KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 9 of 9

Some of the metrics are blocked by your
consent settings
Shape retrieval using Eigen and Fisher Barycenter contour
(2011-01-01)
Thourn, Kosorl
;
Kitjaidure, Yuttana
;
Kondo, Shozo
To achieve a good performance for shape retrieval, it requires both shape representation and classifier. In this paper, the algorithm for shape matching and retrieval is developed by using Eigen Barycenter Contour (EBcC) and Fisher Barycenter Contour (FBcC). In our algorithm, the Signed Enclosed Area (SEA) signature (formed by two adjacent points of contour and its center point), computed at each scale level of Barycenter contour (BcC), is utilized as the shape representation. The BcC technique is robust to moderate amount of noise and occlusion. Furthermore, the SEA signature is invariant to general affine transformation including translation, rotation, scale and shear. Because of high dimension of the shape representation, thus, in the matching step, two classifiers have been studied. The first classifier, Eigen face technique, is employed for dimensionality reduction while the second classifier, Fisher face technique, is used for reducing dimension as well and making discrimination. Then, the similarity among shapes is measured by the normalized crosscorrelation (NCC). The performance of our technique is evaluated onto the affine shape database and two well-known databases, the MPEG-7 shape database part B and the Kimia's database. The experimental results illustrate that our approach gives very high retrieval efficiency over all published methods.
Some of the metrics are blocked by your
consent settings
Eigen and fisher barycenter contour for 2D shape classification
(2009-11-16)
Thourn, Kosorl
;
Kitjaidure, Yuttana
;
Kondo, Shozo
To achieve a good performance for shape classification, it requires both shape representation and classifier. In this paper, the so-called Eigen Barycenter Contour (EBcC) and Fisher Barycenter Contour (FBcC) techniques are presented for 2D shape classification. The representation utilizes the area of triangles at different scale level of Barycenter Contour (BcC). However, it is not invariant to starting point selection, so the phase normalization is applied. After that, we linearly project the shape feature in 3D format onto a subspace based on EBcC technique into low dimensional subspace. The FBcC, another similar method, also produces well separated classes in low dimensional subspace. Finally, the normalized cross correlation is used to measure the similarity among shapes. The experimental results demonstrate that the FBcC method outperforms the EBcC method and achieves high retrieval efficiency over other recent methods in the literature for tests on three different databases, the affine shape database, the MPEG-7 database CE-1 part B and the Kimia's database. © 2009 IEEE.
Some of the metrics are blocked by your
consent settings
A new correlation-based watermarking method using wavelet tree and mathematical morphology
(2009-01-01)
Sepsirisuk, Kasemsuk
;
Hamamoto, Kazuhiko
;
Atsuta, Kiyoaki
;
Kondo, Shozo
This paper proposes a new correlation-based watermarking method using the wavelet tree and the mathematical morphology. In this method a watermark is a two-dimensional pseudorandom array of {-1, 1} with the same size as a host image to be watermarked. The watermark is embedded into a Resilient Tree Structure (RTS) which is created by applying the mathematical morphology, the dilation operation, to the wavelet tree. The dilation operation improves the reliability of the proposed method by increasing the number of coefficients involved in watermarking. Furthermore an improved perceptual weighting function of the Human Visual System is used for preserving the image quality. In a watermark detection process the linear correlation between the watermark and the coefficients of the RTS of a tested image is computed to judge the presence of the watermark. The experimental results show that the proposed method outperforms current correlation-based watermarking methods. © 2009 The Institute of Electrical Engineers of Japan.
