Most learning-based super-resolution algorithms neglect the illumination problem such as shadows and illumination direction changes. In this paper we propose a logarithmic-wavelet transform (Log-WT) based method to combine super-resolution and shadow removing into a single operation. First intrinsic, illumination invariant features of the image are extracted by exploiting logarithmic-wavelet transform. Then an initial estimation of high resolution image is obtained based on the assumption that small patches in low resolution space and patches in high resolution space share the similar local manifold structure. Finally the target high resolution image is reconstructed by applying the reconstruction constraints in pixel domain. Experimental results demonstrate that the proposed method simultaneously achieves singleimage super-resolution and image enhancement especially shadow removing.
{"title":"A Novel Log-WT Based Super-Resolution Algorithm","authors":"Jianping Qiao, Ju Liu","doi":"10.1109/IIH-MSP.2006.30","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.30","url":null,"abstract":"Most learning-based super-resolution algorithms neglect the illumination problem such as shadows and illumination direction changes. In this paper we propose a logarithmic-wavelet transform (Log-WT) based method to combine super-resolution and shadow removing into a single operation. First intrinsic, illumination invariant features of the image are extracted by exploiting logarithmic-wavelet transform. Then an initial estimation of high resolution image is obtained based on the assumption that small patches in low resolution space and patches in high resolution space share the similar local manifold structure. Finally the target high resolution image is reconstructed by applying the reconstruction constraints in pixel domain. Experimental results demonstrate that the proposed method simultaneously achieves singleimage super-resolution and image enhancement especially shadow removing.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132674433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-12-18DOI: 10.1109/IIH-MSP.2006.151
Lei Zhang, Qiuguang Wang, J. Qi
This paper introduces a kind of cancer cells in pleural fluid microscopic images processing and fuzzy recognizing method. We propose a method, which firstly segments the image using the OTSU thresholding method and fuzzy edge detection, then extracts 7 measurement parameters i.e. the area rate of the karyon and cytoplasm, the optic density, the shape factor and else, finally uses fuzzy pattern recognition which is based on establishing 6 membership functions and 4 normative modes to recognize the cancer cells. Experiments show that this system provides valuable suggestions to the diagnosis of cancer.
{"title":"Research Based on Fuzzy Algorithm of Cancer Cells in Pleural Fluid Microscopic Images Recognition","authors":"Lei Zhang, Qiuguang Wang, J. Qi","doi":"10.1109/IIH-MSP.2006.151","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.151","url":null,"abstract":"This paper introduces a kind of cancer cells in pleural fluid microscopic images processing and fuzzy recognizing method. We propose a method, which firstly segments the image using the OTSU thresholding method and fuzzy edge detection, then extracts 7 measurement parameters i.e. the area rate of the karyon and cytoplasm, the optic density, the shape factor and else, finally uses fuzzy pattern recognition which is based on establishing 6 membership functions and 4 normative modes to recognize the cancer cells. Experiments show that this system provides valuable suggestions to the diagnosis of cancer.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130316793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a novel image-based facial expression recognition method called "expression transition" to identify six kinds of facial expressions (anger, fear, happiness, neutral, sadness, and surprise) at low-resolution images. Two approaches: direct mapping and singular value decomposition (SVD) are applied to calculate the expression transition matrices. The transformed images with a set of expression transition matrices are compared to identify the facial expressions. The experimental results show that the proposed facial expression recognition system can recognize 120 test images in the Chon-Kanade facial expression database with high accuracy and efficiency.
{"title":"A Fast Facial Expression Recognition Method at Low-Resolution Images","authors":"C. Lien, Yang-Kai Chang, Chih-Chiang Tien","doi":"10.1109/IIH-MSP.2006.10","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.10","url":null,"abstract":"In this paper, we propose a novel image-based facial expression recognition method called \"expression transition\" to identify six kinds of facial expressions (anger, fear, happiness, neutral, sadness, and surprise) at low-resolution images. Two approaches: direct mapping and singular value decomposition (SVD) are applied to calculate the expression transition matrices. The transformed images with a set of expression transition matrices are compared to identify the facial expressions. The experimental results show that the proposed facial expression recognition system can recognize 120 test images in the Chon-Kanade facial expression database with high accuracy and efficiency.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132832019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In a digital TV system, the Conditional Access (CA) system is essential to protect programs from unauthorized access. However, the encryption technique alone is not sufficient to protect or control the use of contents after decryption. To provide flexible and complete Digital Rights Management (DRM) protection on the Digital Video Broadcasting (DVB) programs, we propose a method that adapts the MPEG- 21 REL technology and integrates it into a DVB-T system. By extending the Service Information (SI) section of a DVB stream to include an REL license, the transmitted content can be conveniently consumed and legally protected. Our design is verified by an experimental hardware system. The results show that the proposed method can provide both the conditional access functionality and the usage control of broadcasted contents.
