• 전자공학회논문지B
• /
• 제30B권3호
• /
• pp.50-59
• /
• 1993

There is basic problem with the current evaluation method for character recognition systems. The current method evaluates the average recognition rate by applying the test data to the target system. The average recognition rate tells no more than and no less than the overall performance and it depends on the data. In this paper we propose a testing method which will analyze the target system and point out its strong points and weak points. This can be made possible through using the data which are generated cy distorting the standard character images according to a carefully controlled manner. This paper will describe how to automatically generate such distorted images. Also we will show the method is actually effective and useful by applying it to evaluating existing recognition algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2368-2372
• /
• 2005

We proposed a novel method for object recognition using the Smart tag system in the previous research. We identified the object easily, but could not assure the object pose, because the threshold problem was not solved. So we propose a new method to solve this threshold problem. This method uses a smart tag to decide the threshold by recording color information of the image when the object feature is extracted. This method records the original of the object color information at the smart tag first. And then it records the object image information, the circumstance image information and the sensors information continuously when the object feature is extracted through the experiments. Finally, it estimates the current threshold by recorded information. This method can be applied the threshold to each objects. And it can solve the difficult threshold decision problem easily. To approve the possibility of our method, we implemented our approach by using easy and simple techniques as possible.

• 제어로봇시스템학회논문지
• /
• 제17권2호
• /
• 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.

• 대한음성학회지:말소리
• /
• 제61호
• /
• pp.113-123
• /
• 2007

The environmental differences between training and testing mode are generally considered to be the critical factor for the performance degradation in speaker recognition systems. Especially, general speaker recognition systems try to get as clean speech as possible to train the speaker model, but it's not true in real testing phase due to environmental and channel noise. So in this paper, the new method of weighting the frame-based likelihood according to frame SNR is proposed in order to cope with that problem. That is to make use of the deep correlation between speech SNR and speaker discrimination rate. To verify the usefulness of this proposed method, it is applied to the context dependent speaker identification system. And the experimental results with the cellular phone speech DB which is designed by ETRI for Koran speaker recognition show that the proposed method is effective and increase the identification accuracy by 11% at maximum.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권9호
• /
• pp.884-891
• /
• 2008

RFID 시스템이 그 규모가 커짐에 따라 리더 충돌에 따른 인식률 저하 문제가 대두되고 있다. 시분할 기법을 사용하면 충돌문제를 해결할 수 있지만, 전체 인식시간은 늘어가게 된다. 이 문제는 RFID를 이용한 실시간 재고관리를 위해 해결해야만 한다. 본 연구에서는 ARCM(Anti Reader Collision Manager)을 RFID 시스템에 두어 전체 인식시간을 개선하였다. ARCM은 효율적인 주파수 채널 사용으로 짧은 인식시간을 가지며 리더가 간섭을 회피해 태그를 인식할 수 있도록 RFID 시스템을 관리한다. ARCM을 사용한 결과, 기존의 시스템보다 최대 20%정도의 시간을 절약할 수 있었다.

• 대한전기학회논문지
• /
• 제40권8호
• /
• pp.731-740
• /
• 1991

This paper presents a knowledge based system to solve reactive power/voltage control problem in a power system. The methods to reduce inference time are proposed in inferring the solution of problem in the knowledge base which consists of heuristic rules and inowledge of experts. A set of indices drawn from the heuristic knowledge on the power system is utilized to make up for the defect of existing knowledge based systems which determine both the location and the amount of reactive power compensation devices. The concept of set of indices developed in this paper makes it possible to infer the amount of reactive power source only since the bus order list representing priority for the location of reactive power compensator to be switched on can be determined in advance. From the fact that there exists a relationship between the system voltage pattern and the reactive power pattern in operation, the pattern recognition technique is introduced to reduce the inference time in solving the severe voltage problem. To demonstrate the usefulness of the proposed knowledge based system, the IEEE 30 bus system is chosen as a sample system. The results of case study are also presented.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.472-472
• /
• 1996

