• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.575-578
• /
• 2005

Topographical images, in case of aerial or satellite images, are usually similar in colors and textures, and complex in shapes. Thus we have to use shape features of images for efficiently retrieving a query image from topographical image databases. In this paper, we propose a shape feature extraction method which is suitable for topographical images. This method, which improves the existing projection in the Cartesian coordinates, performs the projection operation in the polar coordinates. This method extracts three attributes, namely the number of region pixels, the boundary pixel length of the region from the centroid, the number of alternations between region and background, along each angular direction of the polar coordinates. It extracts the features of complex shape objects which may have holes and disconnected regions. An advantage of our method is that it is invariant to rotation/scale/translation of images. Finally we show the advantages of our method through experiments by comparing it with CSS which is one of the most successful methods in the area of shape feature extraction

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.255-258
• /
• 2003

Recently, Digital Watermarking is used to authenticate data and to determine whether the data are distorted or not in medical images which is digitalized. The Fourier Mellin method using the Fourier Transform and the Log-Polar coordinate transform gets an invariant feature for RST distortion in images. But there are several problems in the real materialization. Interpolation of the image value should be considered according to the pixel position and so a watermark loss, original image distortion, numerical approximation is happened. Therefore there should be solved to realization of the Fourier Mellin method. Using the Look up table, there reduce the data loss caused by the conversion between Rectangular and Polar coordinate. After diagnose, medical images are transformed the Polar coordinate and taken the Discrete Fourier transform in the center of ROI region. Maintaining the symmetry in Fourier magnitude coefficient, the gaussian distributed random vectors and binary images are embedded in medical images.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.103-116
• /
• 2013

Prostate cancer is one of the most frequent cancers in men and is a major cause of mortality in the most of countries. In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation in TRUS images using Gabor feature extraction and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. The speckle reduction for preprocessing step has been achieved by using stick filter and top-hat transform has been implemented for smoothing the contour. A Gabor filter bank for extraction of rotation-invariant texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. Finally, the boundary of prostate is extracted by the snake-like contour algorithm. A number of experiments are conducted to validate this method and results showed that this new algorithm extracted the prostate boundary with less than 10.2% of the accuracy which is relative to boundary provided manually by experts.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.195-197
• /
• 2010

본 논문은 기존 평행좌표를 이용하는 얼굴 영상 대신 극좌표계 변환을 이용한 얼굴 영상을 이용하여 회전에 강인한 얼굴인식 방법을 제안한다. 극좌표계 변환 방법은 얼굴의 중심부분의 한 점을 극으로 삼아 이 점을 기준으로 360도 각 방향으로 일정 길이만큼 얼굴 영상을 샘플링 하여 새로운 얼굴 영상을 제작하는 방법이다. 이 극좌표계 변환 방법을 이용해 재구성된 영상에 대해 회귀( regression )문제 해결을 위해 변형된 LDA인 LDAr(LDA for regression)을 이용하여 얼굴의 중심부분의한 점인 극을 중심으로 임의의 각도로 회전된 영상의 회전 정도를 추정하여 이를 정규화 시키는 방법을 통해 얼굴 인식의 인식률을 향상시키고자 한다. LDAr은 LDA의 기본개념인 각 클래스 간 떨어진 정도를 최대화하는 것이 목적으로 클래스간 분산과 클래스내 분산의 비율을 최대화 하는 방법을 응용하여 이를 회귀문제에 적용할 수 있게 변형을 한 것이다. 즉, LDAr은 목표값(target)의 차이가 큰 샘플들과 목표값의 차이가 작은 샘플들 간의 거리의 비율을 최대화 하는 것을 목적으로 하게 된다. 제안된 방법을 Yale데이터에 적용하여 임의의 각도로 회전시킨 영상에 대해 회전 각도를 정확히 찾아내는 것을 확인할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.52-55
• /
• 2013

