• 융합정보논문지
• /
• 제10권8호
• /
• pp.40-46
• /
• 2020

교통안전에 대한 관심이 높아짐에 따라 교통사고의 발생률을 줄이는 자율 주행에 대한 연구가 지속적으로 진행되고 있다. 객체의 인식과 탐지는 자율 주행을 위한 필수적인 요소이다. 때문에 도로 상황을 판단하기 위하여 교통 영상 빅데이터에서 객체 인식 및 탐지에 대한 연구가 활발히 진행 중이다. 하지만 기존 연구들은 대부분 주간 데이터만 사용하기 때문에 야간 도로에서 객체 인식이 어렵다. 특히 광원 객체의 경우 빛 번짐과 백화 현상으로 인해 주간의 특징을 그대로 사용하기 어렵다. 따라서 본 연구에서는 교통 영상 빅데이터 처리를 위한 Yolo 기반 광원 객체 탐지를 제안한다. 제안하는 방법은 야간 교통 영상을 대상으로 색상 모델 변화를 적용하여 이미지 처리를 수행한다. 이미지 처리를 통해서 객체의 특징을 추출하여 객체의 후보군을 결정한다. 후보군 데이터를 활용하여 딥러닝 모델을 통해 야간 도로에서 광원 객체 탐지의 인식률을 높이는 것이 가능하다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.1055-1056
• /
• 2008

In this paper, we survey various Robust Object Recognition Algorithms. One of the core technologies for local feature detector is Scale Invariant Feature Transform. And we compared several algorithms with SIFT based on IPP technology. As a result, the conversion of source codes using IPP is sped up. And this will be more improved recognition speed using SIMD Instructions.

• 대한음성학회지:말소리
• /
• 제50호
• /
• pp.99-110
• /
• 2004

The normal transmission characteristics of sound are hardly obtained due to the various noises and structural factors in a running car environment. It is due to the channel distortion of the original source sound recorded by microphones, and it seriously degrades the performance of the speech recognition in real driving environments. In this paper we analyze the degree of intelligibility under the various sound distortion environments by channels according to driving speed with respect to speech transmission index(STI) and compare the STI with rates of speech recognition. We examine the correlation between measures of intelligibility depending on sound pick-up patterns and performance in speech recognition. Thereby we consider the optimal location of a microphone in single channel environment. In experimentation we find that high correlation is obtained between STI and rates of speech recognition.

• Journal of information and communication convergence engineering
• /
• 제9권6호
• /
• pp.637-640
• /
• 2011

The hybrid neural networks have characteristics such as fast learning times, generality, and simplicity, and are mainly used to classify learning data and to model non-linear systems. The middle layer of a hybrid neural network clusters the learning vectors by grouping homogenous vectors in the same cluster. In the clustering procedure, the homogeneity between learning vectors is represented as the distance between the vectors. Therefore, if the distances between a learning vector and all vectors in a cluster are smaller than a given constant radius, the learning vector is added to the cluster. However, the usage of a constant radius in clustering is the primary source of errors and therefore decreases the recognition success rate. To improve the recognition success rate, we proposed the enhanced hybrid network that organizes the middle layer effectively by using the enhanced ART1 network adjusting the vigilance parameter dynamically according to the similarity between patterns. The results of experiments on a large number of calling card images showed that the proposed algorithm greatly improves the character extraction and recognition compared with conventional recognition algorithms.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.109-115
• /
• 2009

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. In this paper, we investigate several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. At first, word distance method based on phone and syllable distances are considered. These methods use just Levenstein distance on phones or double Levenstein distance algorithm on syllables of candidates. Next, word similarity approaches are presented that they use characters' position information of word candidates. Each character's position is labeled to inserted, deleted, and correct position after alignment between source and target string. The word similarities are obtained from characters' positional probabilities which mean the frequency ratio of the same characters' observations on the position. From experimental results, we can find that the proposed methods are effective for removing non-similar words without loss of system performance from the N-best recognition candidates of the systems.

