• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.3
• /
• pp.39-52
• /
• 2009

Scale Invariant Feature Transform (SIFT) is an effective algorithm in object recognition, panorama stitching, and image matching, however, due to its complexity, real time processing is difficult to achieve with software approaches. This paper proposes using a reconfigurable hardware processor with integer half kernel. The integer half kernel Gaussian reduces the Gaussian pyramid complexity in about half [] and the reconfigurable processor carries out a parallel implementation of a full search Fast SIFT algorithm. We use a low memory, fine grain single instruction stream multiple data stream (SIMD) pixel processor that is currently being developed. This implementation fully exposes the available parallelism of the SIFT algorithm process and exploits the processing and I/O capabilities of the processor which results in a system that can perform real time image and video compression. We apply this novel implementation to images and measure the effectiveness. Experimental simulation results indicate that the proposed implementation is capable of real time applications.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.24-29
• /
• 2014

Digital mammography is the most common technique for the early detection of breast cancer. To diagnose the breast cancer in early stages and treat efficiently, many image enhancement methods have been developed. This paper presents a multi-scale contrast enhancement method in the Laplacian pyramid for the digital mammogram. The proposed method decomposes the image into the contrast measures by the Gaussian and Laplacian pyramid, and the pyramid coefficients of decomposed multi-resolution image are defined as the frequency limited local contrast measures by the ratio of high frequency components and low frequency components. The decomposed pyramid coefficients are modified by the contrast measure for enhancing the contrast, and the final enhanced image is obtained by the composition process of the pyramid using the modified coefficients. The proposed method is compared with other existing methods, and demonstrated to have quantitatively good performance in the contrast measure algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.156-160
• /
• 2011

This paper describes the design and implementation of a System-on-a-Chip (SoC) for pattern recognition to use in embedded applications. The target Soc consists of LEON2 core, AMBA/APB bus-systems and custom-designed accelerators for Gaussian Pyramid construction, lighting compensation and histogram equalization. A new FPGA-based prototyping platform is implemented and used for design and verification of the target SoC. To ensure that the implemented SoC satisfies the required performances, a pattern recognition application is performed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.3
• /
• pp.41-48
• /
• 2012

Using multi-sensor or multi-temporal high resolution satellite images together is essential for efficient applications in remote sensing area. The purpose of this paper is to estimate geometric difference of translations between high-resolution optical and SAR images automatically. The geometric and radiometric pre-processing steps were fulfilled to calculate the similarity between optical and SAR images by using Mutual Information method. The coarsest-level pyramid images of each sensor constructed by gaussian pyramid method were generated to estimate the initial translation difference of the x, y directions for calculation efficiency. The precise geometric difference of translations was able to be estimated by applying this method from coarsest-level pyramid image to original image in order. Yet even when considered only translation between optical and SAR images, the proposed method showed RMSE lower than 5m in all study sites.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.304-306
• /
• 2003

본 논문은 손상되지 않은 지문과 손상된 지문에 대해 전처리 및 3 레벨 가우스 피라미드(Gaussian pyramid)변환과 왈쉬(Walsh)변환을 하고, 출력되는 결(texture) 정보를 평활화 및 이진화를하여 해밍거리(Hamming Distance)를 계산하였다. 여기서 얻은 결 정보에 대한 해밍거리 변화율은 인식을 위한 매칭 변수로 사용하였다. 이러한 비교를 위해 이미지를 전처리하여 잡음을 제거하고, 대비를 개선한 후 각 이미지를 이진화 이미지로 만든 다음 세선화 처리를 하였다. 3 레벨 가우스 피라미드 변환은 이미지의 크기를 1/8로 축소하며, 해밍거리 변화율은 타인 수락율(FAR: False Acceptance Ratio)과 본인 거부율 (FRR: False Rejection Ratio)계산에 사용하였다. 그 결과 손상된 동일 지문에 대한 본인 거부율은 -20% 내외이었으며, 타인수락율은 -50%가 되어 지문이 일부 손상되었어도 결 무늬에 대한 해밍거리는 인식의 특성 벡터로 사용할 수 있음을 알 수 있다.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.559-573
• /
• 2018

