• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1255-1258
• /
• 1998

Hidden Markov Model (HMM) is the most widely used method in speech recognition. In general, HMM parameters are trained to have maximum likelihood (ML) for training data. This method doesn't take account of discrimination to other words. To complement this problem, this paper proposes a word verification method by re-recognition of the recognized word and its similar word using the discriminative function between two words. The similar word is selected by calculating the probability of other words to each HMM. The recognizer haveing discrimination to each word is realized using the weighting to each state and the weighting is calculated by genetic algorithm.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.517-521
• /
• 2008

Hand motion classification problem is considered as basis for sign or gesture recognition. We promote optical flow as main feature extracted from images sequences to simultaneously segment the motion's area by its magnitude and characterize the motion' s directions by its orientation. We manage the flow orientation histogram as motion descriptor. A motion is encoded by concatenating the flow orientation histogram from several frames. We utilize simple histogram matching to classify the motion sequences. Attempted experiments show the feasibility of our method for hand motion localization and classification.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1135-1139
• /
• 1989

Three layered neural network was applied for the pattern recognition problem of human spermatozoa in clinical test. The goodness of recognition rate was studied in relation to the number of hidden layer cells and of output layer cells. The proposed method provided better results than conventional template matching technique. Parallel processing of the back propagation learning algorithm was also studied using transputers and its performance was evaluated.

• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.1-7
• /
• 2014

Gesture recognition provides the ease and immediacy to users in the processing technique for recognizing the gesture. Because of these benefits, gesture recognition technology has been applied and fused in many areas, such as the military, health care, education. In particular, the gesture recognition in game field since it can provide users to play games similar to the actual gesture, it being fused with many areas such as medical, military, and education. This paper is to discuss the future convergence direction of motion recognition games based on this background. In this paper, it looks at technology status and the game of gesture recognition, describe the problem and improvement of gesture recognition game. This paper can help improving the competitiveness of domestic convergence on gesture recognition game.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.10
• /
• pp.1601-1610
• /
• 2009

Unplanned purchase is an unexpected buying behavior affected by product or marketing stimuli. Unplanned purchase does not follow the order of the rational decision making process. Through an in-depth interview, this study classified the types of unplanned purchase of clothing and examined the decision-making processes. The results (according to the need recognition level of consumers prior to stimuli) show three types of unplanned purchase of clothing products that are classified as: the need-manifesting type, the need-embodying type, and the need-reminding type. In addition, each type is reclassified into the high-cognition type and the low-cognition type according to the cognitive effort level of consumers during the purchase decision-making process. The need-manifesting type recognized a buying need after exposure to stimuli and then engaged in unplanned purchases. The need-embodying type recognized a problem, but the purchase intention was not concrete. The need-reminding type recognized a desire to buy clothing products, but temporarily forgot it, and then later remembered the problem recognition from the past after experiencing the stimuli.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.2
• /
• pp.93-101
• /
• 2011

For mobile robot, recognizing its current location is very important to navigate autonomously. Especially, loop closing detection that robot recognize location where it has visited before is a kernel problem to solve localization. A considerable amount of research has been conducted on loop closing detection and localization based on appearance because vision sensor has an advantage in terms of costs and various approaching methods to solve this problem. In case of scenes that consist of repeated structures like in corridors, perceptual aliasing in which, the two different locations are recognized as the same, occurs frequently. In this paper, we propose an improved method to recognize location in the scenes which have similar structures. We extracted salient regions from images using visual attention model and calculated weights using distinctive features in the salient region. It makes possible to emphasize unique features in the scene to classify similar-looking locations. In the results of corridor recognition experiments, proposed method showed improved recognition performance. It shows 78.2% in the accuracy of single floor corridor recognition and 71.5% for multi floor corridors recognition.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.999-1004
• /
• 1989

This paper discusses a new method of recognizing patterns employing consistent labeling. A consistent labeling problem is a generalized expression of constraint satisfaction problems. When a pattern is recognized by pattern matching, the matching between a reference pattern and an acquired pattern resolves itself into finding correspondence between the pixels on the former and those on the latter. This can be expressed as a consistent labeling problem. Pattern association, a variation of pattern recognition, is also described employing consistent labeling. The proposed technique is supported by experimental results, yet further studies need to be done before its practical use.

• Education of Primary School Mathematics
• /
• v.4 no.2
• /
• pp.151-163
• /
• 2000

This research is the object to investigate these thing; how do teachers undertaking at the spot classrooms to recognize performance assessment and how do they decide to question and how go the present practiced state and what is the problem points in the present performance assessment. Additonal things of problem point like a research object are following; Lets look over recognition, actual situations and various problems for mathematics performance assessment of elementary school teachers. Concerning question papers, the problem largely lie in 4 regions, that is to say the recognition of performance assessment, the current state of affairs in practice, deciding questions and problems of putting theory into practices, of the 480 teachers-the object of our studies-about 380 returned our questionaire. However, as there were too many in the age range 30 to 40 are excluded 80, choosing 300 to us as data in our analysis.