• 대한의용생체공학회:의공학회지
• /
• 제15권2호
• /
• pp.175-182
• /
• 1994

The international standard for digital compression and coding of continuous-tone still image known as JPEG (Joint Photographic Experts Group) standard is investigated for medical image archiving and communication. The JPEG standard has widely been accepted in the areas of electronic image communication, computer graphics, and multimedia applications, however, due to the lossy character of the JPEG compression its application to the field of medical imaging has been limited. In this paper, the JPEG standard is investigated for medical image compression with a series of head sections of magnetic resonance (MR) images (256 and 4096 graylevels, $256 {\times}256$size). Two types of Huffman codes are employed, i. e., one is optimized to the image statistics to be encoded and the other is a predetermined code, and their coding efficiencies are examined. From experiments, compression ratios of higher than 15 were obtained for the MR images without noticeable distortion. Error signal in the reconstructed images by the JPEG standard appears close to random noise. Compared to existing full-frame bit-allocation technique used for radiological image compression, the JPEG standard achieves higher compression with less Gibb's artifact. Feature of the progressive image build-up of the JPEG progressive coding may be useful in remote diognosis when data is transmitted through slow public communication channel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.280-282
• /
• 2020

최근 사물인터넷(IoT), 자율주행과 같이 기계 간의 통신이 요구되는 서비스가 늘어감에 따라, 기계 임무 수행에 최적화된 데이터의 생성 및 압축에 대한 필요성이 증가하고 있다. 또한, 사물인터넷과 인공지능(AI)이 접목된 기술이 주목을 받으면서 딥러닝 모델에서 추출되는 특징(feature)을 디바이스에서 클라우드로 전송하는 방안에 관한 연구가 진행되고 있으며, 국제 표준화 기구인 MPEG에서는 '기계를 위한 부호화(Video Coding for Machine: VCM)'에 대한 표준 기술 개발을 진행 중이다. 딥러닝으로 특징을 추출하는 가장 대표적인 방법으로는 합성곱 신경망(Convolutional Neural Network: CNN)이 있으며, 오토인코더는 입력층과 출력층의 구조를 동일하게 하여 출력을 가능한 한 입력에 근사시키고 은닉층을 입력층보다 작게 구성하여 차원을 축소함으로써 데이터를 압축하는 딥러닝 기반 이미지 압축 방식이다. 이에 본 논문에서는 이러한 오토인코더의 성질을 이용하여 CNN 기반의 이미지 분류 네트워크의 합성곱 신경망으로부터 추출된 feature에 오토인코더를 적용하여 압축하는 방안을 제안한다.

• 한국통신학회논문지
• /
• 제24권6B호
• /
• pp.1174-1182
• /
• 1999

최근 MPEG-4 표준화 작업의 마무리와 MPEG-7 표준화 작업이 활발히 진행됨에 따라 영상내의 물체(object)의 모양 정보 부호화의 중요성이 대두되었다. 본 논문에서는 물체의 특징을 표현하기에 적합한 다각형 근사화 정점을 효율적으로 부호화하는 기법에 대해 연구하였다. 제안한 기법에서는 근사 다각형의 정점들을 이용하여 삼각형의 무게 중심들을 구한 후 순차적으로 부호화한다. 무게 중심들의 분포영역이 좁다는 사실을 이용하여 부호화 효율을 얻을 수 있다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 추계 종합학술대회 논문집
• /
• pp.505-510
• /
• 2004

This paper suggests a new CT-image segmentation algorithm. This algorithm uses morphological filters and the watershed algorithms. The proposed CT-image segmentation algorithm consists of six parts: preprocessing, image simplification, feature extraction, decision making, region merging, and postprocessing. By combining spatial and temporal information, we can get more accurate segmentation results. The simulation results illustrate not only the segmentation results of the conventional scheme but also the results of the proposed scheme; this comparison illustrates the efficacy of the proposed technique. Furthermore, we compare the various medical images of the structuring elements. Indeed, to illustrate the improvement of coding efficiency in postprocessing, we use differential chain coding for the shape coding of results.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2000년도 춘계공동학술대회 논문집
• /
• pp.28-31
• /
• 2000

In this paper, part features are classified and then coding system is constructed by the considering characteristics of features in assembly process. Analyzing the characteristics of features, code values about part features are determined. Assembly process is divided into five functions such as transporting, handling, approaching, alignment, joining and then the detail parameters of each function are determined. Code values about assembly process are determined according to detail parameters. The detail parameters are the kinds of available working method and assembly tools, when each assembly function is going on. By the coding system, available assembly process can be grasped and perceived the part that Is difficult to assemble.

• 전기전자학회논문지
• /
• 제4권2호
• /
• pp.288-294
• /
• 2000

본 논문에서는 동영상 압축 기법을 향상시키기 위하여 효율적인 detail 추출 기법을 제안한다. 기존의 top-hat 변환을 이용한 기법은 고립되어 있고 시각적으로 중요한 detail의 추출에는 효율적이지만, 영역의 경계에서는 비효율적이다. 제안된 기법은 수리형태학적 Laplacian 연산의 영역경계 정보추출의 성질을 이용하여 압축을 향상시키고 저비트율을 제공한다. 실험결과를 통해서 제안된 기법이 기존 기법보다 효율적임을 보이고 수리형태학적 Laplacian 연산 적용의 타당성을 설명한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.20-22
• /
• 2007

The H.264/AVC standard developed by the joint Video Team (JVT) provides better coding efficiency than previous standards. The new emerging H.264/AVC employs variable block size motion estimation using multiple reference frame with 1/4-pel MV(Motion Vector) accuracy. These techniques are a important feature to accomplish higher coding efficiency. However, these techniques are increased overall computational complexity. To overcome this problem, this paper proposes advanced fast mode decision suited for variable block size by classifying inter mode based on Rate Distortion Optimization(RDO) technique. Proposed algorithm is going to use to implement H/W structure for fast mode decision. The experimental results shows that the proposed algorithm provides significant reduction computational complexity without any noticeable coding loss and additional computation. Entire computational complexity is decreased about 30%.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.326-329
• /
• 2009

This paper proposes a new video compression algorithm using an adaptive transform that is adjusted depending on the frequency contents of the input signals. The adaptive transform is based on the warped discrete cosine transform (WDCT) which is shown to provide better performance than the DCT at high bit rates, when applied to JPEG compression scheme [1, 2, 3]. The WDCT is applied to the video compression in this paper, as a new feature in the H.264/AVC. The proposed method shows the coding gain over the H.264/AVC at high bit rates. The coding gain is shown over the 35dB PSNR quality, and the gain increases as the bit rate increases. (about 1.0dB at 45dB PSNR quality at maximum)

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.153-162
• /
• 1995

When vector quantization is used in low rate image coding (e.g., R<0.5), the primary problem is the tremendous computational complexity which is required to search the whole codebook to find the closest codevector to an input vector. Since the number of code vectors in a vector quantizer is given by an exponential function of the dimension. i.e., L=2$^{nR}$ where Rn. To alleviate this problem, a multiple shell structure of hypercube feature maps (MSSHFM) is proposed. A binary HFM of k-dimension is composed of nodes at hypercube vertices and a multiple shell architecture is constructed by surrounding the k-dimensional hfm with a (k+1)-dimensional HFM. Such a multiple shell construction of nodes inherently has a complete tree structure in it and an efficient partial search scheme can be applied with drastically reduced computational complexity, computer simulations of still image coding were conducted and the validity of the proposed method has been verified.