• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.405-407
• /
• 1997

본 논문은 자동차 번호판 용도문자를 인식하개 위한 전처리 과정으로써 웨이브릿 변환을 적용한 연구에 관해 기술한다. 웨이브릿 변환에 의하여 여과된 고주파 대역의 영상은 수평방향, 수직방향, 대각선 방향의 윤관석 형태로 세 개의 대역에 존재하게 되는데, 대상영상이 고주파 대역의 에너지량이 적게 나타나는 반면에 저주파 대역의 에너지량은 크므로 용도문자의 인식 과정에서 저주파 대역 부분만을 이용하였다. 저주파 대역에서 $20{\times}20$크기의 영상을 추출하고 영상을 정규화 하여 오츠알고리즘을 통한 이치화 과정을 거친 다음 역전파 신경망으로 인식함으로써 기존의 단순축소 방법보다 향상된 결과를 실험을 통하여 확인할 수 있었다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.97-108
• /
• 1994

A modified Karhunen-Loeve transformation technique using normalization and simultaneous diagonalization of two sample covariance matrices is proposed to separate the object from the background. The transformation technique for the separation of local data structure through maximizing the ratio of sample variances between two classes was identified as a promising one for a preprocessing of multi-variate signal processing algorithms using neighborhood operators including morphological filtering. To relate the separation quality of the proposed technique to a morphological measure, average height was defined by using morphological pattern spectrum. A practical implementation of the transformation technique was tested experimentally and the theoretical results were confirmed.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.361-373
• /
• 2002

In this paper, we propose a channel normalization method to improve the performance of CMS (cepstral mean subtraction) which is widely adopted to normalize a channel variation for speech and speaker recognition. CMS which estimates the channel effects by averaging long-term cepstrum has a weak point that the estimated channel is biased by the formants of voiced speech which include a useful speech information. The proposed Formant-broadened Cepstral Mean Subtraction (FBCMS) is based on the facts that the formants can be found easily in log spectrum which is transformed from the cepstrum by fourier transform and the formants correspond to the dominant poles of all-pole model which is usually modeled vocal tract. The FBCMS evaluates only poles to be broadened from the log spectrum without polynomial factorization and makes a formant-broadened cepstrum by broadening the bandwidths of formant poles. We can estimate the channel cepstrum effectively by averaging formant-broadened cepstral coefficients. We performed the experiments to compare FBCMS with CMS, PFCMS using 4 simulated telephone channels. In the experiment of channel estimation, we evaluated the distance cepstrum of real channel from the cepstrum of estimated channel and found that we were able to get the mean cepstrum closer to the channel cepstrum due to an softening the bias of mean cepstrum to speech. In the experiment of text-independent speaker identification, we showed the result that the proposed method was superior than the conventional CMS and comparable to the pole-filtered CMS. Consequently, we showed the proposed method was efficiently able to normalize the channel variation based on the conventional CMS.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1991.10a
• /
• pp.96-99
• /
• 1991

FIR형은 하드웨어 규모가 커져서 구성이 어렵다는 단점을 가지고 있으나, IIR형은 적은 차수로써 큰 차수의 FIR필터를 대신할 수 있다. IIR형은 적은 계산량과 간단한 하드웨어 구성이라는 장점을 갖고 있으나 수렴성에 있어서는 어려움이 있다. 본 연구에서는 적은 차수로 양호한 수렴특성을 갖는 IIR 필터를 구성하기 위하여 연속시간영역의 직교필터를 이산시간영역으로 변환하고 직교성을 유지하도록 정규화한 정규직교함수계에 의해서 설정된 전달함수를 적응 디지틀필터에 적용하였다. 이 방법을 확인하기 위하여 FIR형에 비교해서 적은 차수로 컴퓨터 시뮬레이션을 수행한 결과 양호한 수렴특성을 확인하였다.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.02a
• /
• pp.357-358
• /
• 2009

