• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.321-326
• /
• 2019

As AI technology is recently introduced into various fields, it is being applied to the fashion field. This paper proposes a system for recommending cody clothes suitable for a user's selected clothes. The proposed system consists of user app, cody recommendation module, and server interworking of each module and managing database data. Cody recommendation system classifies clothing images into 80 categories composed of feature combinations, selects multiple representative reference images for each category, and selects 3 full body cordy images for each representative reference image. Cody images of the representative reference image were determined by analyzing the user's preference using Google survey app. The proposed algorithm classifies categories the clothing image selected by the user into a category, recognizes the most similar image among the classification category reference images, and transmits the linked cody images to the user's app. The proposed system uses the ResNet-50 model to categorize the input image and measures similarity using ORB and HOG features to select a reference image in the category. We test the proposed algorithm in the Android app, and the result shows that the recommended system runs well.

• 한국인터넷방송통신학회논문지
• /
• 제11권3호
• /
• pp.175-179
• /
• 2011

본 논문에서는 모바일 환경에서의 음성인식 개선에 관한 내용으로 기존의 HMM에서 특징보상기법을을 적용한 방식으로 예측잡음이 아닌 실제 오염된 데이터를 적용하여 인식모델을 잡음상황에 맞도록 적응시키는 모델적응 HMM을 사용하였다. 음성인식 시 기존의 방법에서는 주변노이즈를 고려하지 않은 참조패턴을 사용하였으나 본 연구에서는 주변노이즈를 고려한 참조패턴을 생성하여 인식률을 향상 시키는 방법으로 모바일 환경에서의 음성 인식률을 향상 시켰다.

• 대한산업공학회지
• /
• 제21권1호
• /
• pp.51-65
• /
• 1995

This paper presents an automatic fixture planning system for machining processes of prismatic parts. A rationalized approach to integrate fixture planning with process planning is proposed and representation schemes for workpiece, part design information with features, machine tools, cutting tools and fixtures are developed. The proposed system implements two activities of fixture planning such as machining of reference surfaces and machining of features. For machining of reference surfaces, the machining sequence of reference surfaces is determined by using decision tables, which are drawn from relations of part dimension, degree of surface roughness, fixture type and its capacity, cutting tool's capacity and experienced planners' knowledge. For machining of features, a preferential machining orientation is selected for its feature which can be machined in more than one direction, and features with the same machining orientation are grouped, and the machining sequence of features is determined by interactive mode. A case study is performed to show the performance of the proposed system.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 춘계학술대회논문집
• /
• pp.1074-1079
• /
• 2007

We will introduce speech/speaker recognition algorithm for the isolated word. In general case of speaker verification, Gaussian Mixture Model (GMM) is used to model the feature vectors of reference speech signals. On the other hand, Dynamic Time Warping (DTW) based template matching technique was proposed for the isolated word recognition in several years ago. We combine these two different concepts in a single method and then implement in a real time speaker/speech recognition system. Using our proposed method, it is guaranteed that a small number of reference speeches (5 or 6 times training) are enough to make reference model to satisfy 90% of recognition performance.

• 대한전기학회논문지
• /
• 제38권2호
• /
• pp.83-92
• /
• 1989

This paper presents a load frequency control by optimal linear tracking, which can be well adapted to practical power systems with successive load disturbances. Conventional Load Frequency Controls (LEC's) have a feedback control scheme of the state error deviated from the post-disturbance steady state. This requires the modification of reference everytime the system encounters load changes. In this study, a new feedback scheme of LEC is developed by using the optimal linear tracking method with a fixed reference. As a result, the proposed LFC, which requires no reference modification, can be efficiently applied to power systems with successive disturbances such as load changes due to the on-off operations of reclosers or feeder switches. Another feature of the proposed LFC is that it adopts an algorithm to calculate an optimal post-fault steady state with the consideration of control input changes. The proposed LFC has been tested for a 2-area power system, which shows that it can be well adapted to successive load disturbances with good frequency response.

• 대한음성학회지:말소리
• /
• 제61호
• /
• pp.87-100
• /
• 2007

A punctuation generation system which combines prosodic information with acoustic and language model information is presented. Experiments have been conducted first for the reference text transcriptions. In these experiments, prosodic information was shown to be more useful than language model information. When these information sources are combined, an F-measure of up to 0.7830 was obtained for adding punctuation to a reference transcription. This method of punctuation generation can also be applied to the 1-best output of a speech recogniser. The 1-best output is first time aligned. Based on the time alignment information, prosodic features are generated. As in the approach applied in the punctuation generation for reference transcriptions, the best sequence of punctuation marks for this 1-best output is found using the prosodic feature model and an language model trained on texts which contain punctuation marks.