{"title":"A Digital Content Protection Scheme Using MPEG-21 REL with Applications to DVB Systems","authors":"Ying-Tzu Shih, Feng-Cheng Chang, H. Hang","doi":"10.1109/IIH-MSP.2006.6","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.6","url":null,"abstract":"In a digital TV system, the Conditional Access (CA) system is essential to protect programs from unauthorized access. However, the encryption technique alone is not sufficient to protect or control the use of contents after decryption. To provide flexible and complete Digital Rights Management (DRM) protection on the Digital Video Broadcasting (DVB) programs, we propose a method that adapts the MPEG- 21 REL technology and integrates it into a DVB-T system. By extending the Service Information (SI) section of a DVB stream to include an REL license, the transmitted content can be conveniently consumed and legally protected. Our design is verified by an experimental hardware system. The results show that the proposed method can provide both the conditional access functionality and the usage control of broadcasted contents.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128221539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-12-18DOI: 10.1109/IIH-MSP.2006.141
Zhenyu Wu, Hongyang Yu, B. Tang, H. Hu
The latest Chinese video coding standard AVS-P2 has been recently approved and is going to be adopted for numerous applications including HD-DVD and satellite broadcast. To allow interconnectivity between different video coding standards, transcoding will be a key factor. This paper assesses the performance of existing requantization techniques developed when applied to transcoding from MPEG-2 to AVS-P2 together with a new technique. The proposed transcoding algorithm is based on an improved mixed re-quantization technique, which gives a good compromise between complexity and quality.
{"title":"Performance Evaluation of Transcoding Algorithms for MPEG-2 to AVS-P2","authors":"Zhenyu Wu, Hongyang Yu, B. Tang, H. Hu","doi":"10.1109/IIH-MSP.2006.141","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.141","url":null,"abstract":"The latest Chinese video coding standard AVS-P2 has been recently approved and is going to be adopted for numerous applications including HD-DVD and satellite broadcast. To allow interconnectivity between different video coding standards, transcoding will be a key factor. This paper assesses the performance of existing requantization techniques developed when applied to transcoding from MPEG-2 to AVS-P2 together with a new technique. The proposed transcoding algorithm is based on an improved mixed re-quantization technique, which gives a good compromise between complexity and quality.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134347782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-12-18DOI: 10.1109/IIH-MSP.2006.144
Ruogu Yang, Gang Feng, Donghai Li
Reducing bus power consumption has become one of key issues for low power multimedia SoC design. The power which dissipated on interconnected bus includes the self transition power consumption and the coupled transition power consumption between every two signal lines. This paper, firstly propose an on-chip bus power consumption model. Then a heuristic algorithm is proposed to determine a physical order of signal lines in bus to minimize the power consumption on the interconnected bus. Experimental results show that the proposed heuristic algorithm is effective.
{"title":"Power Optimization for Bus on Multimedia SoC","authors":"Ruogu Yang, Gang Feng, Donghai Li","doi":"10.1109/IIH-MSP.2006.144","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.144","url":null,"abstract":"Reducing bus power consumption has become one of key issues for low power multimedia SoC design. The power which dissipated on interconnected bus includes the self transition power consumption and the coupled transition power consumption between every two signal lines. This paper, firstly propose an on-chip bus power consumption model. Then a heuristic algorithm is proposed to determine a physical order of signal lines in bus to minimize the power consumption on the interconnected bus. Experimental results show that the proposed heuristic algorithm is effective.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124116852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a novel SVD-based method is developed to classify face images. The experimental results show that the novel method outperforms the existing SVD-based face recognition methods. In addition, we investigate the performances on face recognition of singular values, left and right singular vectors generated from SVD and assess the existing SVD-based face recognition methods. It appears that by compared with singular values and singular vectors, SVD-based reconstruction images are more useful in classifying face images. In practice, through the SVD-based image reconstruction process, we may weaken the side effects on face classification of varying imaging conditions and facial expressions.
