• Journal of Institute of Control, Robotics and Systems
• /
• v.1 no.2
• /
• pp.105-111
• /
• 1995

This paper proposes a segmentation algorithm using gray-level discontinuity and surface reflectance ratio of input images obtained under different illumination conditions. Each image is divided by a certain number of subregions based on the thresholds. The thresholds are determined using the histogram of fusion image which is obtained by ANDing the multiple input images. The subregions of images are projected on the eigenspace where their bases are the major eigenvectors of image matrix. Points in the eigenspace are classified into two clusters. Images associated with the bigger cluster are fused by revised ANDing to form a combined edge image. Missing edges are detected using surface reflectance ration and chain code. The proposed algorithm obtains more accurate edge information and allows to more efficiently recognize the environment under various illumination conditions.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.8
• /
• pp.1074-1084
• /
• 1995

In this paper, we investigate edge extraction and segmentation of range images. We first discuss problems that arise in the conventional region-based segmentation methods and edge-based ones using principal curvatures, then we propose an edge-based algorithm. In the proposed algorithm, we extract edge contours by using the Gaussian filter and directional derivatives, and segment a range image based on extracted edge contours, Also we present the problem that arises in the conventional thresholding, then we propose a new threshold selection method. To solve the problem that local maxima of the first- and second- order derivatives gather near step edges, we first find closed roof edge contours, fill the step edge region, and finally thin edge boundaries. Computer simulations with several range images show that the proposed method yields better performance than the conventional one.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.12-18
• /
• 2020

In semiconductor manufacturing, defect detection is critical to maintain high yield. Currently, computer vision systems used in semiconductor photo lithography still have adopt to digital image processing algorithm, which often occur inspection faults due to sensitivity to external environment. Thus, we intend to handle this problem by means of using Mask R-CNN instead of digital image processing algorithm. Additionally, Mask R-CNN can be trained with image dataset pre-processed by means of the specific designed digital image filter to extract the enhanced feature map of Convolutional Neural Network (CNN). Our approach converged advantage of digital image processing and instance segmentation with deep learning yields more efficient semiconductor photo lithography inspection system than conventional system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.120-129
• /
• 1996

This paper presents an efficient block segmentation and classification using the edge information of the document image. We extract four prominent features form the edge gradient and orientaton, all of which, and thereby the block clssifications, are insensitive to the background noise and the brightness variation of of the image. Using these four features, we can efficiently classify a document image into the seven categrories of blocks of small-size letters, large-size letters, tables, equations, flow-charts, graphs, and photographs, the first five of which are text blocks which are character-recognizable, and the last two are non-character blocks. By introducing the clumn interval and text line intervals of the document in the determination of th erun length of CRLA (constrained run length algorithm), we can obtain an efficient block segmentation with reduced memory size. The simulation results show that the proposed algorithm can rigidly segment and classify the blocks of the documents into the above mentioned seven categories and classification performance is high enough for all the categories except for the graphs with too much variations.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.3
• /
• pp.1-6
• /
• 2019

Foreground/background segmentation in video sequences is often one of the first tasks in machine vision applications, making it a critical part of the system. In this paper, we present an improved sample-based technique that provides robust background image as well as segmentation mask. The conventional multiple interval sampling (MIS) algorithm have suffer from the unbalance of computation time per frame and the rapid change of confidence factor of background pixel. To balance the computation amount, a random-based pixel update scheme is proposed and a spatial and temporal smoothing technique is adopted to increase reliability of the confidence factor. The proposed method allows the sampling queue to have more dispersed data in time and space, and provides more continuous and reliable confidence factor. Experimental results revealed that our method works well to estimate stable background image and the foreground mask.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2838-2844
• /
• 1999

