• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1663-1669
• /
• 1995

This paper is a study on the recognition of Korean proverb using neural network and Markov model. The neural network uses, at the stage of training neurons, features such as the rate of zero crossing, short-term energy and PLP-Cepstrum, covering a time of 300ms long. Markov models were generated by the recognized phoneme strings. The recognition of words and proverbs using Markov models have been carried out. Experimental results show that phoneme and word recognition rates are 81. 2%, 94.0% respectively for Korean proverb recognition experiments.

• 한국멀티미디어학회논문지
• /
• 제14권10호
• /
• pp.1243-1251
• /
• 2011

본 논문에서는 차량의 헤드라이트 영상에 Scale Invariant Feature Transform(SIFT) 알고리즘을 적용하여 획득한 특징점을 이용하여 차량의 모델을 인식하는 차종 인식 방법을 제안한다. 보다 정확도 높은 차종 인식을 구현하기 위해서 특징점들의 분포로부터 동질성(homogeneity)을 계산하여 인식 정확성의 척도로 두었다. 제안한 방법의 성능을 평가하기 위해 국내 54종의 차량 영상으로부터 촬영된 400장의 실험 영상을 이용해 실험한 결과, 제안한 방법은 90%의 인식률과 16.45의 평균 동질성을 보였다.

• 반도체디스플레이기술학회지
• /
• 제12권1호
• /
• pp.1-7
• /
• 2013

Grey-level statistical models have been widely used in many applications for object location and identification. However, conventional models yield some problems in model refinement when training images are not properly aligned, and have difficulties for real-time recognition of arbitrarily rotated models. This paper presents improved grey-level statistical models that align training images using image or feature matching to overcome problems in model refinement of conventional models, and that enable real-time recognition of arbitrarily rotated objects using efficient hierarchical search methods. Edges or features extracted from a mean training image are used for accurate alignment of models in the search image. On the aligned position and orientation, fitness measure based on grey-level statistical models is computed for object recognition. It is demonstrated in various experiments in PCB inspection that proposed methods are superior to conventional methods in recognition accuracy and speed.

• 대한전자공학회논문지
• /
• 제27권12호
• /
• pp.1933-1939
• /
• 1990

In this paper, we proposed an algorithm which used backtracking method to get time information, and it be modelled DMS (Dynamic Multisection) by feature vectors and time information whic are represented to similiar feature in word patterns spoken during continuous time domain, for Korean Speech recognition by independent speaker using DMS. Each state of model is represented time sequence, and have time information and feature vector. Typical feature vector is determined as the feature vector of each state to minimize the distance between word patterns. DDD Area names are selected as recognition wcabulary and 12th LPC cepstrum coefficients are used as the feature parameter. State of model is made 8 multisection and is used 0.2 as weight for time information. Through the experiment result, recognition rate by DMS model is 94.8%, and it is shown that this is better than recognition rate (89.3%) by MSVQ(Multisection Vector Quantization) method.

• 한국산업정보학회논문지
• /
• 제13권4호
• /
• pp.56-63
• /
• 2008

얼굴 인식률 향상을 위해서는 전처리 단계에서의 영상 보정이 매우 중요하며, 특히 배경 잡음 제거는 얼굴 인식의 정확도에 중대한 영향을 미친다. 본 논문에서는 얼굴 인식률 향상을 위하여 전처리 단계에서 타원 모델을 이용하여 배경 영역을 제거하는 방법을 제안하였다. 사람의 얼굴 윤곽은 타원의 형태를 나타내기 때문에 얼굴 영상에서 타원 모델을 이용할 경우 얼굴 영역을 용이하게 검출할 수 있다. ETRI, ORL, 및 XM2VTS 얼굴 데이터베이스에 대한 실험 분석을 통하여 제안된 방법이 얼굴 인식 성능을 뚜렷하게 개선시켰음을 알 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• 제13권1E호
• /
• pp.20-24
• /
• 1994

이 논문에서는 새로운 음성 인식 모델인 동적 국부 자기 조직 지도 모델과 그 학습 알고리즘을 제안한다. 동적 국부 자기 조직 지도 모델은 음성의 시간적, 공간적 왜곡을 프로그래밍 기법과 국부 자기 조직 지도로 각각 정규화 시킨다. 한국어 숫자음에 대한 실험 결과로 제안하는 모델이 예측 신경회로망 모델보다 적은 수의 연결을 갖고서도 약간 높은 인식률을 보여 효과적임을 알 수 있었다.

• Journal of Multimedia Information System
• /
• 제5권4호
• /
• pp.221-228
• /
• 2018

Skin-color information is not sufficient for palmprint segmentation in complex scenes, including mobile environments. Traditional active shape model (ASM) combines gray information and shape information, but its performance is not good in complex scenes. An improved ASM method is developed for palmprint segmentation, in which Perux method normalizes the shape of the palm. Then the shape model of the palm is calculated with principal component analysis. Finally, the color likelihood degree is used to replace the gray information for target fitting. The improved ASM method reduces the complexity, while improves the accuracy and robustness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.929-944
• /
• 2019

Many critical applications require accurate real-time human action recognition. However, there are many hurdles associated with capturing and pre-processing image data, calculating features, and classification because they consume significant resources for both storage and computation. To circumvent these hurdles, this paper presents a recognition machine learning (ML) based system model which uses reduced data structure features by projecting real 3D skeleton modality on virtual 2D space. The MMU VAAC dataset is used to test the proposed ML model. The results show a high accuracy rate of 97.88% which is only slightly lower than the accuracy when using the original 3D modality-based features but with a 75% reduction ratio from using RGB modality. These results motivate implementing the proposed recognition model on an embedded system platform in the future.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• 반도체디스플레이기술학회지
• /
• 제23권1호
• /
• pp.61-64
• /
• 2024

As research on autonomous driving technology becomes more active, various studies on signal recognition of traffic lights are also being conducted. When recognizing traffic lights with different purposes and shapes, such as pedestrian traffic lights, vehicle-only traffic lights, and right-turn traffic lights, existing classification methods may cause misrecognition problems. Therefore, in this study, we studied a model that allows accurate signal recognition by subdividing the classification of signals according to the purpose and type of traffic lights. A signal recognition model was created by classifying traffic lights according to their shape and purpose into horizontal, vertical, right turn, etc., and by comparing them with the existing signal recognition model based on YOLOv5, it was confirmed that more correct and accurate recognition was possible.