• 전자공학회논문지B
• /
• 제32B권3호
• /
• pp.24-30
• /
• 1995

The process of conventional floating-point additio $n_traction operation consists of alignment, additio $n_traction, normalization, and rounding stage. Because rounding stage needs an incrementor or adder, it occupies much time and chip area. In addition, it needs additional time and hardware for renormalization which occurs in overflow due to rounding In this paper, floating-point adde $r_tractor performing rounding and additio $n_traction in parallel is presented by using the feature of additio $n_traction and carry select adder used in additio $n_tracting stage. Proposed floating point adde $r_tractor doesn't need time and incrementor nor adder for rounding. Also, renormalization doesn't occur since rounding is performed prior to normalization.to normalization.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 춘계종합학술대회
• /
• pp.591-594
• /
• 2004

In this paper, The identity distinction of the moving objects using distance among hue normalization levels was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from 0$^{\circ}$ to 360$^{\circ}$. A distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.65-70
• /
• 2020

CNN's technologies that represent emotional detection include primitive CNN algorithms, deployment normalization, and drop-off. We present the methods and data of the three experiments in this paper. The training database and the test database are set up differently. The first experiment is to extract emotions using Batch Normalization, which complemented the shortcomings of distribution. The second experiment is to extract emotions using Dropout, which is used for rapid computation. The third experiment uses CNN using convolution and maxpooling. All three results show a low detection rate, To supplement these problems, We will develop a deep learning algorithm using feature extraction method specialized in image processing field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.166-179
• /
• 2021

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

• 대한전자공학회논문지SP
• /
• 제41권4호
• /
• pp.1-7
• /
• 2004

본 논문은 3차원 얼굴 영상을 이용한 얼굴 인식에 있어서, 정규화 과정에 사용될 얼굴의 특징 영역을 추출하는 방법을 제안한다. 3차원 얼굴 영상은 조명의 변화에 상관없이 얼굴의 특징 분석이 가능하고, 이를 이용한 얼굴 인식이 가능하다. 그러나 입력된 형상의 자세에 따라 회전, 기울어진 정도, 그리고 좌우로 움직인 정도가 다르다. 이런 특성을 고려하지 않고 추출된 특징들은 잘못된 인식 결과를 초래할 수 있다. 이런 이유로 입력에서의 오류들을 바로잡는 정규화 과정이 필요하다. 정규화 과정에서는 얼굴의 기하학적인 특징인 눈, 코, 입 등을 이용하는 것이 일반적이다. 이들 중, 코는 3차원 얼굴 영상에서 두드러진 특징이 될 수 있다. 본 연구에서는 코의 실제 형상과 유사한 긴 추출 마스크를 사용하여 입력된 영상으로부터 코를 추출하는 방법을 제안한다.

• 융합신호처리학회논문지
• /
• 제3권1호
• /
• pp.8-14
• /
• 2002

본 논문에서는 Gaussian mixture model을 이용한 실시간 문맥독립화자식별시스템을 구현하여 인식실험을 수행하였으며, 인식시스템의 성능을 향상시키기 위하여 화자검증시스템에서 좋은 결과를 보인 유사도 정규화(Likelihood normalization)방법을 적용하여 인식실험을 하였다. 시스템은 크게 전처리단과 화자모델생성단, 화자식별단으로 나누어진다. 전처리단에서는 화자의 발성변화를 고려하여 CMN(Cepstral mean normalization)과 Silence removal 방법을 적용하였다. 화자모델생성단에서는, 화자발성의 음향학적 특징을 잘 표현할 수 있는 GMM(Gaussian mixture model)을 이용하여 화자모델을 작성하였으며, GMM의 파라미터를 최적화하기 위하여 MLE(Maximum likelihood estimation)방법을 사용하였다. 화자식별단에서는 학습된 데이터와 테스트용 데이터로부터 ML(Maximum likelihood)을 이용하여 유사도를 계산하였으며, 이 과정에서 유사도 정규화를 적용한 경우에는 프레임단위로 유사도를 계산하게 된다. 계산된 유사도는 스코어(S$_{C}$)로 표현하였고, 가장 높은 스코어를 가지는 화자가 인식화자로 결정된다. 화자인식에서 발성의 종류로는 문맥독립 문장을 사용하였다. 인식실험을 위해서는 ETRI445 DB와 KLE452 DB를 사용하였으며, 특징파라미터로서는 켑스트럼계수 및 회귀계수값만을 사용하였다. 인식실험에서는 등록화자의 수를 달리하여 일반적인 화자식별방법과 프레임단위유사도정규화방법으로 각각 인식실험을 하였다. 인식실험결과, 프레임단위유사도정규화방법이 인식화자수가 많아지는 경우에 일반적인 방법보다 향상된 인식률을 얻을 수 있었다.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.131-140
• /
• 1996