Some of the metrics are blocked by your
consent settings
Affine invariant shape recognition based on multi-level of barycenter contour
(2008-12-01)
Thourn, Kosorl
;
Kitjaidure, Yuttana
;
Kondo, Shozo
In this paper, a new multiresolution created from multi-level of barycenter contour is proposed in order to reduce the moderate amount of noise and to improve the retrieval efficiency of the recognition task in computer vision. Then, the Triangle Area Representation with two points (TAR-2p) signature at each level of barycenter contour is introduced as the shape representation. Finally, the normalized cross-correlation function at each level is used for measuring the similarity among the shapes. Our experiment has been performed on database consisting of 560 affine distorted shapes, chosen from MPEG-7 contour shape database CE-1. The results illustrate that our algorithm is invariant to affine transformation, robustness to the noise. Moreover, it achieves high retrieval efficiencies when compares to those of the Triangle Area Representation with three points (TAR-3p) signature and the centroid distance signature. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
Data scattering algorithm for very large multivariable data visualization
(1998-12-01)
Leauhatong, Thurdsak
;
Ausavarungsakul, Prasert
;
Chitsakul, Kitiphol
;
Sangwarasilp, Manas
;
Kondo, Shozo
Data visualization techniques are very important now. Techniques such as data scattering, 3D vector glyphs, vector warping, and hedgehogs are used for multivariable data representation. Data represented by these techniques are more reasonable than current techniques such as histogram graph or table, but they take very long time to plot data. In this paper an algorithm which quickly creates very large data scattering is proposed. Data scattering represents each element of data by a sphere in 3D space. For example, 3 axes of 3D space, and 3 components of a color and the radius of a sphere are used to present data of seven variables. Since meshes or polygons are not required, this algorithm saves time and memory. IBM PC compatible with Pentium Pro Processor 200MHz, 32Mbyte RAM and Windows95 is used in our experiments. The numbers of data are from 1,436 to 232357 and computation time is from 0.05 to 5.44 second.
Some of the metrics are blocked by your
consent settings
Recognition of handprinted thai characters using loop structures
(1996-01-01)
Airphaiboon, Surapan
;
Kondo, Shozo
A method for the recognition of handprinted Thai characters input using an image scanner is presented. We use methods of edge detection and boundary contour tracing algorithms to extract loop structures from input characters. The number of loops and their locations are detected and used as information for rough classification. For fine classification, local feature analysis of Thai characters is presented to discriminate an output character from a group of similar characters. In this paper, four parts of the recognition system are presented: Preprocessing, single-character segmentation, loop structure extraction and character identification. Preprocessing consists of pattern binarization, noise reduction and slant normalization based on geometrical transformation for the forward (backward) slanted word. The method of single-character segmentation is applied during the recognition phase. Each character from an input word including the character line level information is subjected to the processes of edge detection, contour tracing and thinning to detect loop structures and to extract topological properties of strokes. The decision trees are constructed based on the obtained information about loops, end points of strokes and some local characteristics of Thai characters. The proposed system is implemented on a personal computer, and a high recognition rate is obtained for 1000 samples of handprinted Thai words from 20 subjects.
Some of the metrics are blocked by your
consent settings
Off-line handwritten Thai characters from word script
(1994-01-01)
Airphaiboon, Suraphun
;
Sangworasil, Manas
;
Kondo, Shozo
This paper proposes a recognition method of off-line handwritten Thai characters from word scripts. Firstly a new method on line level separation of Thai words are proposed. Loop structure is used to classify 4 groups of characters. Secondly by using topological properties of strokes and other Thai character's structural features, decision trees are constructed. Finally a recognition experiment is presented in which 100 copies of handwritten Thai words written by 10 persons are tested. Recognition rate is 99.0% and recognition time is 0.5 second per character.
Some of the metrics are blocked by your
consent settings
Structure analysis of handwriting using opposing relations
(1992-01-01)
Kondo, Shozo
;
Maitree, Kanchit
;
Itoh, Daisuke
;
Atsuta, Kiyoaki
The structure of handwriting is analyzed using an opposing relation between two continuous curves. A fundamental character element(FCE) is defined as a simple curves. A curve regarded as a character in a class is represented by a concatenation of several FECs and an opposing relation between two characters is defined. Using the opposing relation, the structure of the characters is analyzed. It is seen that in some character system, there are some pairs of characters whose opposing relation is distinctive and can be characterized only by some continuous quantities and the structure of the characters can be determined by their opposing relation.
Some of the metrics are blocked by your
consent settings
Shape and source from shading using zero crossings
(1992-01-01)
Kondo, Shozo
;
Xu, Tong
;
Tanaka, Hidenori
;
Sangwarasil, Manas
;
Atsuta, Kiyoaki
We propose a new estimation method of 3D shape of an object and the illuminant direction from a single image using the zero crossings under the assumption that the illuminant direction and strength, and the object surface albado are unknown. In most practical cases the illuminant direction is unknown. For these cases, a new theory was proposed by M.J. Brooks and B.K.P. Horn where the illuminant direction and 3D shape are simultaneously estimated from a single image. This theory, however, can not be applied to an object whose surface is not convex. We propose a new theory which has not such a drawback.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results