• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.634-638
• /
• 2018

Haze is a factor that degrades the performance of various image processing algorithms, such as those for detection, tracking, and recognition using an electro-optical sensor. For robust operation of an electro-optical sensor-based unmanned system used outdoors, an algorithm capable of effectively removing haze is needed. As a haze removal method using a single electro-optical sensor, the dark channel prior using statistical properties of the electro-optical sensor is most widely known. Previous methods used a square filter in the process of obtaining a transmission using the dark channel prior. When a square filter is used, the effect of removing haze becomes smaller as the size of the filter becomes larger. When the size of the filter becomes excessively small, over-saturation occurs, and color information in the image is lost. Since the size of the filter greatly affects the performance of the algorithm, a relatively large filter is generally used, or a small filter is used so that no over-saturation occurs, depending on the image. In this paper, we propose an improved haze removal method using color image segmentation. The parameters of the color image segmentation are automatically set according to the information complexity of the image, and the over-saturation phenomenon does not occur by estimating the amount of transmission based on the parameters.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.2
• /
• pp.80-85
• /
• 2011

Speaker change detection involves the identification of time indices of an audio stream, where the identity of the speaker changes. In this paper, we propose novel measures for the speaker change detection based on a graph-partitioning criterion over the pairwise distance matrix of feature-vector stream. Experiments on both synthetic and real-world data were performed and showed that the proposed approach yield promising results compared with the conventional statistical measures.

• Journal of Digital Contents Society
• /
• v.1 no.1
• /
• pp.53-64
• /
• 2000

This paper is related to color image segmentation scheme which makes it possible to achieve the excellent segmented results by block-based segmentation using Y/C bit-plane summation image. First, normalized chrominance summation image is obtained by normalizing the image which is summed up the absolutes of color-differential values between R, G, B images. Secondly, upper 2 bits of the luminance image and upper 6bits of and the normalized chrominance summation image are bitwise operated by the pixel to generate the Y/C bit-plane summation image. Next, the Y/C bit-plane summation image divided into predetermined block size, is classified into monotone blocks, texture blocks and edge blocks, and then each classified block is merged to the regions including one more blocks in the individual block type, and each region is selectively allocated to unique marker according to predetermined marker allocation rules. Finally, fine segmented results are obtained by applying the watershed algorithm to each pixel in the unmarked blocks. As shown in computer simulation, the main advantage of the proposed method is that it suppresses the over-segmentation in the texture regions and reduces computational load. Furthermore, it is able to apply global parameters to various images with different pixel distribution properties because they are nonsensitive for pixel distribution. Especially, the proposed method offers reasonable segmentation results in edge areas with lower contrast owing to the regional characteristics of the color components reflected in the Y/C bit-plane summation image.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.1-11
• /
• 2006

Many research demonstrations and commercial applications have been tried to develop face detection and recognition systems. Human face detection plays an important role in applications such as access control and video surveillance, human computer interface, identity authentication, etc. There are some special problems such as a face connected with background, faces connected via the skin color, and a face divided into several small parts after skin region segmentation in generally. It can be allowed many face detection techniques to solve the first and second problems. However, it is not easy to detect a face divided into several parts of regions for reason of different illumination conditions in the third problem. Therefore, we propose an efficient modified skin segmentation algorithm to solve this problem because the typical region segmentation algorithm can not be used to. Our algorithm detects skin regions over the entire image, and then generates face candidate regions using our skin segmentation algorithm For each face candidate, we implement the procedure of region merging for divided regions in order to make a region using adjacency between homogeneous regions. We utilize various different searching window sizes to detect different size faces and a face detection classifier based on a back-propagation algorithm in order to verify whether the searching window contains a face or not.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.1
• /
• pp.55-68
• /
• 2012

In this paper, we propose a novel method to solve the problem of excessive segmentation out of the method of segmenting regions from an image using Homogeneity Threshold($H_T$). The algorithm of the previous image segmentation based on $H_T$ was carried out region growth by using only the center pixel of selected window. Therefore it was caused resulting in excessive segmented regions. However, before carrying region growth, the proposed method first of all finds out whether the selected window is homogeneity or not. Subsequently, if the selected window is homogeneity it carries out region growth using the total pixels of selected window. But if the selected window is not homogeneity, it carries out region growth using only the center pixel of selected window. So, the method can reduce remarkably the number of excessive segmented regions of image segmentation based on $H_T$. In order to show the validity of the proposed method, we carried out multiple experiments to compare the proposed method with previous method in same environment and conditions. As the results, the proposed method can reduce the number of segmented regions above 40% and doesn't make any difference in the quality of visual image when we compare with previous method. Especially, when we compare the image united with regions of descending order by size of segmented regions in experimentation with the previous method, even though the united image has regions more than 1,000, we can't recognize what the image means. However, in the proposed method, even though image is united by segmented regions less than 10, we can recognize what the image is. For these reason, we expect that the proposed method will be utilized in various fields, such as the extraction of objects, the retrieval of informations from the image, research for anatomy, biology, image visualization, and animation and so on.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.513-524
• /
• 2022

