• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.1
• /
• pp.82-89
• /
• 2001

This paper presents recognition of unconstrained handwritten numeral strings using decision value generator, which is combined with both isolated digit identifier and recognizer designed with structural characteristics of digits. Numerical string recognition system is composed of three modules, which are pre-segmentation, segmentation and recognition. Pre-segmentation module classifies a numeral string into sub-images, which are isolated digit, touched digits or broken digit, using confidence value of decision value generator. Segmentation module segments touched digits using reliability value of decision value generator that will separate the leftmost digit from touched string of digits. Segmentation-based and segmentation-free methods have used for classification and segmentation, respectively. To evaluate proposed method, experiments have carried out with handwritten numeral strings of NIST SD19 and higher recognition performance than previous works has obtained with 96.7%.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.3
• /
• pp.35-46
• /
• 1992

Recently, the fuzzy theory has been adopted broadly to the applications of image processing. Especially the fuzzy clustering algorithm is adopted to image segmentation to reduce the ambiguity and the influence of noise in an image.But this needs lots of memory and execution time because of the great deal of image data. Therefore a new image segmentation algorithm is needed which reduces the memory and execution time, doesn't change the characteristices of the image, and simultaneously has the same result of image segmentation as the conventional fuzzy clustering algorithm. In this paper, for image segmentation, an extended fuzzy clustering algorithm is proposed which uses the occurence of data of the same characteristic value as the weight of the characteristic value instead of using the characteristic value directly in an image and it is proved the memory reduction and execution time reducted in comparision with the conventional fuzzy clustering algorithm in image segmentation.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.103-111
• /
• 2020

Liver cancer is the most fatal cancer that occurs worldwide. In order to diagnose liver cancer, the patient's physical condition was checked by using a CT technique using radiation. Segmentation was needed to diagnose the liver on the patient's abdominal CT scan, which the radiologists had to do manually, which caused tremendous time and human mistakes. In order to automate, researchers attempted segmentation using image segmentation algorithms in computer vision field, but it was still time-consuming because of the interactive based and the setting value. To reduce time and to get more accurate segmentation, researchers have begun to attempt to segment the liver in CT images using CNNs, which show significant performance in various computer vision fields. The pixel value, or numerical value, of the CT image is called the Hounsfield Unit (HU) value, which is a relative representation of the transmittance of radiation, and usually ranges from about -2000 to 2000. In general, deep learning researchers reduce or limit this range and use it for training to remove noise and focus on the target organ. Here, we observed that the range of HU values was limited in many studies but different in various liver segmentation studies, and assumed that performance could vary depending on the HU range. In this paper, we propose the possibility of considering HU value range as a hyper parameter. U-Net and ResUNet were used to compare and experiment with different HU range limit preprocessing of CHAOS dataset under limited conditions. As a result, it was confirmed that the results are different depending on the HU range. This proves that the range limiting the HU value itself can be a hyper parameter, which means that there are HU ranges that can provide optimal performance for various models.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.61-70
• /
• 2023

Image segmentation is a very crucial step in effective digital image processing. In the past decade, several research contributions were given related to this field. However, a general segmentation algorithm suitable for various applications is still challenging. Among several image segmentation approaches, graph-based approach has gained popularity due to its basic ability which reflects global image properties. This paper proposes a methodology to partition the image with its pixel, region and texture along with its intensity. To make segmentation faster in large images, it is processed in parallel among several CPUs. A way to achieve this is to split images into tiles that are independently processed. However, regions overlapping the tile border are split or lost when the minimum size requirements of the segmentation algorithm are not met. Here the contributions are made to segment the image on the basis of its pixel using min-cut/max-flow algorithm along with edge-based segmentation of the image. To segment on the basis of the region using a homogenous optimum cut algorithm with boundary segmentation. On the basis of texture, the object type using spectral partitioning technique is identified which also minimizes the graph cut value.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.812-819
• /
• 2016

