• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.633-637
• /
• 2001

In this paper, we proposed model creation algorithm for multiple moving objects tracking. The proposed algorithm is divided that the initial model creation step as moving objects are entered into background image and the model reformation step in the moving objects tracking step. In the initial model creation step, the initial model is created by AND operating division image, divided using difference image and clustering method, and edge image of the current image. In the model reformation step, a new model was reformed in the every frame to adapt appearance change of moving objects using Hausdorff Distance and 2D-Logarithmic searching algorithm. We simulated for driving cart in the road. In the result, model was created over 98% in case of irregular approach direction of cars and tracking objects number.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.637-644
• /
• 2006

Biomedical image is often complex. An applied image analysis system should deal with the images which are of quite low quality and are challenging to segment. This paper presents a framework for color cell image segmentation by learning and classification online. It is a robust two-stage scheme using kernel method and watershed transform. In first stage, a two-class SVM is employed to discriminate the pixels of object from background; where the SVM is trained on the data which has been analyzed using the mean shift procedure. A real-time training strategy is also developed for SVM. In second stage, as the post-processing, local watershed transform is used to separate clustering cells. Comparison with the SSF (Scale space filter) and classical watershed-based algorithm (those are often employed for cell image segmentation) is given. Experimental results demonstrate that the new method is more accurate and robust than compared methods.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.9
• /
• pp.76-90
• /
• 1999

In this paper, a color image retrieval algorithm is proposed based on color histogram and color texture. The representative color vectors of a color image are made from k-means clustering of its color histogram, and color texture is generated by centering around the color of pixels with its color vector. Thus the color texture means texture properties emphasized by its color histogram, and it is analyzed by Gaussian Markov Random Field (GMRF) model. The proposed algorithm can work efficiently because it does not require any low level image processing such as segmentation or edge detection, so it outperforms the traditional algorithms which use color histogram only or texture properties come from image intensity.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.5
• /
• pp.57-63
• /
• 2017

In the paper, we propose a new reliable technique for measuring food intake based on image automatically without user intervention. First, food and bowl image before and after meal is obtained by user. The food and the bowl are divided into each region by the K-means clustering, Otsu algorithm, Morphology, etc. And the volume of food is measured by a proportional expression based on the information of the container such as it's entrance diameter, depth, and bottom diameter. Finally, our method calculates the volume of the consumed food by the difference between before and after meal. The proposed technique has higher accuracy than existing method for measuring food intake automatically. The experiment result shows that the average error rate is up to 7% for three types of containers. Computer simulation results indicate that the proposed algorithm is a convenient and accurate method of measuring the food intake.

• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.479-490
• /
• 2003

This study proposed a modified anisotropic diffusion restoration for image classification. The anisotropic diffusion restoration uses a probabilistic model based on Markov random field, which represents geographical connectedness existing in many remotely sensed images, and restores them through an iterative diffusion processing. In every iteration, the bonding-strength coefficient associated with the spatial connectedness is adaptively estimated as a function of brightness gradient. The gradient function involves a constant called "temperature", which determines the amount of discontinuity and is continuously decreased in the iterations. In this study, the proposed method has been extensively evaluated using simulated images that were generated from various patterns. These patterns represent the types of natural and artificial land-use. The simulated images were restored by the modified anisotropic diffusion technique, and then classified by a multistage hierarchical clustering classification. The classification results were compared to them of the non-restored simulation images. The restoration with an appropriate temperature considerably reduces error in classification, especially for noisy images. This study made experiments on the satellite images remotely sensed on the Korean peninsula. The experimental results show that the proposed approach is also very effective on image classification in remote sensing.

• Journal of Broadcast Engineering
• /
• v.1 no.2
• /
• pp.165-175
• /
• 1996

In this paper, the image segmentation method based on the hierarchical pyramid image structure of reduced resolution versions of the image for solving the problems in the conventional methods is presented. This method is described the object detection and delineation by statistical approach. In the object detection method, IFSVR( Inverse-father-son variance ratio) method and FSVR(father-son variance ratio ) method are proposed for solving clustering validity problem occurred In the hierarchical pyramid image structure. An optimal object pixel Is detected at some level by this method. In the object delineation method, the iterative algorithm by top-down traversing method is proposed for moving the optimal object pixel to levels of higher resolution. Using the computer simulation, the results by the proposed statistical methods and object traversing method are investigated for the binary Image and the real image. At the results of computer simulation, the proposed methods of image segmentation based on the hierarchical pyramid Image structure seem to have useful properties and deserve consideration as a possible alternative to existing methods of image segmentation. The computation for the proposed method is required 0(log n) for n${\times}$n input image.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.53-66
• /
• 2006