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.683-687
• /
• 2010

This paper studied some methods which use frequency warping method that is the one of the speech transformation method to develope the robust speech recognition system for the emotional variation. For this purpose, the effect of emotional variations on the speech signal were studied using speech database containing various emotions and it is observed that speech spectrum is affected by the emotional variation and this effect is one of the reasons that makes the performance of the speech recognition system worse. In this paper, new training method that uses frequency warping in training process is presented to reduce the effect of emotional variation and the speech recognition system based on vocal tract length normalization method is developed to be compared with proposed system. Experimental results from the isolated word recognition using HMM showed that new training method reduced the error rate of the conventional recognition system using speech signal containing various emotions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.244-247
• /
• 1999

in this paper, we propose the recognition system of face using polynomial coefficients to recognize fact images using neural network. The system consists of following steps. First step, the sizes of fare images is reduced sizes of input images to 1/4 using wavelet transform. Second step, the polynomial coefficients is obtained from low frequency coefficient matrix after 3 level wavelet transform. Third step, polynomial coefficients is normalized. The of range of normalization is from -1 to 1. Last, Face images is trained and recognized using neural network with error back propagation algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.359-361
• /
• 2012

본 논문은 T2강조 MR 영상과 확산강조 MR 영상의 강체 정합을 통해 크기, 위치, 회전 변환 왜곡을 보정하여 자궁내막암의 위치를 자동으로 찾는 방법을 제안한다. 영상해상도와 밝기값 분포가 서로 다른 두 영상간 정합의 정확성을 향상시키기 위해 잡음을 제거하고 두 영상의 밝기값 신호 분포의 유사성을 강화시킨다. 유사성이 향상된 두 영상의 크기, 위치, 회전 변환 왜곡을 보정하기 위해 정규화 상호정보를 최대화 하는 강체 정합을 반복적으로 수행한다. 정합된 영상에서 악성 종양을 쉽게 판별 할 수 있도록 현상확상계수지도를 컬러맵으로 생성하여 T2강조 MR 영상에서 얻은 종양의 후보군에 매핑하여 T2강조 MR 영상과 융합한다. 실험을 위하여 최적화 반복 과정에 따른 정규화 상호정보 수치 수렴 과정을 확인하고, 융합 후 종양 영역이 매핑되는 것을 육안평가를 통해 분석하였다. 제안방법을 통하여 T2강조 MR 영상과 확산강조 MR 영상을 융합함으로써 종양의 위치를 자동으로 파악하고 자궁내막암의 병기를 확정하는 용도로 활용할 수 있다.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.221-230
• /
• 2011

Digital comic images are one of popular contents on the Internet. Usually, they are scanned from comic books by digital scanners. Without post-processing, they may have different sizes, skews and margins other than contents at the boundary. To normalize the size of their contents without the skews and margins is an important step in comic image analysis and application such as content-based comic image retrieval system. In this paper, we propose a method to detect a box frame in comic images by extracting of line segments using the gradient Radon transform. The box frame in comic images is the maximum rectangle which consists of contents without margins. We use the detected box frame to normalize the size of comic images and to make them no skew. In addition, the proposed method is implemented by OpenCL to speed up the detection of the line segments. Experimental results show that our proposed method effectively detects the box frame in comic images.

• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1102-1111
• /
• 2012

In this paper, we propose a robust watermarking method against geometric attack even though the watermarked image is partially damaged. This method consists of standard image normalization which transforms any image into a predefined standard image and embedding watermark in DCT domain of standard normalized image using spread spectrum technique. The proposed standard image normalization method has an improvement over existing image normalization method, so it is robust to partial damage and geometric attack. The watermark embedding method using spread spectrum technique also has a robustness to image losses such as blurring, sharpening and compressions. In addition, the proposed watermarking method does not need an original image to detect watermark, so it is useful to public watermarking applications. Several experimental results show that the proposed watermarking method is robust to partial damage and various attacks including geometric deformation.