• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4476-4491
• /
• 2021

Video service providers tend to face user network problems in the process of transmitting video streams. They strive to provide user with superior video quality in a limited bitrate environment. It is necessary to accurately determine the target bitrate range of the video under different quality requirements. Recently, several schemes have been proposed to meet this requirement. However, they do not take the impact of visual influence into account. In this paper, we propose a new multi-category model to accurately predict the target bitrate range with target visual quality by machine learning. Firstly, a dataset is constructed to generate multi-category models by machine learning. The quality score ladders and the corresponding bitrate-interval categories are defined in the dataset. Secondly, several types of spatial-temporal features related to VMAF evaluation metrics and visual factors are extracted and processed statistically for classification. Finally, bitrate prediction models trained on the dataset by RandomForest classifier can be used to accurately predict the target bitrate of the input videos with target video quality. The classification prediction accuracy of the model reaches 0.705 and the encoded video which is compressed by the bitrate predicted by the model can achieve the target perceptual quality.

• 한국산업정보학회논문지
• /
• 제21권2호
• /
• pp.73-91
• /
• 2016

이 연구는 사용자 관점의 클라우드 품질항목 체계를 도출하고, 각 품질항목별 중요도와 만족도를 조사하며, 사용자-공급자의 인식 차이를 실증 분석함으로써 향후 품질 개선을 위한 정보를 제공한다. 선행 연구 조사와 전문가 포커스 그룹 평가에 의하여 도출된 13개 품질항목은 (1)기능 충분성, (2)이용 편리성, (3)서비스 가용성, (4)반응속도, (5)기술 최신성, (6)서비스 호환성, (7)서비스 맞춤화, (8)서비스 확장성, (9)시스템 보안, (10)고객비밀 보장, (11)계약 신뢰성, (12)고객대응 성실성, (13)인력 전문성이다. 13개 품질항목별 중요도와 만족도를 묻는 설문조사를 사용자 그룹과 공급자 그룹을 대상으로 각각 실시하였다. 통계 분석 결과, 각 품질항목이 얼마나 중요한지에 대하여 사용자와 공급자가 달리 인식하고 있고, 사용자의 만족도가 공급자 만족도보다 낮은 것으로 나타났다. IPA 기법 분석 결과에서도 두 그룹 간 차이가 현저하였다. 13개 품질항목 중 (1)기능 충분성, (10)고객비밀 보장 등 6개 항목의 품질개선이 필요한 것으로 나타났으며, 이러한 개선 필요성은 공급자가 아니라 사용자 관점에서 주로 제시되고 있었다. 연구 본문은 이런 분석 결과가 나타난 원인과 시사하는 바를 조명하고 있다.

• 한국ITS학회 논문지
• /
• 제10권4호
• /
• pp.71-77
• /
• 2011

본 논문에서는 고품질 모바일 VoIP 음성통신에 대한 객관적인 QoS를 제공하는 대화음질 측정시스템을 구현하였다. 대화음질 측정을 위해서 VoIP로 연결된 두 대의 스마트폰에 에코 및 잡음 제거, 음성 인코딩 및 디코딩, RTP (Real-TimeProtocol)을 적용한 패킷 생성, 지터버퍼 콘트롤, LC (Loss Concealment)를 포함한 POS (Play-out Schedule)로 구성된 VoIP음성 통화시스템을 구현하였다. 대화음질 측정 시스템은 VoIP로 연결된 두 스마트폰의 마이크, 그리고 스피커와 연결되어 각 화자별로 음성신호를 녹음한 후에, 녹음된 음성신호를 이용하여 CE (Conversational Efficiency), CS (Conversational Symmetry) 및 PESQ (Perceptual Evaluation of Speech Quality)를 측정하고, CE-CS-PESQ에 대한 상관관계를 측정한다. 본 논문에서는 다양한 SNR, IP 네트워크망 변동에 따른 지연, 손실 변화에 따른 CE, CS, PESQ를 측정하여 대화음질 측정시스템을 검증하였다.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제13권2호
• /
• pp.27-36
• /
• 2007

