• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.9-17
• /
• 2009

License plate recognition is an active research area. but few comparative studies on license plate binarization have been conducted. Many related researchers have experienced similar trial and error for finding an effective binarization method. To reduce this trial and error, this study implemented some binarization methods and quantitatively compared the performance of the methods. The performance evaluation consists of a low level measure and a high level measure, so it can evaluate not only the quality of binarized image itself but also the usefulness of the result. The performance evaluation was separately performed with three groups of images so as to understand the properties of the binarization methods. Experimental results show that the quality of binarization is more dependent on the evenness of illumination than the intensity of illumination. The Otsu's method has acquired the most effective performance in the group of even illumination images and the Niblack's method with parameter correction has shown the best quality in the group of uneven illumination images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.815-818
• /
• 2015

AODV routing protocol, one of the most studied routing protocols for the Mobile Ad hoc Network (MANET), uses the number of hops as the metric to choose a path from a source node to a destination node. If the path is deteriorated, it will cause many problems to the communication. In order to improve the performance of the network, we propose AuM-AODV routing protocol that contains an auxiliary metric besides the number of hops. Nodes using AuM-AODV use control packets such as Route Request (RREQ), Route Reply (RREP), and HELLO to exchange information about network topology like AODV routing protocol. AuM-AODV routing protocol is implemented in NS-3 for performance evaluation. We use three performance metrics, that is to say, throughput, packet delivery ratio, and average end-to-end delay. According to numerical results, the new AuM-AODV routing protocol has better performance over three performance metrics than AODV routing protocol.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.1-6
• /
• 2014

Emotion recognition is defined as that machines automatically recognize human emotions. Because the human emotions is very subjective, it is impossible to measure objectively. Therefore, the goal of emotion recognition is to obtain a measure that is agreed by as many people as possible. Emotion recognition in a image is implemented as the method that matches human emotions to the various features of the image. In the paper, we propose an emotion recognition system using color features of clothing image based on the Kobayashi's image scale. The proposed system stores colors of image scale into a database. And extracted major colors from a input clothing image are compared with those in the database. The proposed system can obtain three emotions maximally. In order to evaluate the system performance 70 observers are tested. The test results shows that recognized emotions of the proposed system are very similar to the observers emotions.

• Clean Technology
• /
• v.17 no.2
• /
• pp.175-180
• /
• 2011

A novel multi-criteria decision making strategy is developed for the construction of industrial symbiosis network in eco-industrial park and the strategy is applied to the construction of acid/alkali wastewater neutralization network in Yeosu industrial complex. Acid (or alkali) wastewater is commonly generated in chemical industries, and it can be used as neutralizing agent for alkali (or acid) wastewater generated from another source. As a consequence, a large-scale industrial symbiosis network for wastewater neutralization can be constructed in petrochemical complexes where a large amount of acid/alkali wastewater is generated. In this study, substance flow model is constructed which describes the wastewater neutralization network and multi-criteria decision making strategy is applied to find a few candidate for industrial symbiosis network.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.9
• /
• pp.1112-1118
• /
• 2014

In this paper, we propose a local descriptor and a similarity measure that is robust to radiometic variations. The proposed local descriptor is made up Haar wavelet filter and it can contain frequency informations about the feature point and its surrounding pixels in fixed region, and it is able to describe feature point clearly under ununiform illumination condition. And a proposed similarity measure is combined with conventional entropy-based similarity and another similarities that is generated by local descriptor. It can reflect similarities between image regions accurately under radiometic illumination variations. We validate with experimental results on some images and we confirm that the proposed algorithm is more superior than conventional algorithms.

• Journal of the Microelectronics and Packaging Society
• /
• v.29 no.2
• /
• pp.121-127
• /
• 2022

Micro-LED is a light-emitting diode smaller than 100 ㎛ in size. It attracts much attention due to its superior performance, such as resolution, brightness, etc., and is considered for various applications like flexible display and VR/AR. Micro-LED display requires a mass transfer process to move micro-LED chips from a LED wafer to a target substrate. In this study, we proposed a vacuum chuck method as a mass transfer technique. The vacuum chuck was fabricated with MEMS technology and PDMS micro-mold process. The spin-coating approach using a dam structure successfully controlled the PDMS mold's thickness. The vacuum test using solder balls instead of micro-LED confirmed the vacuum chuck method as a mass transfer technique.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1215-1223
• /
• 2014

In multi-hop wireless networks, a message transmission path is set up on demand by a route discovery step, where a shortest path is used in general. The shortest path, however, normally uses the nodes near the center area, which causes a high traffic load in that area and reduces the message transmission reliability. We propose a stable routing protocol considering the remaining energy of nodes. Our protocol uses ETX as a link performance estimator and tries to avoid the nodes with smaller energy. By doing this, we can reduce the route failure probability and packet loss. We have evaluated the performance of the proposed protocol using QualNet and compared with AODV and MRFR protocols. The simulation result shows that our protocol has a similar performance as MRFR in terms of end-to-end message reception ratio, average message delay and delay jitter, but outperforms MRFR in terms of traffic load distribution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3502-3509
• /
• 2010

Streaming service in the wireless mobile network environment has been a very challenging issue due to the dynamic uncertain nature of the channels. Overhead such as congestion, latency, and jitter lead to the problem of performance degradation of an adaptive multi-streaming service. This paper proposes a AMSS (Adaptive Multi-level Streaming Service) mechanism to reduce the performance degradation due to overhead such as variable network bandwidth, mobility and limited resources of the wireless mobile network. The proposed AMSS optimizes streaming services by: 1) use of fuzzy similarity metric, 2) minimization of packet loss due to buffer overflow and resource waste, and 3) minimization of packet loss due to congestion and delay. The simulation result shows that the proposed method has better performance in congestion control and packet loss ratio than the other existing methods of TCP-based method, UDP-based method and VBM-based method. The proposed method showed improvement of 10% in congestion control ratio and 8% in packet loss ratio compared with VBM-based method which is one of the best method.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.407-414
• /
• 2002

In this paper, we present a method that automatically generates concatenate morpheme based language models to improve the performance of Korean large vocabulary continuous speech recognition. The focus was brought into improvement against recognition errors of monosyllable morphemes that occupy 54% of the training text corpus and more frequently mis-recognized. Knowledge-based method using POS patterns has disadvantages such as the difficulty in making rules and producing many low frequency concatenate morphemes. Proposed method automatically selects morpheme-pairs from training text data based on measures such as frequency, mutual information, and unigram log likelihood. Experiment was performed using 7M-morpheme text corpus and 20K-morpheme lexicon. The frequency measure with constraint on the number of morphemes used for concatenation produces the best result of reducing monosyllables from 54% to 30%, bigram perplexity from 117.9 to 97.3. and MER from 21.3% to 17.6%.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2786-2800
• /
• 1997

In this paper, we investigate how well the channel memory (statistical dependence in the occurrence of transmission errors) can be used in the evaluation of widely used error control schemes. For this we assume a special case named as the simplest Markovian block-error pattern with two states, in which each block is classified into two classes of whether the block transmission is in error or not. We apply the derived pattern to the performance evaluation of the practical link-level procedures, LAPB/D/M with multi-reject options, and investigate both throughput and user-perceived response time behaviors on the discrete-time domain to determine how much the performance of error recovery action is improved under burst error condition. Through numerical examples, we show that the simplest Markovian block-error pattern tends to be superior in throughput and delay characteristics to the random error case. Also, instead of mean alone, we propose a new measure of the response time specified as mean plus two standard deviations 50 as to consider user-perceived worst cases, and show that it results in much greater sensitivity to parameter variations than does mean alone.