• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.579-582
• /
• 2001

Vector Transformation is a new method unified vector quantization and coding. So far, codebook generation applied to coding was LBG algorithm. But using the advantage of SOFM(Self-Organizing Feature Map) based on neural network can improve a system's performance. In this paper, we generated VTC(Vector Transformation Coding) codebook applied with SOFM algorithm and compare the result for several coding rates with LBG algorithm. The problem of Vector quantization is complicated calculation and codebook generation. So, to solve this problem, we used neural network approach method.

• Journal of IKEEE
• /
• v.6 no.2 s.11
• /
• pp.152-160
• /
• 2002

This paper is the realization of the face recognition system for multimedia application. This system is focused on the design concerning the improvement of recognition rate and the reduction of processing time for face recognition. The non-modificated application of typical RGB color system enables the reduction of time required for color system transform. The neural network and the application of algorithm using face characteristic improves the recognition rate. After mosaicking an image, a face-color block has been selected through the color analysis of mosaic block. The characteristic of the face removes the mis-checked face-color candidate block. Finally, from the face color block, four special values are obtained. These values are processed to the neural network using the back propagation algorithm. The output values are the touchstone to decide the genuineness of face field. The realized system showed 90% of face recognition rate with less than 0.1 second of processing time. This result can be understood as sufficient processing time and recognition rate to find out the face block for multimedia application in dynamic image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.571-574
• /
• 2001

In our paper, We propose an efficient adaptive coding method using kohonen neural network. An efficient adaptive encoding method using Kohonen net work is discribed through the analysis of those compression methods with the application of the neural network. In order to increase the compression ratio, a image is first divided into 8*8 subimages, then all subimages are transformed by DCT. These DCT sub-blocks are divided into N(4) classes by Kohonen network. Hits are distributed according to the variance of the DCT sub-block. Thus we get N(4)bit allocation matrices. Excellent performance is shown by the computer simulation. so we found that our proposed method is better then classifing subimages by AC energy.

• Annual Conference on Human and Language Technology
• /
• 1992.10a
• /
• pp.237-248
• /
• 1992

본 논문에서는 통계적인 특징 추출 방법을 사용하여 샘물체로 필기된 한글을 고속으로 인식하는 방법을 소개한다. 대부분이 직선 성분으로 이루어진 한글의 특성을 이응하기 위하여 입력 영상으로부터 수평, 수직, 사선, 역사선의 방향 성분을 추출하며, 검은 화소의 밀도에 따라 동적으로 그물을 결정함으로써 획 간의 접촉 변형에 무관한 특징 벡터를 추출한다. 이와 같은 통계적 특징 추출 방법은 크기 정규화나 세선화 과정이 필요없으며, 또한 샘물체라는 필기 형태의 제약에 의해 정합 대상 부류의 수가 현저히 줄어들기 때문에 인식에 소요되는 시간을 상당히 줄일 수 있음은 물론, 인식률을 향상시켰다. 제안된 방법의 타당성을 검증하기 위하여 샘물체로 필기된 KS 완성형 한글 2,350자에 대해 실험한 결과, 평균 90% 이상의 인식률을 보이며, IBM PC 486(33MHz)상에서 문자당 평균 0.17초의 인식 속도를 보임으로써, 실용적인 고속 OCR 시스템의 개발 가능성을 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.474-480
• /
• 2020

With the advent of the Fourth Industrial Revolution, many new technologies are being utilized. In particular, video signals are used in various fields. However, when transmitting and receiving video signals, salt and pepper noise and additive white Gaussian noise (AWGN) occur for multiple reasons. Failure to remove such noise when performing image processing can cause problems. Generally, filters such as CWMF, MF, and AMF remove noise. However, these filters perform somewhat poorly in the high-density noise domain and cause smoothing, resulting in slightly lower retention of the edge components. In this paper, we propose an algorithm by effectively eliminating salt and pepper noise using a modified weight filter using standard deviation. In order to prove the noise reduction performance of the proposed algorithm, we compared it with the existing algorithm using PSNR and magnified images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.307-310
• /
• 2013

