• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.9 no.2
• /
• pp.49-56
• /
• 1991

In this study, 3D positioning of CCT digital imagery was done by using a personal computer image processing method to increase the economic and time efficiency of SPOT satellite imagery. Image matching technique which applies statistical theories, was applied to acqusition of satellite imagery. The reliability of these coordinates was anlysed to presente a new algorithm for three dimensional positioning necessary in digital elevation modelling and orthophoto production. In acquiring image coordinates from CCT digital satellite imagery, accuracy of planimetric and height coordinates was improved by applying the image matching technique and it was found through analysis of correlation factors between sizes of target window that 19$\times$19 pixels was the most suitable size for image coordinate acquisition. From these results, it was able to present an algorithm about utility of digital imagery in the analysis of SPOT satellite data.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.7 no.1
• /
• pp.87-99
• /
• 2015

In recent years, the development of autonomous surface vehicles has been a field of increasing research interest. There are two major areas in this field: control theory and path planning. This study focuses on path planning, and two objectives are discussed: path planning for Unmanned Surface Vehicles (USVs) and implementation of path planning in a real map. In this paper, satellite thermal images are converted into binary images which are used as the maps for the Finite Angle $A^*$ algorithm ($FAA^*$), an advanced $A^*$ algorithm that is used to determine safer and suboptimal paths for USVs. To plan a collision-free path, the algorithm proposed in this article considers the dimensions of surface vehicles. Furthermore, the turning ability of a surface vehicle is also considered, and a constraint condition is introduced to improve the quality of the path planning algorithm, which makes the traveled path smoother. This study also shows a path planning experiment performed on a real satellite thermal image, and the path planning results can be used by an USV.

• International Journal of Contents
• /
• v.11 no.2
• /
• pp.15-19
• /
• 2015

In this paper, we propose an efficient document layout analysis algorithm that includes table detection. Typical methods of document layout analysis use the height and gap between words or columns. To correspond to the various styles and sizes of documents, we propose an algorithm that uses the mean value of the distance transform representing thickness and compare with components in the local area. With this algorithm, we combine a table detection algorithm using the same feature as that of the text classifier. Table candidates, separators, and big components are isolated from the image using Connected Component Analysis (CCA) and distance transform. The key idea of text classification is that the characteristics of the text parallel components that have a similar thickness and height. In order to estimate local similarity, we detect a text region using an adaptive searching window size. An improved adaptive run-length smoothing algorithm (ARLSA) was proposed to create the proper boundary of a text zone and non-text zone. Results from experiments on the ICDAR2009 page segmentation competition test set and our dataset demonstrate the superiority of our dataset through f-measure comparison with other algorithms.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.66-69
• /
• 1998

Comparative genomic hybridization (CGH) is an important molecular cytogenetics technique that maps abnormal copy number of specific DNA sequence of the chromosome. CGH is based on quantitative digital image analysis of ratio images from fluorescently labeled chromosomes. In this paper, we would like to introduce how recently developed image analysis algorithms are used for CGH techniques. To average the ratio profile of each chromosome, binarization, skeletonization, and stretching of chromosome images have been studied. Developed algorithms have been implemented in the karyotyping system ChIPS commercially developed at Biomedlab Co. Ltd.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.2
• /
• pp.71-78
• /
• 2021

In order to classify a target image in a cluster of images, the difference in brightness between the object and the background is mainly concerned, which is not easy to classify if the shape of the object is blurred and the sharpness is low. However, there are a few studies attempted to solve these problems, and there is still the problem of not properly distinguishing between wrong pattern and right pattern images when applied to actual data analysis. In this paper, we propose an algorithm that classifies 3D films into sharp and blurry using the width of the pixel values histogram. This algorithm determines the width of the right and wrong images based on the width of the pixel distributions. The larger the width histogram, the sharp the image, while the shorter the width histogram the blurry the image. Experiments show that the proposed algorithm reflects that the characteristics of these histograms allows classification of all wrong images and right images. To determine the reliability and validity of the proposed algorithm, we compare the results with the other obtained from preprocessed 3D films. We then trained the 3D films using few-shot learning algorithm for accurate classification. The experiments verify that the proposed algorithm can perform higher without complicated computations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.2
• /
• pp.1-10
• /
• 2003

This paper presents an efficient method for image segmentation based on a multiresolution application of a wavelet transform and watershed segmentation algorithm. The procedure toward complete segmentation consists of four steps: pyramid representation, image segmentation, region merging and region projection. First, pyramid representation creates multiresolution images using a wavelet transform. Second, image segmentation segments the lowest-resolution image of the pyramid using a watershed segmentation algorithm. Third, region merging merges the segmented regions using the third-order moment values of the wavelet coefficients. Finally, the segmented low-resolution image with label is projected into a full-resolution image (original image) by inverse wavelet transform. Experimental results of the presented method can be applied to the segmentation of noise or degraded images as well as reduce over-segmentation.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.339-342
• /
• 2005

We present an efficient block-based motion estimation algorithm with motion analysis. The motion analysis determines a size of search pattern and a maximum repeated count of search pattern. In case of large movement in large image, we reduce search points and the local minimum which caused by low performance. The proposed algorithm employs with searching step of 2. The first step determines an initial search point with neighbor block vector and a size of initial search pattern. The second step determines a size of search pattern and a maximum repeated count with motion analysis. We improve motion prediction accuracy while reducing required computational complexity compared to other fast block-based motion estimation algorithms.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.603-605
• /
• 1997

A new algorithm using 1-dimensional wavelet transform for autofocusing of optical instrument has been developed. Previous studies based on the conventional frequency analysis have shown that as the lens-object distance approaches the optimum value, the high frequency energy in the corresponding image shows a consistent increase. However, as conventional frequency analysis techniques hide spatial distribution of each band energy, shape information in the original signal cannot be easily utilized. In this paper, a newly devised wavelet based focus measuring scheme is presented. Unlike other frequency domain analysis techniques that simply produce "frequency-only" spectra, wavelet analysis provides a "time-frequency" localized view of a given signal. As a result, both frequency band filtering and spatial distribution filtering can easily be realized. Depending on the proposed focus quality measuring algorithm, a fast and reliable automatic focus adjustment of optical devices could be implemented.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.239-246
• /
• 2005

Biologist must have to do 2DGE biological experiment for Protein Search and Analysis. This experiment coming into being 2 dimensional image. 2DGE (2D Gel Electrophoresis : two dimensional gel electrophoresis) image is the most widely used method for isolating of the objective protein by comparative analysis of the protein spot pattern in the gel plane. The process of protein spot analysis, firstly segment protein spots that are spread in 2D gel plane by image processing and can find important protein spots through comparative analysis with protein pattern of contrast group. In the algorithm which detect protein spots, previous 2DGE image analysis is applies gaussian fitting, however recently Watersheds region based segmentation algorithm, which is based on morphological segmentation is applied. Watersheds has the benefit that segment rapidly needed field in big sized image, however has under-segmentation and over-segmentation of spot area when gray level is continuous. The drawback was somewhat solved by marker point institution, but needs the split and merge process. This paper introduces a novel marker search of protein spots by watersheds-based hierarchical threshold, which can resolve the problem of marker-driven watersheds.