The motion-based video segmentation provides a powerful method of video compression, because it defines a region with similar motion, and it makes video compression system to more efficiently describe motion video. In this paper, we propose the Modified Fuzzy Competitive Learning Algorithm (MFCLA) to improve the traditional K-menas clustering algorithm to implement the motion-based video segmentation efficiently. The segmented region is described with the affine model, which consists of only six parameters. This affine model was calculated with optical flow, describing the movements of pixels by frames. This method could be applied in the low bit rate video transmission, such as video conferencing system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.345-346
• /
• 2009

The segmentation of vessel including portal vein, hepatic vein and artery, from Computed Tomography (CT) images plays an important role in the therapeutic strategies for hepatic diseases. Representing segmented vessels in three dimensional spaces is extremely useful for doctors to plan liver surgery. In this paper, proposed method is focused on smoothing technique of segmented 3D liver vessels, which derived from 3D region growing approach. A pixel expand algorithm has been developed first to avoid vessel lose and disconnection cased by the next smoothing technique. And then a binary volume filtering technique has been implemented and applied to make the segmented binary vessel volume qualitatively smoother. This strategy uses an iterative relaxation process to extract isosurfaces from binary volumes while retaining anatomical structure and important features in the volume. Hard and irregular place in volume image has been eliminated as shown in the result part, which also demonstrated that proposed method is a suitable smoothing solution for post processing of fine vessel segmentation.

• Journal of Biosystems Engineering
• /
• v.43 no.2
• /
• pp.103-109
• /
• 2018

Purpose: This study has been conducted to develop a potato yield monitoring system, consisting of a segmentation algorithm to detect potatoes scattered on a soil surface and a counting system to count the number of potatoes and convert the data from two-dimensional images to masses. Methods: First, a segmentation algorithm was developed using top-hat filtering and processing a series of images, and its performance was evaluated in a stationary condition. Second, a counting system was developed to count the number of potatoes in a moving condition and calculate the mass of each using a mass estimation equation, where the volume of a potato was obtained from its two-dimensional image, and the potato density and a correction factor were obtained experimentally. Experiments were conducted to segment potatoes on a soil surface for different potato sizes. The counting system was tested 10 times for 20 randomly selected potatoes in a simulated field condition. Furthermore, the estimated total mass of the potatoes was compared with their actual mass. Results: For a $640{\times}480$ image size, it took 0.04 s for the segmentation algorithm to process one frame. The root mean squared deviation (RMSD) and average percentage error for the measured mass of potatoes using this counting system were 12.65 g and 7.13%, respectively, when the camera was stationary. The system performance while moving was the best in L1 (0.313 m/s), where the RMSD and percentage error were 6.92 g and 7.79%, respectively. For 20 newly prepared potatoes and 10 replication measurements, the counting system exhibited a percentage error in the mass estimation ranging from 10.17-13.24%. Conclusions: At a travel speed of 0.313 m/s, the average percentage error and standard deviation of the mass measurement using the counting system were 12.03% and 1.04%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.21-29
• /
• 2015

This paper proposes a shot change detection algorithm by using frame segmentation and the object changes among moving blocks. In order to detect the rapid moving changes of objects between two consecutive frames, the moving blocks on the diagonal are defined, and their histograms are calculated. When a block of the current frame is compared to the moving blocks of the next frame, the block histograms are used and the threshold of a shot change detection is automatically adjusted by Otsu's threshold method. The proposed algorithm was tested for the various types of color or gray videos such as films, dramas, animations, and video tapes in National Archives of Korea. The experimental results showed that the proposed algorithm could enhance the detection rate when compared to the studied methods that use brightness, histogram, or segmentation.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.670-673
• /
• 2002

This paper proposes a digital algorithm for gray-scale/color image segmentation of real-time video signals and a cell-network-based implementation architecture in state-of-the-art CMOS technology. Through extrapolation of design and simulation results we predict that about 300$\times$300 pixels can be integrated on a chip at 100nm CMOS technology, realizing very high-speed segmentation at about 1600sec per color image. Consequently real-time color-video segmentation will become possible in near future.