아무르불가사리에 기인한 환경적, 경제적 피해는 해마다 증가되고 있습니다. 우리나라 남해와 동해 바다에 널려 있는 불가사리들이 최근 서해안에서도 급속히 늘어나고 있습니다. 특히 러시아 해역에 서식하는 아무르 불가사리의 개체수가 급증해 어장을 황폐화 시키고 있습니다. 이로 인하여 엄청난 번식력과 포식력을 지닌 아무르불가사리가 살아있는 조개류를 먹어치우고 있어서 어민들의 피해가 막심합니다. 이 논문은 변형되어진 아무르불가사리의 구조적 특징과 방사대칭 특성을 이용하여 불가사리 영상을 복원하는 복원기법으로 불가사리의 인식률을 높게 하여 불가사리 퇴치에 많은 도움이 될 것으로 기대합니다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.785-788
• /
• 2001

문자 인식에 있어서 입력 벡터 생성을 위한 정규화(Normalization)는 다차원 입력 벡터를 단순화하여 속도 및 인식률의 개선을 가져오는 중요한 과정이다. 본 논문에서는 문자 인식을 위한 효율적인 입력 영상의 정규화 방법에 대한 연구와 제안하는 획 정규화 기법을 이용하여 Kohonene Neural Network으로 다양한 입력 영상 변형에 따른 인식 성능을 실험으로 비교 분석하여 제안한 정규화 방법의 효율성을 증명하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.7
• /
• pp.1980-1987
• /
• 1999

Restored image is always lower quality than original one due to distortion and noise. The purpose of image restoration is to improve the image quality by fixing the noise or distortion information. One category of spatial filters for image restoration is linear filter. This filter algorithm is easily implemented and can be suppressed the Gaussian noise effectively, but not so good performance for spot or impulse noise. In this paper, we propose the nonlinear spatial filter algorithm for image restoration called the optimal adaptive multistage filter(OAMF). The OAMF is used to reduce the filtering time, increases the noise suppression ratio and preserves the edge information. The OAMF optimizes the adaptive multistage filter(AMF) by using weight learning algorithm of back-propagation learning algorithm. Simulation results of this filter algorithm are presented and discussed.

• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.96-108
• /
• 2014

In case of contrast of the image enhancement by using the conventional histogram equalization, over-enhancement, false contouring and distortion such as the details disappearance of the image occurs due to the excessive brightness change. Especially, these distortion appears when the brightness distribution is concentrated in a particular brightness level. In order to solve these problems, improved histogram equalization methods to transform the input histogram by clipping using threshold have been proposed, but contrast enhancement effect is reduced because it does not consider the characteristics of the input image's histogram to apply the same threshold for the entire histogram, and unnatural image is obtained because it does not retain the characteristics of the image. In this paper, to solve the problems of existing methods, we propose new equalization method that suppress excessive brightness changes by applying to the differential compression according to the histogram frequency, and maintain the characteristics of the input image. In addition, we propose a more effectively method to improve contrast by controlling the strength of the compression ratio depending on the characteristics of the input image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.929-939
• /
• 2010

The growth of multimedia technology forces the development of video detection for large database management and illegal copy detection. To meet this demand, this paper proposes a fast video detection method to apply to a large database. The fast video detection algorithm uses spatial features using the gray value distribution from frames and temporal features using the temporal similarity map. We form the video signature using the extracted spatial feature and temporal feature, and carry out a stepwise matching method. The performance was evaluated by accuracy, extraction and matching time, and signature size using the original videos and their modified versions such as brightness change, lossy compression, text/logo overlay. We show empirical parameter selection and the experimental results for the simple matching method using only spatial feature and compare the results with existing algorithms. According to the experimental results, the proposed method has good performance in accuracy, processing time, and signature size. Therefore, the proposed fast detection algorithm is suitable for video detection with the large database.