Recently, hospital patients experience anxiety, confusion, and stress about wayfinding as the spacial layout and treatment circulatory system of hospitals have become complicated due to their oversized and complex structure. As part of finding a solution to the problem, this study seeks to examine what are the essential elements of the wayfinding planning of O.P.D. in general hospitals, to develop the model of wayfinding, and to suggest the methods of improving the wayfinding system. The research methods of this study adopted were literature review in wayfinding cognition, plan analysis of ten general hospitals, space analysis of these hospitals through space syntax, analysis of the system of visual-perceptual information through a field study, and analysis of surveys and follow-up surveys conducted to support the results. Based on these results, the proposals for finding decision points, providing the information, and developing a model planning are listed as follows. 1) The comprehensive understanding of O.P.D. spacial layout and the visual-perceptual information system is necessary to find the essential elements of wayfinding. 2) The decision points are found through the full understanding of spacial functions, circulation systems, and facility configuration, considering the spacial layout, the bound of the visual-perceptual information system, and the circulatory system. Furthermore, the information decision points could be confined by space syntax. 3) The checklist and color compound & color codes, developed through the planning of signage system and color system could be applied to the methods of providing the information. 4) The planning of wayfinding system according to the whole process of practices for outpatients was mentioned above. The system of visual-perceptual information developed through the process of this study should be integrated in the spacial layout of the whole O.P.D.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.2230-2250
• /
• 2015

Multiple projectors with partially overlapping regions can be used to project a seamless image on a large projection surface. With the advent of high-resolution photography, such systems are gaining popularity. Experts set up such projection systems by subjectively identifying the types of errors induced by the system in the projected images and rectifying them by optimizing (correcting) the parameters associated with the system. This requires substantial time and effort, thus making it difficult to set up such systems. Moreover, comparing the performance of different multi-projector display (MPD) systems becomes difficult because of the subjective nature of evaluation. In this work, we present a framework to quantitatively determine the quality of an MPD system and any image projected using such a system. We have divided the quality assessment into geometric and photometric qualities. For geometric quality assessment, we use Feature Similarity Index (FSIM) and distance-based Scale Invariant Feature Transform (SIFT). For photometric quality assessment, we propose to use a measure incorporating Spectral Angle Mapper (SAM), Intensity Magnitude Ratio (IMR) and Perceptual Color Difference (ΔE). We have tested the proposed framework and demonstrated that it provides an acceptable method for both quantitative evaluation of MPD systems and estimation of the perceptual quality of any image projected by them.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.800-803
• /
• 2004

This paper presents a wavelet-based digital watermarking technique for still images. The digital watermarking considering human visual system (HVS) to increase the robustness and perceptual invisibility of digital watermark. The watermarking embedding is modified discrete wavelet transform (DWT) coefficients of the subbands of the images. The human visual system is number of factors that effect the noise sensitivity of human eyes that is considered to increase the robustness and perceptual invisibility of digital watermark. The watermark detection is blind watermark ( original image is not required ). Experimental results successful against attacks by image processing such as add noise, cropping, filtering, JPEG and JPEG2000 compression.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.225-228
• /
• 2005

According to a popularization of the Internet and digital lifestyle, digital watermarks have been proposed for protection of copyrighted multimedia content. In blind watermark detection, which an original image is not provided, robustness against geometric distortion and compression remains challenging. In this paper, we propose a new perceptual blind discrete wavelet transform - discrete Fourier transform (DWT-DFT) composite watermarking scheme that is robust against both general linear transform and JPEG compression. This algorithm constructs an image-dependent watermark in the most significant DWT coefficients, which is determined by using a hierarchical tree structure. Strength of watermark is determined from a just-noticeable difference (JND) profile of a perceptual model. Furthermore, a desired template is inserted into DFT domain of the watermarked image. In new manner, a cross-ratio of four collinear points is used for detecting the template. Experimental results have showed that the proposed scheme is robust against general linear distortion, JPEG compression and various general kinds of attacks in the Stirmark 3.1 watermark evaluation tool.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권5호
• /
• pp.1388-1399
• /
• 2012

This paper proposes a quality metric based on a No-Reference Bitstream (NR-B) having least computational complexity for the assessment of the human-perceptual quality of H.264 encoded video. The proposed NR-B method performs a modeling of encoding distortion with three bit-stream information (i.e. frame-rate, motion-vector, and quantization-parameter) that can be directly extractable from the encoded bitstream and does not require additional complex processing of final pictures. From performance evaluation using 165 compressed video sequences, the experiment results show that the proposed metric has a higher correlation with subjective quality than is achieved with other comparable methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권8호
• /
• pp.1444-1456
• /
• 2011

This paper presents a low-complexity algorithm for an H.264/AVC encoder. The proposed motion estimation scheme determines the best coding mode for a given macroblock (MB) by finding motion-blurred MBs; identifying, before motion estimation, an early selection of MBs; and hence saving processing time for these MBs. It has been observed that human vision is more sensitive to the movement of well-structured objects than to the movement of randomly structured objects. This study analyzed permissible perceptual distortions and assigned a larger inter-mode value to the regions that are perceptually less sensitive to human vision. Simulation results illustrate that the algorithm can reduce the computational complexity of motion estimation by up to 47.16% while maintaining high compression efficiency.