• ETRI Journal
• /
• 제46권1호
• /
• pp.71-81
• /
• 2024

Recent advances in deep learning for speech and visual recognition have accelerated the development of multimodal speech recognition, yielding many innovative results. We introduce a Korean audiovisual speech recognition corpus. This dataset comprises approximately 150 h of manually transcribed and annotated audiovisual data supplemented with additional 2000 h of untranscribed videos collected from YouTube under the Creative Commons License. The dataset is intended to be freely accessible for unrestricted research purposes. Along with the corpus, we propose an open-source framework for automatic speech recognition (ASR) and audiovisual speech recognition (AVSR). We validate the effectiveness of the corpus with evaluations using state-of-the-art ASR and AVSR techniques, capitalizing on both pretrained models and fine-tuning processes. After fine-tuning, ASR and AVSR achieve character error rates of 11.1% and 18.9%, respectively. This error difference highlights the need for improvement in AVSR techniques. We expect that our corpus will be an instrumental resource to support improvements in AVSR.

• 음성과학
• /
• 제10권3호
• /
• pp.213-224
• /
• 2003

Spoken sound includes not only speaker's source but the characteristics of vocal tract and speech radiation. This paper is based on the theory of Park[1], who proposes the Phonation Type Index k; a variable that shows the characteristic of speaker's source excluding those of speaker's vocal tract and speech radiation. With Park's theory, we collect data by changing recording environments and expanding experimental data, and analyze the data collected to see whether or not the PTI k shows good discriminating power as a variable for speaker recognition. In the experiment, we repeatedly record 8 sentences ten times for each of 5 males in the environment of a recording room and an office, extract PTI k for each speaker, and measure the discriminating power for each speaker by using the value of PTI k. The result shows that PTI k has the excellent discriminating power of speakers. We also confirm that, even if the recording environment is changed, PTI k shows similar results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1244-1248
• /
• 2005

In this paper, we propose fuzzy c-means (FCM) to solve recognition errors in invariant range image, multi-pose face recognition. Scale, center and pose error problems were solved using geometric transformation. Range image face data was digitized into range image data by using the laser range finder that does not depend on the ambient light source. Then, the digitized range image face data is used as a model to generate multi-pose data. Each pose data size was reduced by linear reduction into the database. The reduced range image face data was transformed to the gradient face model for facial feature image extraction and also for matching using the fuzzy membership adjusted by fuzzy c-means. The proposed method was tested using facial range images from 40 people with normal facial expressions. The output of the detection and recognition system has to be accurate to about 93 percent. Simultaneously, the system must be robust enough to overcome typical image-acquisition problems such as noise, vertical rotated face and range resolution.

• 한국정보통신학회논문지
• /
• 제19권12호
• /
• pp.2792-2799
• /
• 2015

본 논문에서는 화자 인식의 성능을 개선하기 위해서 glottal flow로부터 source mel-frequency cepstral coefficient (SMFCC), 왜도, 첨도를 추출하여 활용하였다. 일반적으로 glottal flow의 고주파 대역은 응답의 크기가 평탄하므로 미리 정한 차단주파수 미만에 대해서만 SMFCC를 추출한다. 추출된 SMFCC, 왜도, 첨도는 종래의 특징 파라미터와 결합된 후 종래의 화자인식 시스템과 동등한 조건에서의 성능 비교를 위하여 principal component analysis (PCA) 및 linear discriminiat analysis (LDA)를 통한 차원축소가 행해진다. 대용량의 화자인식 실험결과를 통해서 제안된 인식 시스템이 종래의 화자인식 시스템 보다 더 좋은 성능을 나타냄을 확인할 수 있었으며, 특히 가우시안 혼합이 낮을 때 더 높은 성능향상을 나타내었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.430-435
• /
• 1992

This paper presents a real-time algorithm for an infrared seeker to find the real target automatically against various background noises without changing the reticle configuration. The modeling technique of infrared sources and analysis results of the various source types based on the FFT algorithm are included. Futhermore, a neural network is used to recognize the source type using the results of FFT analysis. The evaluation of target recognition for cases which can happen in real situation is also treated.