unstructured peer-to-peer networks are popular due to
its robustness and scalability. Query schemes that are being used in
unstructured peer-to-peer such as the flooding and interest-based
shortcuts suffer various problems such as using large communication
overhead long delay response. The use of routing indices has been a
popular approach for peer-to-peer query routing. It helps the query
routing processes to learn the routing based on the feedbacks
collected. In an unstructured network where there is no global
information available, efficient and low cost routing approach is
needed for routing efficiency.
In this paper, we propose a novel mechanism for query-feedback
oriented routing indices to achieve routing efficiency in unstructured
network at a minimal cost. The approach also applied information
retrieval technique to make sure the content of the query is
understandable and will make the routing process not just based to
the query hits but also related to the query content. Experiments have
shown that the proposed mechanism performs more efficient than
flood-based routing.
Abstract: Information Retrieval has the objective of studying
models and the realization of systems allowing a user to find the
relevant documents adapted to his need of information. The
information search is a problem which remains difficult because the
difficulty in the representing and to treat the natural languages such
as polysemia. Intentional Structures promise to be a new paradigm to
extend the existing documents structures and to enhance the different
phases of documents process such as creation, editing, search and
retrieval. The intention recognition of the author-s of texts can reduce
the largeness of this problem. In this article, we present intentions
recognition system is based on a semi-automatic method of
extraction the intentional information starting from a corpus of text.
This system is also able to update the ontology of intentions for the
enrichment of the knowledge base containing all possible intentions
of a domain. This approach uses the construction of a semi-formal
ontology which considered as the conceptualization of the intentional
information contained in a text. An experiments on scientific
publications in the field of computer science was considered to
validate this approach.
Abstract: Human-related information security breaches within organizations are primarily caused by employees who have not been made aware of the importance of protecting the information they work with. Information security awareness is accordingly attracting more attention from industry, because stakeholders are held accountable for the information with which they work. The authors developed an Information Security Retrieval and Awareness model – entitled “ISRA" – that is tailored specifically towards enhancing information security awareness in industry amongst all users of information, to address shortcomings in existing information security awareness models. This paper is principally aimed at expounding a prototype for the ISRA model to highlight the advantages of utilizing the model. The prototype will focus on the non-technical, humanrelated information security issues in industry. The prototype will ensure that all stakeholders in an organization are part of an information security awareness process, and that these stakeholders are able to retrieve specific information related to information security issues relevant to their job category, preventing them from being overburdened with redundant information.
Abstract: Currently searching through internet is very popular especially in a field of academic. A huge of educational information such as research papers are overload for user. So community-base web sites have been developed to help user search information more easily from process of customizing a web site to need each specifies user or set of user. In this paper propose to use association rule analyze the community group on research paper bookmarking. A set of design goals for community group frameworks is developed and discussed. Additionally Researcher analyzes the initial relation by using association rule discovery between the antecedent and the consequent of a rule in the groups of user for generate the idea to improve ranking search result and development recommender system.
Abstract: The state-of-the-art Bag of Words model in Content-
Based Image Retrieval has been used for years but the relevance
feedback strategies for this model are not fully investigated. Inspired
from text retrieval, the Bag of Words model has the ability to use the
wealth of knowledge and practices available in text retrieval. We
study and experiment the relevance feedback model in text retrieval
for adapting it to image retrieval. The experiments show that the
techniques from text retrieval give good results for image retrieval
and that further improvements is possible.