-
An Efficient Fingerprint Image Thinning Algorithm
Issue:
Volume 2, Issue 1, February 2013
Pages:
1-6
Published:
20 February 2013
Abstract: Most fingerprint recognition applications rely heavily on efficient and fast image enhancement algorithms. Image thinning is a very important stage of image enhancement. A good thinning algorithm preserves the structure of the original fingerprint image, reduces the amount of data needed to process and helps improve the feature extraction accuracy and efficiency. In this paper we describe and compare some of the most used fingerprint thinning algorithms. Results show that faster algorithms have difficulty preserving connectivity. Zhang and Suen’s algorithm gives the least processing time, while Guo and Hall’s algorithm produces the best skeleton quality. A modified Zhang and Suen’s algorithm is proposed, that is efficient and fast, and better preserves structure and connectivity.
Abstract: Most fingerprint recognition applications rely heavily on efficient and fast image enhancement algorithms. Image thinning is a very important stage of image enhancement. A good thinning algorithm preserves the structure of the original fingerprint image, reduces the amount of data needed to process and helps improve the feature extraction accuracy ...
Show More
-
R Language in Data Mining Techniques and Statistics
Issue:
Volume 2, Issue 1, February 2013
Pages:
7-12
Published:
20 February 2013
Abstract: Data mining is a set of techniques and methods relating to the extraction of knowledge from large amounts of data (through automatic or semi-automatic methods) and further scientific, industrial or operational use of that knowledge. Data mining is closely related to the statistics as an applied mathematical discipline with an analysis of data that could be defined as the extraction of useful information from data.The only difference between the two disciplines is that data mining is a new discipline that is related to significant or large data sets. R is an object-oriented programming language. This means that everything what is done with R can be saved as an object. Every object has a class. It describes what the object contains and what each function does. Application of R as a programming language and statistical software is much more than a supplement to Stata, SAS, and SPSS. Although it is more difficult to learn, the biggest advantage of R is its free-of-charge feature and the wealth of specialized application packages and libraries for a huge number of statistical, mathematical and other methods. R is a simple, but very powerful data mining and statistical data processing tool and once "discovered", it provides users with an entirely new, rich and powerful tool applicable in almost every field of research
Abstract: Data mining is a set of techniques and methods relating to the extraction of knowledge from large amounts of data (through automatic or semi-automatic methods) and further scientific, industrial or operational use of that knowledge. Data mining is closely related to the statistics as an applied mathematical discipline with an analysis of data that ...
Show More
-
Generic Object Recognition Using Graph Embedding into A Vector Space
Takahiro Hori,
Tetsuya Takiguchi,
Yasuo Ariki
Issue:
Volume 2, Issue 1, February 2013
Pages:
13-18
Published:
20 February 2013
Abstract: This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.
Abstract: This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance f...
Show More
-
An approach to Virtual Laboratory Design and Testing
A. Hovakimyan,
S. Sargsyan,
N. Ispiryan,
L. Khachoyan,
K. Darbinyan
Issue:
Volume 2, Issue 1, February 2013
Pages:
19-23
Published:
20 February 2013
Abstract: Laboratory experiments and research are important parts in natural science education. They supplement the theoretical learning material and contribute to deeper learn of a subject. The realization of such activities requires an ap-propriate laboratory equipment and reagents that are often either inaccessible or incomplete. Virtual labs solve this prob-lem and provide the performing of the same experiment repeatedly without any restriction. An interactive laboratory envi-ronment engages pupils in active learning to enhance their understanding of processes and practical skills and promotes a successful e-learning strategy. Virtual Lab includes a lot of embedded experiments that the student must perform via cer-tain scenarios. In the paper an approach to design of laboratory experiments for virtual lab environment and their scenarios implementation testing is suggested. Experiments design patterns are based on finite-state automaton model. The object-oriented approach for virtual experiment implementation is provided. For testing pattern a methodology of class testing is used. The suggested approaches are realized in the presented virtual laboratory environments for Chemistry and Biology that have been developed to support laboratory study in Armenian schools, colleges, and universities. These methods will be used in long-term research activity in the field of creation of virtual laboratories on different disciplines: organic and inorganic chemistry, physics, and biology as well as during developing others virtual laboratories.
Abstract: Laboratory experiments and research are important parts in natural science education. They supplement the theoretical learning material and contribute to deeper learn of a subject. The realization of such activities requires an ap-propriate laboratory equipment and reagents that are often either inaccessible or incomplete. Virtual labs solve this p...
Show More