• 한국통신학회논문지
• /
• 제14권6호
• /
• pp.611-620
• /
• 1989

본 논문에서, PC를 이용하여 개인을 확인할 수 있는 지문정합에 관한 방법을 논하였다. 지문정합법에서 첫째, 지문영상을 세션화하고 단점과 분기점의 위치와 방향으로 구성된 특징점을 추출한다. 지문식별은 추출된 데이터를 이용하여 참조지문과 입력지문의 일치 또는 불일치 판정으로 수행된다. 평활화와 2진화처리, 세션처리후에 세션영상은 정확한 특징량의 추출을 위해 복원처리를 행한다. 정합시에 참조지문과 입력지문사이의 단점과 분기점 위치를 평행이동과 회전이동에 의하여 보상하여 지문확인을 수행한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.220-225
• /
• 2020

This paper investigates the non-intrusive speech intelligibility estimation method in noise environments when the bottleneck feature of autoencoder is used as an input to a neural network. The bottleneck feature-based method has the problem of severe performance degradation when the noise environment is changed. In order to overcome this problem, we propose a novel non-intrusive speech intelligibility estimation method that adds the noise environment information along with bottleneck feature to the input of long short-term memory (LSTM) neural network whose output is a short-time objective intelligence (STOI) score that is a standard tool for measuring intrusive speech intelligibility with reference speech signals. From the experiments in various noise environments, the proposed method showed improved performance when the noise environment is same. In particular, the performance was significant improved compared to that of the conventional methods in different environments. Therefore, we can conclude that the method proposed in this paper can be successfully used for estimating non-intrusive speech intelligibility in various noise environments.

• 한국통신학회논문지
• /
• 제24권6B호
• /
• pp.1191-1202
• /
• 1999

본 논문에서는 간단히 한국통신학회본 논문에서는 웨이브렛 영역에서의 질감 유사성을 특징으로 사용함으로써 프레임간의 급격한 밝기변화에 강건한 특성을 가지는 툴게이트 과금을 위한 차량검지 및 차종분류 알고리듬을 제안하였다. 질감의 유사성을 나타내는 특징으로는 웨이브렛 변환된 입력영상과 배경영상 간의 국부상관계수를 이용하였다. 기존의 차량검지에서 사용되었던 특징인 차영상에 대한 분산과 비교하여 제안된 특징의 유용성을 정상적으로 분석하였으며, 실제 테스트 영상에 대하여 차량과 그림자가 관측되거나 관측되지 않는 도로와의 구분 용이성 정도를 측정함으로써 제안된 특징의 우수성을 보인다. 현장 테스트에 대한 실험 결과는 제안된 차량검지 및 차종분류 알고리듬이 센서의 특성과 그림자의 발생에 의한 프레임 간의 급격한 밝기 변화와 같은 상황하에서도 매우 안정적이며 우수한 성능을 보이는 것을 확인할 수 있다.

• 한국광학회지
• /
• 제8권5호
• /
• pp.403-409
• /
• 1997

다양한 특징들을 광학적으로 병렬추출하여 패턴인식을 수행하는 시스템을 제안하고 실험하였다. 추출하려는 특징은 6개의 방향선소들 및 선소특징만으로 구별되지 않는 패턴들에 대한 공분산행렬의 고유벡터들이다. 이 시스템은 크게 특징추출부와 패턴인식부로 구성된다. 전자는 여러 특징을 병렬적으로 추출하기 위해 다중 Vander Lugt 필터를 사용하여 광학적으로 구현되었으며, 후자는 이들 추출된 특징들을 사용하여 패턴인식이 수행되도록 컴퓨터에서 구현되었다. 패턴인식 방법으로는, 추출된 특징을 인공신경망에 학습을 시키는 방법과 단순히 선소들의 논리적인 개수를 사용하는 방법, 두 가지가 각각 사용되었다. 여기서는 선소들로만 구성된 15개의 영문자 패턴들에 대해 실험하였고 그 실험결과를 보고한다.