In this paper, we propose the method that extracts the speech feature using the hearing model through signal precessing techniques. The proposed method includes following procedure ; normalization of the short-time speech block by its maximum value, multi-resolution analysis using the discrete wavelet transformation and re-synthesize using thediscrete inverse wavelet transformation, differentiation after analysis and synthesis, full wave rectification and integration. In order to verify the performance of the proposed speech feature in the speech recognition task, korean digita recognition experiments were carried out using both the dTW and the VQ-HMM. The results showed that, in case of using dTW, the recognition rates were 99.79% and 90.33% for speaker-dependent and speaker-independent task respectively and, in case of using VQ-HMM, the rate were 96.5% and 81.5% respectively. And it indicates that the proposed speech feature has the potentials to use as a simple and efficient feature for recognition task.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.203-207
• /
• 2001

In this Paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using CCD color image. To do this, we first acquire the color image from the CCD camera, and then propose the method for recognizing the expression to be represented the structural correlation of man's feature Points(eyebrows, eye, nose, mouse) It is central technology that the Process of extract, separate and recognize correct data in the image. for representation is expressed by structural corelation of human's feature Points In the Proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Had separated complexion area using color-difference of color space by method that have separated background and human's face toughly to change such as external illumination in this paper. For this, we propose an algorithm to extract four feature Points from the face image acquired by the color CCD camera and find normalization face picture and some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector. Finally, we show the Practical application possibility of the proposed method.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.435-447
• /
• 1996

In this paper, we propose the method that extracts the speech feature using the hearing model through signal processing techniques. The proposed method includes the following procedure ; normalization of the short-time speech block by its maximum value, multi-resolution analysis using the discrete wavelet transformation and re-synthesize using the discrete inverse wavelet transformation, differentiation after analysis and synthesis, full wave rectification and integration. In order to verify the performance of the proposed speech feature in the speech recognition task, korean digit recognition experiments were carried out using both the DTW and the VQ-HMM. The results showed that, in the case of using DTW, the recognition rates were 99.79% and 90.33% for speaker-dependent and speaker-independent task respectively and, in the case of using VQ-HMM, the rate were 96.5% and 81.5% respectively. And it indicates that the proposed speech feature has the potential for use as a simple and efficient feature for recognition task

• 한국정보과학회논문지:데이타베이스
• /
• 제36권6호
• /
• pp.446-454
• /
• 2009

다양한 영역 검출 및 형태 특징 추출 방법 중에서 MSER과 SIFT를 응용한 방법들이 컴퓨터비전 분야에 많이 사용된다. 하지만 기존의 SIFT를 이용한 특징 추출 방법은 자기 변화에 민감한 특성을 지니며, MSER 방법은 이미지의 크기 변화에 민감하고, 이미지 유사성 검색에 그대로 적용하기에는 어려움이 많다. 본 논문에서는 스케일 피라미드, MSER 그리고 어파인(affine) 정규화 과정 등을 이용한 영역 특징 서술자를 제안한다. 제안한 방법은 어파인 정규화 방법과 스케일 피라미드를 사용하기 때문에 이미지의 크기, 회전 및 자기 변화에 불변하다. 다양한 이미지들을 이용하여 실험하고, 실험 결과에서 제안한 방법이 SIFT, PCA-SIFT, CE-SIFT 그리고 SURF 방법에 비해서 각각 20%, 38%, 11%, 24% 이상 좋은 이미지 검색 성능을 보이고 있다.