• 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.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.59-62
• /
• 2002

Watershed Segmentation with Multiple Merging Conditions in Region Growing Process The watershed segmentation method holds the merits of edge-based and region-based methods together, but still shows some problems such as over segmentation and merging fault. We propose an algorithm which overcomes the problems of the watershed method and shows efficient performance for .general images, not for specific ones. The algorithm segments or merges regions by thresholding the depths of the catchment basins, the similarities and the sizes of the regions. The experimental results shows the reduction of the number of the segmented regions that are suitable to human visual system and consciousness.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1972-1975
• /
• 2003

Video segmentation is an essential part in region-based video coding and any other fields of the video processing. Among lots of methods proposed so far, the watershed method in which the region growing is performed for the gradient image can produce well-partitioned regions globally without any influence on local noise and extracts accurate boundaries. But, it generates a great number of small regions, which we call over segmentation problem. Therefore we proposes image segmentation improvement by selective application structuring element of mathematical morphology.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.107-109
• /
• 2004

High-resolution remotely sensed data such as SPOT-5 imagery are employed to study the effectiveness of the watershed segmentation algorithm. Existing problems in this approach are identified and appropriate solutions are proposed. As a case study, the panchromatic SPOT-5 image of part of Beijing urban areas has been segmented by using the MATLAB software. In segmentation, the structuring element has been firstly created, then the gaps between objects have been exaggerated and the objects of interest are converted. After that, the intensity valleys have been detected and the watershed segmentation have been conducted. Through this process, the objects in an image are divided into separate objects. Finally, the effectiveness of the watershed segmentation approach for high-resolution imagery has been summarized. The approach to solve the problems such as over-segmentation has been proposed.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.670-675
• /
• 2001

This paper is to propose image segmentation method based on chamfer algorithm. First, we get original image from CCD camera and transform it into gray image. Second, we extract maximum gray value of background and reconstruct and eliminate the background using surface fitting method and bilinear interpolation. Third, we subtract the reconstructed background from gray image to remove noises in gray image. Fourth, we transform the subtracted image into binary image using Otsu's optimal thresholding method. Fifth, we use morphological filters such as areaopen, opening, filling filter etc. to remove noises and isolated points. Sixth, we use chamfer distance or Euclidean distance to this filtered image. Finally, we use watershed algorithm and count microorganisms in image by labeling. To prove the effectiveness, we apply the proposed algorithm to one of Ammonia-oxidizing bacteria, Acinetobacter sp. It is shown that both Euclidean algorithm and chamfer algorithm show over-segmentation. But Chamfer algorithm shows less over-segmentation than Euclidean algorithm.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.159-166
• /
• 2021

In order to analyze cell images, accurate segmentation of each cell is indispensable. However, the reality is that accurate cell image segmentation is not easy due to various noises, dense cells, and inconsistent shape of cells. Therefore, in this paper, we propose an algorithm that combines marker-based watershed segmentation and ellipse fitting method for glioblastoma cell segmentation. In the proposed algorithm, in order to solve the over-segmentation problem of the existing watershed method, the marker-based watershed technique is primarily performed through "seeding using local minima". In addition, as a second process, the concave point search using ellipse fitting for final segmentation based on the connection line between the concave points has been performed. To evaluate the performance of the proposed algorithm, we compared three algorithms with other algorithms along with the calculation of segmentation accuracy, and we applied the algorithm to other cell image data to check the generalization and propose a solution.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.187-196
• /
• 2000

A lot of Internet shopping malls strive for obtaining a competitive advantage over others in an increasingly tighter electronic marketplace. To this end, understanding customer preference toward products (or services) and administering appropriate marketing strategy is essential for their continuous survival. However, only a few marketing researchers and practicioners focused on this issue, compared with academic and industry efforts devoted to traditional market segmentation. In this paper, we suggest a methodology of conjoint segmentation for electronic shopping malls. Traditional market segmentation methodologies based on customer's profile sometimes fail to utilize abundant information given while navigating around cyber shopping malls. In this methodology, we do not impose information overload to the customer for preference elicitation, but this methodology, we do not impose information overload to the customer for preference elicitation, but capture automatically generated surfing or buying data and analyze them to get useful market segmentation information. The methodology consists of 4-stages: 1) analyzing legacy homepages, 2) data preparation, 3) estimating and interpreting the result, and 4) developing marketing mix. Our methodology was to give useful guidelines for market segmentation to companies working in the electronic marketplace.