Recently, detecting damages of civil infrastructures from digital images using deep learning technology became a very popular research topic. In order to adapt those methodologies to the field, it is essential to explain robustness of deep learning models. Our research points out that the existing pixel-based deep learning model evaluation metrics are not sufficient for detecting cracks since cracks have linear appearance, and proposes a new evaluation methodology to explain crack segmentation deep learning model more rationally. Specifically, we design, implement and validate a methodology to generate tolerance buffer alongside skeletonized ground truth data and prediction results to consider overall similarity of topology of the ground truth and the prediction rather than pixel-wise accuracy. We could overcome over-estimation or under-estimation problem of crack segmentation model evaluation through using our methodology, and we expect that our methodology can explain crack segmentation deep learning models better.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.7
• /
• pp.4641-4650
• /
• 2015

This study aims to further strengthen the medical expertise to offer specialized medical care specialization strategies to gain a competitive edge through the customer segmentation of the Regional Public Hospital. Investigation period was selected to study the inpatients 26,658 people January to December 2013. The method of analysis are Cluster analysis and Decision Tree Analysis. In conclusion, female, age over 60, and diseases in musculoskeletal system and connective tissue were commonly selected as identifiers of the target market of Regional Public Hospital. Customers in this target market are loyal to specialized medical service and keeping continuous relationship with these customers through communication and monitoring of results of provided medical service would be important because the effect of word of mouth propagated to other group of customers having equivalent scale of consumption is expected. And the concentration of the scope of medical service of Regional Public Hospital and the collaboration and mutual reliance of medical service under the strategic alliance with other institutions and private hospitals are also needed.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.4
• /
• pp.26-34
• /
• 2008

This study focus on segmentation process that classifies road surfaces into 5 different categories, dry, wet water, icy, and snowy surfaces by analyzing asphalt-paved road images taken in daylight. By using the polarization coefficients, the proportions of horizontally polarized components to vertically polarized components, regions with over 1.3 polarization coefficients are classified as wet surfaces. Except for wet surfaces, the decision process a lies time-frequency analysis to other parts by using the third order wavelet packet transform. In addition, by using the average frequency characteristics of dry and icy surfaces from image templates, decide which is closer to a test image, and finally identify dry and icy surfaces. It is confirmed that the reposed estimation and segmentation of recognition on various images. This can be interpreted as an indication that image-only mad surface condition supervision is probable.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.7-14
• /
• 2005

In this paper we proposed the block-based color image segmentation method using the cylindrical metric to solve the problems such as long processing time and over segmentation due to noise and texture properties in the conventional methods. In the proposed method we define the new similarity function and the merge condition between regions to merge initial regions with the same size considering the color and texture properties of chromatic and achromatic regions which is defined according to the HSI color values, and we continue to merge boundary blocks into the adjacent region already segmented to maintain edges until the size of block is one. In the simulation results the proposed method is better than the conventional methods in the evaluation of the segmented regions of texture and edge region, and we found that the processing time is decreased by factor of two in the proposed method.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2555-2564
• /
• 2000

In this paper, a new unsupervised image segmentation algorithm is proposed. To model the contextual information presented in images, the characteristics of the Markov random fields (MRF) are utilized. Textured images are modeled as realizations of the stationary Gaussian MRF on a two-dimensional square lattice using the conditional autoregressive (CAR) equations with a second-order noncausal neighborhood. To detect boundaries, hypothesis tests over two masked areas are performed. Under the hypothesis, masked areas are assumed to belong to the same class of textures and CAR equation parameters are estimated in a minimum-mean-square-error (MMSE) sense. If the hypothesis is rejected, a measure of dissimilarity between two areas is accumulated on the rejected area. This approach produces potential edge maps. Using these maps, boundary detection can be performed, which resulting no micro edges. The performance of the proposed algorithm is evaluated by some experiments using real images as weB as synthetic ones. The experiments demonstrate that the proposed algorithm can produce satisfactorY segmentation without any a priori information.