Recently, one of the most actively applied image media in the most fields such as virtual reality (VR) is omni-directional or panorama image. This image is generated by stitching images obtained by various methods. In this process, it takes the most time to extract keypoints necessary for stitching. In this paper, we analyze the parameters involved in the extraction of SIFT keypoints with the aim of reducing the computation time for extracting the most widely used SIFT keypoints. The parameters considered in this paper are the initial standard deviation of the Gaussian kernel used for Gaussian filtering, the number of gaussian difference image sets for extracting local extrema, and the number of octaves. As the SIFT algorithm, the Lowe scheme, the originally proposed one, and the Hess scheme which is a convolution cascade scheme, are considered. First, the effect of each parameter value on the computation time is analyzed, and the effect of each parameter on the stitching performance is analyzed by performing actual stitching experiments. Finally, based on the results of the two analyses, we extract parameter value set that minimize computation time without degrading.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.4
• /
• pp.321-330
• /
• 1999

Automation of observation and positioning of fiducial marks is made possible with the application of image matching technique, developed through the cooperative research effort of computer vision and digital photogrammetry. The major problem in such automation effort is to minimize the computing time and to increase the positional accuracy. Except for scanning and ground control surveying, the interior orientation process was automated in this study, through the development of an algorithm which applies the image matching and image processing techniques. The developed system was applied to close-range photogrammetry and the analysis of the results showed 54% improvement in processing time. For fiducial mark observation during interior orientation, the Laplacian of Gaussian transformation and the Hough transformation were applied to determine the accurate position of the center point, and the correlation matching and the least squares matching method were then applied to improve the accuracy of automated observation of fiducial marks. Image pyramid concept was applied to reduce the computing time of automated positioning of fiducial mark.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.74-86
• /
• 1994

In this paper a hierarchical stereo matching algorithm to obtain the disparity in wavelet transformed domain by using locally adaptive window and weights is proposed. The pyramidal structure obtained by wavelet transform is used to solve the loss of information which the conventional Gaussian or Laplacian pyramid have. The wavelet transformed images are decomposed into the blurred image the horizontal edges the vertical edges and the diagonal edges. The similarity between each wavelet channel of left and right image determines the relative importance of each primitive and make the algorithm perform the area-based and feature-based matching adaptively. The wavelet transform can extract the features that have the dense resolution as well as can avoid the duplication or loss of information. Meanwhile the variable window that needs to obtain precise and stable estimation of correspondense is decided adaptively from the disparities estimated in coarse resolution and LL(low-low) channel of wavelet transformed stereo image. Also a new relaxation algorithm that can reduce the false match without the blurring of the disparity edge is proposed. The experimental results for various images show that the proposed algorithm has good perfpormance even if the images used in experiments have the unfavorable conditions.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.4
• /
• pp.1035-1041
• /
• 2016

Internal cracks in products are invisible and can lead to fatal crashes or damage. Since X-rays can penetrate materials and be attenuated according to the material’s thickness and density, they have rapidly become the accepted technology for non-destructive inspection of internal cracks. This paper presents a robust crack filter based on local gray level variation and multiscale analysis for automatic detection of cracks in X-ray images. The proposed filter takes advantage of the image gray level and its local variations to detect cracks in the X-ray image. To overcome the problems of image noise and the non-uniform intensity of the X-ray image, a new method of estimating the local gray level variation is proposed in this paper. In order to detect various sizes of crack, this paper proposes using different neighboring distances to construct an image pyramid for multiscale analysis. By use of local gray level variation and multiscale analysis, the proposed crack filter is able to detect cracks of various sizes in X-ray images while contending with the problems of noise and non-uniform intensity. Experimental results show that the proposed crack filter outperforms the Gaussian model based crack filter and the LBP model based method in terms of detection accuracy, false detection ratio and processing speed.

• Journal of Korea Multimedia Society
• /
• v.22 no.3
• /
• pp.335-348
• /
• 2019

Cell segmentation and counting represent one of the most important tasks required in order to provide an exhaustive understanding of biological images. Conventional features suffer the lack of spatial consistency by causing the joining of the cells and, thus, complicating the cell counting task. We propose, in this work, a cascade of networks that take as inputs different versions of the original image. After constructing a Gaussian pyramid representation of the microscopy data, the inputs of different size and spatial resolution are given to a cascade of deep convolutional autoencoders whose task is to reconstruct the segmentation mask. The coarse masks obtained from the different networks are summed up in order to provide the final mask. The principal and main contribution of this work is to propose a novel method for the cell counting. Unlike the majority of the methods that use the obtained segmentation mask as the prior information for counting, we propose to utilize the hidden latent representations, often called the high-level features, as the inputs of a neural network based regressor. While the segmentation part of our method performs as good as the conventional deep learning methods, the proposed cell counting approach outperforms the state-of-the-art methods.