본 논문은 Boosted Random Ferns 기반의 회전 불변 얼굴 검출 방법을 제안한다. 기존 Random Ferns 의 경우 특징값을 추출할 때 임의로 선택한 두 픽셀의 밝기값 비교를 통하여 이진 특징값을 추출한다. 이 경우 해당 픽셀의 밝기값에 잡음이 포함되면 특징값이 부정확하게 추출되는 문제가 있다. 본 논문에서는 이러한 문제를 해결하기 위하여 임의로 두 블록을 선택하고 해당 블록내 밝기값의 평균을 비교하여 이진 특징값을 추출하였다. 또한 픽셀 위치를 임의로 선택하여 ferns 를 구성하였던 기존의 방법 대신 최고의 분류 성능을 가지는 fern 들을 이용하여 분류기를 구성하기 위해, AdaBoost 의 방법을 Random Ferns 에 맞게 변경하였다. Boosted Random Ferns 를 트리 구조의 cascade 노드에 방향과 각도에 따라 배치하여 연산 속도를 향상시키고 false-positive를 줄이는 효과를 보았다. CMU Rotated Face Database 를 사용하여 평가하였을 때, 기존 Random Ferns 는 false-positive 의 수가 57 개 일 때 66%의 검출률을 보인 반면, Boosted Random Ferns 는 false-positive 의 수가 45 개 일 때 88%의 검출률을 보였다.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.427-437
• /
• 2004

Shape comparison between 3D models is essential for shape recognition, retrieval, classification, etc. In this paper, we propose a method for comparing 3D shapes, which is invariant under translation, rotation and scaling of models and is robust to non-uniformly distributed and incomplete data sets. first, a modal model is constructed from input data using vibration modes and then shape similarity is evaluated with modal strain energy. The proposed method provides global-to-local ordering of shape deformation using vibration modes ordered by frequency Thus, we evaluated similarity in terms of global properties of shape without being affected localised shape features using ordered shape representation and modal strain one energy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.11
• /
• pp.2739-2749
• /
• 1996

This aper introduces the multiple Neocognitron module approach for the effective target reognition. The Neocognitron which is designed to classify a pattern by extracting the local features from it, seems to be an unique method that can perform a pattern recognition using the neural networks. But due to its rigid structure, the Neocognitron must be reconstructed whenever there exists a variation on the number of classes. This is a quite difficult problem for the target recognition application that needs huge amount of computation and numerous classes to be classified. In this paper, we construct several smaller Necognitrom modules and train each module to adapt each class. After construction of the mulules, we integrate them in parallel so as to adaopt input at the same time and to produce each score that shold be matched to be learned class. This approach can reduce the sizes of the networks and is adaptive to the increase of classes as well as the authentic distortion, shift, scale variation and slight rotation invariant properties of general Neocognitron. This paper show the effectiveness of the proposed approach through some experience and performs analysis of the inhibitory interconnections in the architecture of the multiple module structure.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.6
• /
• pp.283-288
• /
• 2011

This paper have proposed an object retrieval using the corners area variability based on correlogram. The proposed algorithm is processed as follows. First, the corner points of the object in an image are extracted and then the feature vectors are obtained. It are rearranged according to the number dimension and consist of sequence vectors. And the similarity based on the maximum of sequence vectors is measured. The proposed technique is invariant to the rotation or the transfer of the objects and more efficient in case that the objects present simple structure. In simulation that use Wang's database, the method presents that the recall property is improved by 0.03% and more than the standard corner patch histogram.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.4
• /
• pp.87-91
• /
• 2003

In this paper, a rotation invariant fingerprint identification system is implemented using the circular harmonic filter and phase only correlator. We extracted the phase component from input fingerprint image and correlate it with the circular harmonic filter of the reference fingerprint image by POC. The input image is obtained using a prism operating in the internal full reflection mode. Then the input image is transformed to two dimensional Fourier spectrum in optical way and the phase component is extracted using a digital system from the spectrum. Because composed of the optical system and digital algorithm, the proposed system has the advantages of the two technologies such as realtime parallel processing property of the optics and the flexibility of the digital system.

• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.