This paper proposes the combined image retrieval system that gives the same relevance as exhaustive search method while its performance can be considerably improved. This system is combined with two different retrieval methods and each gives the same results that full exhaustive search method does. Both of them are two-stage method. One uses condensation of feature vectors, and the other uses binary-tree clustering. These two methods extract the candidate images that always include correct answers at the first stage, and then filter out the incorrect images at the second stage. Inasmuch as these methods use equal algorithm, they can get the same result as full exhaustive search. The first method condenses the dimension of feature vectors, and it uses these condensed feature vectors to compute similarity of query and images in database. It can be found that there is an optimal condensation ratio which minimizes the overall retrieval time. The optimal ratio is applied to first stage of this method. Binary-tree clustering method, searching with recursive 2-means clustering, classifies each cluster dynamically with the same radius. For preserving relevance, its range of query has to be compensated at first stage. After candidate clusters were selected, final results are retrieved by computing similarities again at second stage. The proposed method is combined with above two methods. Because they are not dependent on each other, combined retrieval system can make a remarkable progress in performance.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.7-16
• /
• 2009

Some clustering algorithms have a problem that an image is over-segmented since both the spatial information between the segmented regions is not considered and the number of the clusters is defined in advance. Therefore, they are difficult to be applied to the applicable fields. This paper proposes the new post-processing methods, a reclassification of the inhomogeneous clusters and a region merging using Baysian algorithm, that improve the segmentation results of the clustering algorithms. The inhomogeneous cluster is firstly selected based on variance and between-class distance and it is then reclassified into the other clusters in the reclassification step. This reclassification is repeated until the optimal number determined by the minimum average within-class distance. And the similar regions are merged using Baysian algorithm based on Kullbeck-Leibler distance between the adjacent regions. So we can effectively solve the over-segmentation problem and the result can be applied to the applicable fields. Finally, we design a classification system for the segmented regions to validate the proposed method. The segmented regions are classified by SVM(Support Vector Machine) using the principal colors and the texture information of the segmented regions. In experiment, the proposed method showed the validity for various real-images and was effectively applied to the designed classification system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.187-194
• /
• 2017

The present study introduces a method to parallelize k-means clustering algorithm for fast unsupervised classification of large satellite imagery. Known as a representative algorithm for unsupervised classification, k-means clustering is usually applied to a preprocessing step before supervised classification, but can show the evident advantages of parallel processing due to its high computational intensity and less human intervention. Parallel processing codes are developed by using multi-threading based on OpenMP. In experiments, a PC of 8 multi-core integrated CPU is involved. A 7 band and 30m resolution image from LANDSAT 8 OLI and a 8 band and 10m resolution image from Sentinel-2A are tested. Parallel processing has shown 6 time faster speed than sequential processing when using 10 classes. To check the consistency of parallel and sequential processing, centers, numbers of classified pixels of classes, classified images are mutually compared, resulting in the same results. The present study is meaningful because it has proved that performance of large satellite processing can be significantly improved by using parallel processing. And it is also revealed that it easy to implement parallel processing by using multi-threading based on OpenMP but it should be carefully designed to control the occurrence of false sharing.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.65-65
• /
• 2002

In remote sensing, images are acquired over the same area by sensors of different spectral ranges (from the visible to the microwave) and/or with different number, position, and width of spectral bands. These images are generally partially redundant, as they represent the same scene, and partially complementary. For many applications of image classification, the information provided by a single sensor is often incomplete or imprecise resulting in misclassification. Fusion with redundant data can draw more consistent inferences for the interpretation of the scene, and can then improve classification accuracy. The common approach to the classification of multisensor data as a data fusion scheme at pixel level is to concatenate the data into one vector as if they were measurements from a single sensor. The multiband data acquired by a single multispectral sensor or by two or more different sensors are not completely independent, and a certain degree of informative overlap may exist between the observation spaces of the different bands. This dependence may make the data less informative and should be properly modeled in the analysis so that its effect can be eliminated. For modeling and eliminating the effect of such dependence, this study employs a strategy using self and conditional information variation measures. The self information variation reflects the self certainty of the individual bands, while the conditional information variation reflects the degree of dependence of the different bands. One data set might be very less reliable than others in the analysis and even exacerbate the classification results. The unreliable data set should be excluded in the analysis. To account for this, the self information variation is utilized to measure the degrees of reliability. The team of positively dependent bands can gather more information jointly than the team of independent ones. But, when bands are negatively dependent, the combined analysis of these bands may give worse information. Using the conditional information variation measure, the multiband data are split into two or more subsets according the dependence between the bands. Each subsets are classified separately, and a data fusion scheme at decision level is applied to integrate the individual classification results. In this study. a two-level algorithm using hierarchical clustering procedure is used for unsupervised image classification. Hierarchical clustering algorithm is based on similarity measures between all pairs of candidates being considered for merging. In the first level, the image is partitioned as any number of regions which are sets of spatially contiguous pixels so that no union of adjacent regions is statistically uniform. The regions resulted from the low level are clustered into a parsimonious number of groups according to their statistical characteristics. The algorithm has been applied to satellite multispectral data and airbone SAR data.