The material of database for speech recognition should include phonetic phenomena as much as possible. At the same time, such material should be phonetically compact with low redundancy[1, 2]. The phonetic phenomena in continuous speech is the key problem in speech recognition. This paper describes the processing of a set of sentences collected from the database of 1993 and 1994 "People's Daily"(Chinese newspaper) which consist of news, politics, economics, arts, sports etc.. In those sentences, both phonetic phenometla and sentence patterns are included. In continuous speech, phonemes always appear in the form of allophones which result in the co-articulary effects. The task of designing a speech database should be concerned with both intra-syllabic and inter-syllabic allophone structures. In our experiments, there are 404 syllables, 415 inter-syllabic diphones, 3050 merged inter-syllabic triphones and 2161 merged final-initial structures in read speech. Statistics on the database from "People's Daily" gives and evaluation to all of the possible phonetic structures. In this sentence set, we first consider the phonetic balances among syllables, inter-syllabic diphones, inter-syllabic triphones and semi-syllables with their junctures. The syllabic balances ensure the intra-syllabic phenomena such as phonemes, initial/final and consonant/vowel. the rest describes the inter-syllabic jucture. The 1560 sentences consist of 96% syllables without tones(the absent syllables are only used in spoken language), 100% inter-syllabic diphones, 67% inter-syllabic triphones(87% of which appears in Peoples' Daily). There are rougWy 17 kinds of sentence patterns which appear in our sentence set. By taking the transitions between syllables into account, the Chinese speech recognition systems have gotten significantly high recognition rates[3, 4]. The following figure shows the process of collecting sentences. [people's Daily Database] -> [segmentation of sentences] -> [segmentation of word group] -> [translate the text in to Pin Yin] -> [statistic phonetic phenomena & select useful paragraph] -> [modify the selected sentences by hand] -> [phonetic compact sentence set]

• 로봇학회논문지
• /
• 제15권2호
• /
• pp.115-123
• /
• 2020

Farmers using conventional sprayer system are exposed to pesticide poisoning and soil pollution due to pesticide application. In order to reduce this problem, the effective sprayer system is required. In this paper, we propose development of intelligent sprayer system using tree recognition. This intelligent sprayer system consists of an image recognition module, a remote control, a sprayer system, an air blower, and a control module. It is possible to spray pesticides automatically and manually through remote control using cameras and controls. We conducted a total of four experiments in tree recognition experiment, test of attachment and water sensitive papers, measurement of pesticide consumption, and measurement of worker exposure. The test results showed that the consumption of pesticides could be reduced while giving the same effect as conventional controls.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.166-176
• /
• 2023

A scenario known as conflict in face recognition may arise as a result of some disparity-related issues (such as expression, distortion, occlusion and others) leading to a compromise of someone's identity or contradiction of the intended message. However, addressing this requires the determination and application of appropriate procedures among the various conflict theories both in terms of concepts as well as resolution strategies. Theories such as Marxist, Game theory (Prisoner's dilemma, Penny matching, Chicken problem), Lanchester theory and Information theory were analyzed in relation to facial images conflict and these were made possible by trying to provide answers to selected questions as far as resolving facial conflict is concerned. It has been observed that the scenarios presented in the Marxist theory agree with the form of resolution expected in the analysis of conflict and its related issues as they relate to face recognition. The study observed that the issue of conflict in facial images can better be analyzed using the concept introduced by the Marxist theory in relation to the Information theory. This is as a result of its resolution strategy which tends to seek a form of balance as result as opposed to the win or lose case scenarios applied in other concepts. This was also consolidated by making reference to the main mechanisms and result scenario applicable in Information theory.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.9-11
• /
• 2021

현재 우리나라는 층간소음 발생 추이가 점차 증가하고 있으며, 이로 인한 2차 갈등의 문제가 증가하고 있다. 이러한 문제점을 해결하기 위해 다양한 연구들이 진행되어 왔으나 층간소음 실험에 대한 정의가 명확하지 않고, 다양한 상황에서의 층간소음 데이터를 획득할 수 없다. 따라서 이 논문에서는 층간소음 진원지 인지 시스템을 위한 다양한 층간소음 실험 시나리오를 정의한다. 이를 위해 실험에 필요한 환경과 실생활에서 발생하는 층간소음 유형 및 수집기의 위치, 소음 강도를 고려하여 실험 시나리오를 정의한다. 정의한 실험 시나리오 기반으로 데이터 수집 및 학습 연산을 수행할 경우, 층간소음 인지 시스템의 정확도를 높일 수 있다.