• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.10
• /
• pp.446-452
• /
• 2002

For most of pattern recognition applications, it is required to correctly recognize patterns even if they have translation variations. In this paper, to achieve the goal of translation invariant pattern recognition, we propose a new generalized translation invariant second-order neural network using a constraint on the weights. The weight constraint is implemented using generalized translation invariant features which are accumulated sums of pixel combinations. Simulation results will be given to demonstrate that the proposed second-order neural network has the generalized translation invariant property.

• Honam Mathematical Journal
• /
• v.26 no.2
• /
• pp.137-145
• /
• 2004

we shall study some properties of a new class ($\sqrt[\kappa]{P}$) (defined below). Also we show that T may not be normaloid when $T{\in}(\sqrt[\kappa]{P})$, and that the class ($\sqrt{H}$) may not have the translation-invariant propety.

• Bulletin of the Korean Mathematical Society
• /
• v.40 no.4
• /
• pp.685-692
• /
• 2003

In this paper, we study some properties of (equation omitted) (defined below). In particular we show that an operator T $\in$(equation omitted) satisfying the translation invariant property is hyponormal and an invertible operator T $\in$ (equation omitted) and its inverse T$^{-1}$ have a common nontrivial invariant closed set. Also we study some cases which have nontrivial invariant subspaces for an operator in (equation omitted).

• Bulletin of the Korean Mathematical Society
• /
• v.22 no.1
• /
• pp.7-10
• /
• 1985

For each a.mem.S and f.mem.m(S), denote by $l_{a}$ f(s)=f(as) for all s.mem.S. If A is a norm closed left translation invariant subalgebra of m(S) (i.e. $l_{a}$ f.mem.A whenever f.mem.A and a.mem.S) containing 1, the constant ont function on S and .phi..mem. $A^{*}$, the dual of A, then .phi. is a mean on A if .phi.(f).geq.0 for f.geq.0 and .phi.(1) = 1, .phi. is multiplicative if .phi. (fg)=.phi.(f).phi.(g) for all f, g.mem.A; .phi. is left invariant if .phi.(1sf)=.phi.(f) for all s.mem.S and f.mem.A. It is well known that the set of multiplicative means on m(S) is precisely .betha.S, the Stone-Cech compactification of S[7]. A subalgebra of m(S) is (extremely) left amenable, denoted by (ELA)LA if it is nom closed, left translation invariant containing contants and has a multiplicative left invariant mean (LIM). A semigroup S is (ELA) LA, if m(S) is (ELA)LA. A subset E.contnd.S is left thick (T. Mitchell, [4]) if for any finite subser F.contnd.S, there exists s.mem.S such that $F_{s}$ .contnd.E or equivalently, the family { $s^{-1}$ E : s.mem.S} has finite intersection property.y.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.484-486
• /
• 2002

패턴의 이동, 회전, 크기변화에 영향을 받지 않는 불변 패턴 인식은 컴퓨터 비젼 및 패턴인식에서 오랫동안 다루어온 문제이다. 본 논문에서는 픽셀간의 거 리를 히스토그램으로 나타냄으로써 2차원 이진 패턴을 1차원 신호로 표현하는 방법을 제시한다. 제시되는 방법을 디스토그램(Distogram)이라 부르며 6개 로마문자의 이동, 회전, 크기 변화된 이미지를 테스트해봄으로써 디스토그램의 식별 능력을 테스트해본다.

• International Journal of Contents
• /
• v.5 no.2
• /
• pp.26-31
• /
• 2009

This paper describes a new image watermarking scheme invariant to rotation, scaling and translation (RST) attacks. For obtaining the invariance properties we propose to present an image of watermark by wedges and rings to convert its rotation to shift and then utilize the shift invariance property of the Direct Fourier Transform (DFT). But in contrast to conversional schemes based on the Fourier-Mellin transform (FMT), we do not use a log-polar mapping (LPM). As a result, our scheme preserves high quality of original image since it is not underwent to LPM For withstanding against JPEG compression, noise addition and low-pass (LP) filtering attacks a low frequency watermark is embedded into middle frequencies of the original image. Experiments with various attacks show the robustness of the proposed scheme.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.371-374
• /
• 2000

We propose an efficient method for content-based ultrasound image retrieval using magnitude frequency spectra and implement a retrieval system based on the proposed method. The target images are ultrasound images of adult organs. Trained users often acquire such images so that images of the same kind of organs are very similar, although their locations may not exactly coincide. Therefore, the magnitude frequency spectrum, which has a translation-invariant property, is used as a feature. All the object images in the image DB is pre-classified in the same kind organs. Experimental results show that the proposed method is superior to some well-known conventional methods.

• Korean Journal of Remote Sensing
• /
• v.30 no.5
• /
• pp.547-557
• /
• 2014

This paper presents a method for designing circular template used in similarity measurement for image registration. Circular template has translation and rotation invariant property, which results in correct matching of control points for image registration under the condition of translation and rotation between reference and sensed images. Circular template consisting of the pixels located on the multiple circumferences of the circles whose radii vary from zero to a certain distance, is converted to two-dimensional Discrete Polar Coordinate Matrix (DPCM), whose elements are the pixels of the circular template. For sensed image, the same type of circular template and DPCM are created by rotating the circular template repeatedly by a certain degree in the range between 0 and 360 degrees and then similarity is calculated using mutual information of the two DPCMs. The best match is determined when the mutual information for each rotation angle at each pixel in search area is maximum. The proposed algorithm was tested using KOMPSAT-2 images acquired at two different times and the results indicate high accurate matching performance under image rotation.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.50-60
• /
• 2000

In this paper, we propose a new composite feature consists of both color and shape information that are suitable for the task of character image retrieval. This approach extracts shape-based information using Zernike moments from Y image in YCbCr color space. Zernike moments can extract shape-based features that are invariant to rotation, translation, and scaling. We also extract color-based information from the DCT coefficients of Cr and Cb image. This approach is good method reflecting human visual property and is suitable for web application such as large image database system and animation because higher retrieval rate has been achieved using only 36 features. In experiment, this method is applied to 3,834 character images. We confirmed that this approach brought about excellent effect by ANMRR(Average of Normalized, Modified Retrieval Rank), which is used in the evaluation measure of MPEG-7 color descriptor and BEP(Bull's Eye Performance), which is used in evaluation measure of shape descriptor in character image retrieval.