• Journal of Korea Multimedia Society
• /
• 제6권6호
• /
• pp.968-976
• /
• 2003

In this paper, we propose a novel method for lip recognition. Lip model is built based on the concatenated gray level distribution model, and the recognition problem is simplified as the minimization problem of matching object function. The Down Hill Simplex Algorithm is used for the minimization with the proposed novel method for setting initial condition, which can refrain Iteration from converging to local minima. The proposed algorithm shows extracting lip shape from the test image where Active Shape Model fails.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제10권4호
• /
• pp.310-314
• /
• 2000

This paper proposes a new parallel architecture for extracting the object from binarized images using recurrent linear threshold neural networks. Binary functions are initially obtained from the existing iterative thinning algorithms, and the linear threshold neural threshold neural networks are then synthesized using the MSP term grouping algorithm. Experimental results show that the proposed architectures can be implemented easier than with other existing methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송공학회 1998년도 Proceedings of International Workshop on Advanced Image Technology
• /
• pp.171-176
• /
• 1998

This paper resents a spatio-temporal video segmentation method. The algorithm segments each frame of video sequences captured by a static or moving camera into moving objects (foreground) and background using a statistical hypothesis test. In the proposed method, three consecutive image frames are exploited and a hypothesis testing is performed by comparing two means from two consecutive difference images, which results in a T-test. This hypothesis test yields change detection mask that indicates moving areas (foreground) and non-moving areas (background). Moreover, an effective method for extracting object mask form change detection mask is proposed.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2515-2517
• /
• 2002

The process of character recognition goes through 5 steps; image acquisition, character region extraction, preprocessing, character region segmentation, character recognition. Therefore the final recognition rate of character recognition is directly affected by the performance of each step. This paper is a leading research for object recognition using image processing algorithm which is one of the field of study in computer vision. And this paper will suggest an algorithm to extract the portion of number chain, which is part of the research embodying a system to perceive the data of manufacture and the name of the producer on the wrapping of groceries. In addition, this can extract the number chain comparatively accurate without using many complex algorithm by diving and extracting the moving number region at the same time.

• Journal of Institute of Control, Robotics and Systems
• /
• 제16권1호
• /
• pp.33-39
• /
• 2010

The interaction of emotion is an important factor in Human-Robot Interaction(HRI). This requires a contextual appraisal of emotion extracting the emotional information according to the events happened from past to present. In this paper an emotion appraisal system based on the cognitive context is presented. Firstly, a conventional emotion appraisal model is simplified to model a contextual emotion appraisal which defines the types of emotion appraisal, the target of the emotion induced from analyzing emotional verbs, and the transition of emotions in the context. We employ a language based cognitive system and its sentential memory and object descriptor to define the type and target of emotion and to evaluate the emotion varying with the process of time with the a priori emotional evaluation of targets. In a experimentation, we simulate the proposed emotion appraisal system with a scenario and show the feasibility of the system to HRI.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1976-1979
• /
• 2002

A new and efficient layout object extraction technique is presented in this paper, which is to be used in technology migration or hard-U reuse. The technique models the original polygon layout represented by a set of edges as a set of connected or overlapped rectangles. The rectangle model provides easy and efficient recognition, extraction, resizing, and compaction of layout objects such as transistors, contacts, and wires. Experiments on several designs from simple standard cells to more complex designs using standard and/or custom cells demonstrate the effectiveness of our technique.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• 제9권1호
• /
• pp.74-80
• /
• 2010

The purpose of reverse engineering design using 3D measurement data is an accurate reconstruction of real body. In oder to accomplish this object, it is important that creating exact extracting edges should be studying out first of all. This study used edge-based method to find out edge point from the measuring point data. The characteristics are analysed using the mean curvature block method on the fitting NURBS curve and defined edges through block removal condition. The results showed that only using the NURBS curve of maximum curvature analysis to define correct edge of real geometry is limited, but this segmentation approach provides simplified necessary condition for edge classification, and an effectiveness to classify a straight line, curves and fillets etc.

• Journal of the Semiconductor & Display Technology
• /
• 제19권2호
• /
• pp.88-91
• /
• 2020

Image segmentation is the task of partitioning an image into multiple sets of pixels based on some characteristics. The objective is to simplify the image into a representation that is more meaningful and easier to analyze. In this paper, we apply deep-learning to pre-train the learning model, and implement an algorithm that performs image segmentation in real time by extracting frames for the stream input from the Android device. Based on the open source of DeepLab-v3+ implemented in Tensorflow, some convolution filters are modified to improve real-time operation on the Android platform.

• Journal of Ocean Engineering and Technology
• /
• 제20권3호
• /
• pp.15-23
• /
• 2006

On this study, realtime GPS technique and combination of GPS/GLONASS technique are used to extracting coastline. Th￡ object of coastline is Gwanganri beach located in Busan. The coastline is observed along the traces of coastline when high wave of scar by using digital map of 1:1,000 and at random time zone, coastline is surveyed along the boundary line that is contacting with sea water level. When the coastline of random time zone is converted by height of tide table, the coastline when high wave of scar and converted coastline are shown as coincident approximately.

• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.153-155
• /
• 2003

Laser scanning has become a viable technique for the collection of a large amount of accurate 3D point data densely distributed on the scanned object surface. The inherent 3D nature of the sub-randomly distributed point cloud provides abundant spatial information. To explore valuable spatial information from laser scanned data becomes an active research topic, for instance extracting digital elevation model, building models, and vegetation volumes. The sub-randomly distributed point cloud should be segmented and classified before the extraction of spatial information. This paper investigates some exist segmentation methods, and then proposes an octree-based split-and-merge segmentation method to divide lidar data into clusters belonging to 3D planes. Therefore, the classification of lidar data can be performed based on the derived attributes of extracted 3D planes. The test results of both ground and airborne lidar data show the potential of applying this method to extract spatial features from lidar data.