This paper introduces and analyzes the theoretical basis and method of the conventional initial-value assignment problem and feasibility of image segmentation. The paper presents topological evidence and a method of appropriate initial-value assignment based on topology theory. Subsequently, the paper shows minimum conditions for feasibility of image segmentation based on separation axiom theory of topology and a validation method of effectiveness for image modeling. As a summary, this paper shows image segmentation with its mathematical validity based on topological analysis rather than statistical analysis. Finally, the paper applies the theory and methods to conventional Gaussian random field model and examines effectiveness of GRF modeling.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.303-317
• /
• 2006

The process of segmenting customers in CRM should take into equal consideration both the companies' and customers' expected value. However, most of the current studies on customer segmentation have focused only on the companies view in terms of profitability. This study focuses on clarifying a problem and proposing a modified view in the customer segmentation step. The authors offer a proposition which is beneficial to both customers and companies, and thus makes the segmentation step more balanced. There is a two-pronged focus on customer segmentation in this study: first, this paper proposes a balanced view considering not only companies' expected value, but also that of the customers'. Secondly, such balanced segmentation will give a more accurate definition of loyal customers for a given company. This new approach can be expected to improve the level of satisfaction and the length of customer retention, and to increase effectiveness in corporate resource allocation for customer target marketing, as well as improve company insight into customer needs and preferences.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.450-453
• /
• 2000

In this paper, an automated segmentation algorithm is proposed for MR brain images using T1-weighted, T2-weighted, and PD images complementarily. The proposed segmentation algorithm is composed of 3 steps. In the first step, cerebrum images are extracted by putting a cerebrum mask upon the three input images. In the second step, outstanding clusters that represent inner tissues of the cerebrum are chosen among 3-dimensional (3D) clusters. 3D clusters are determined by intersecting densely distributed parts of 2D histogram in the 3D space formed with three optimal scale images. Optimal scale image best describes the shape of densely distributed parts of pixels in 2D histogram. In the final step, cerebrum images are segmented using FCM algorithm with it’s initial centroid value as the outstanding cluster’s centroid value. The proposed segmentation algorithm complements the defect of FCM algorithm, being influenced upon initial centroid, by calculating cluster’s centroid accurately And also can get better segmentation results from the proposed segmentation algorithm with multi spectral analysis than the results of single spectral analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06a
• /
• pp.175-180
• /
• 1996

In this paper, a new image segmentation method based on merging of two low contrast neighbor regions iteratively is proposed. It is suitable for very low bit rate coding. The proposed method reduces efficiently contour information and preserves subjective and objective image quality. It consists of image segmentation using 4-level hierarchical structure based on mathematical morphology and 1-level region merging structure using the contrast difference of two adjacent neighbor regions. For each segmented region of the third level, two adjacent neighbor regions having low contrast difference value in fourth level based on contrast difference value is merged iteratively. It preserves image quality and shows the noticeable reduction of the contour information, so that it can improve the bottleneck problem of segmentation-based coding at very low bit rate.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.4
• /
• pp.169-176
• /
• 2018

In this study, we propose a new Fire Flame Region Extraction using Block Homogeneity Segmentation method of the Fire Image with irregular texture and various colors. It is generally assumed that fire flame extraction plays a very important role. The Color Image with fire flame is divided into blocks and edge strength for each block is computed by using modified color histogram intersection method that has been developed to differentiate object boundaries from irregular texture boundaries effectively. The block homogeneity is designed to have the higher value in the center of region with the homeogenous colors or texture while to have lower value near region boundaries. The image represented by the block homogeneity is gray scale image and watershed transformation technique is used to generate closed boundary for each region. As the watershed transform generally results in over-segmentation, region merging based on common boundary strength is followed. The proposed method can be applied quickly and effectively to the initial response of fire.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2113-2128
• /
• 2019

Image thresholding techniques introducing spatial information are widely used image segmentation. Some methods are used to calculate the optimal threshold by building a specific histogram with different parameters, such as gray value of pixel, average gray value and gradient-magnitude, etc. However, these methods still have some limitations. In this paper, an entropic thresholding method based on Gabor histogram (a new 2D histogram constructed by using Gabor filter) is applied to image segmentation, which can distinguish foreground/background, edge and noise of image effectively. Comparing with some methods, including 2D-KSW, GLSC-KSW, 2D-D-KSW and GLGM-KSW, the proposed method, tested on 10 realistic images for segmentation, presents a higher effectiveness and robustness.