{"title":"Comparison Study on SVD-Based Face Classification","authors":"Yong Xu, Ying-nan Zhao","doi":"10.1109/IIH-MSP.2006.75","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.75","url":null,"abstract":"In this paper, a novel SVD-based method is developed to classify face images. The experimental results show that the novel method outperforms the existing SVD-based face recognition methods. In addition, we investigate the performances on face recognition of singular values, left and right singular vectors generated from SVD and assess the existing SVD-based face recognition methods. It appears that by compared with singular values and singular vectors, SVD-based reconstruction images are more useful in classifying face images. In practice, through the SVD-based image reconstruction process, we may weaken the side effects on face classification of varying imaging conditions and facial expressions.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127974637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For instruction decompression, techniques such as single buffering, double buffering and pipelining have been proposed. However, due to jumping penalty, these techniques incur more delays in pipeline or system has to be stopped to refill the cache buffers. A Pipeline with Back-up for Flushing (PBF) technique has been developed that incurs no delay and without stopping due to jumping. However, the first instruction of each basic block should not be compressed and be put in another ROM, and thus the compression ratio should be sacrificed. This paper improves the PBF technique such that a single program ROM needed only. The simulation results for several benchmarks show that the average compression ratio is decreased about 11%, and the hardware cost deceased about 8%.
{"title":"A Single-Stream Pipelined Instruction Decompression System for Embedded Microprocessors","authors":"Y. Jeang, T. Wey, Hung-Yu Wang, Chih-Chung Tai","doi":"10.1109/IIH-MSP.2006.40","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.40","url":null,"abstract":"For instruction decompression, techniques such as single buffering, double buffering and pipelining have been proposed. However, due to jumping penalty, these techniques incur more delays in pipeline or system has to be stopped to refill the cache buffers. A Pipeline with Back-up for Flushing (PBF) technique has been developed that incurs no delay and without stopping due to jumping. However, the first instruction of each basic block should not be compressed and be put in another ROM, and thus the compression ratio should be sacrificed. This paper improves the PBF technique such that a single program ROM needed only. The simulation results for several benchmarks show that the average compression ratio is decreased about 11%, and the hardware cost deceased about 8%.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128001536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-12-18DOI: 10.1109/IIH-MSP.2006.169
Ku-Lan Kao, C. Ke, C. Shieh
This paper evaluates the video transmission performance of three well-known ad-hoc routing protocols. Due to high mobility and rapid movement characteristics, video transmission over ad-hoc networks is becoming more difficult than simple data transmission. Consequently, finding an efficient way for multimedia communication is becoming an important issue nowadays. We make a complete comparison between the two prominent on-demand reactive routing protocols, DSR and AODV, and the proactive DSDV routing protocol. Our improved simulation tool-set is used with NS-2 and myEvalvid-NT in this simulation, and we adopted the PSNR performance evaluation metric. Results indicate that DSDV is much worse than the other protocols for video transmission, and AODV is the best routing protocol in our simulation.
{"title":"Video Transmission Performance Evaluation of Ad Hoc Routing Protocols","authors":"Ku-Lan Kao, C. Ke, C. Shieh","doi":"10.1109/IIH-MSP.2006.169","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.169","url":null,"abstract":"This paper evaluates the video transmission performance of three well-known ad-hoc routing protocols. Due to high mobility and rapid movement characteristics, video transmission over ad-hoc networks is becoming more difficult than simple data transmission. Consequently, finding an efficient way for multimedia communication is becoming an important issue nowadays. We make a complete comparison between the two prominent on-demand reactive routing protocols, DSR and AODV, and the proactive DSDV routing protocol. Our improved simulation tool-set is used with NS-2 and myEvalvid-NT in this simulation, and we adopted the PSNR performance evaluation metric. Results indicate that DSDV is much worse than the other protocols for video transmission, and AODV is the best routing protocol in our simulation.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121199471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Signal processing is the critical equipment and the guarantee of technology to media gateway, so it is very important to evaluate the signal processing effect of media gateway. In this paper the Correlation Criterion which is based correlation operator on theory and uses correlation coefficient as the index of evaluation is put forward. In this method, the select of standard test signal is the key. The paper introduces the dependence and reason of choosing standard test signal. The cross correlation criterion is a normalized, quantitative, time domain evaluation method.
{"title":"Evaluation of Signal Processing Effect in Media Gateway Based on Cross Correlation","authors":"Hao Wang, Yanying Wang, Jikun Guo, D. Gao","doi":"10.1109/IIH-MSP.2006.96","DOIUrl":"https://doi.org/10.1109/IIH-MSP.2006.96","url":null,"abstract":"Signal processing is the critical equipment and the guarantee of technology to media gateway, so it is very important to evaluate the signal processing effect of media gateway. In this paper the Correlation Criterion which is based correlation operator on theory and uses correlation coefficient as the index of evaluation is put forward. In this method, the select of standard test signal is the key. The paper introduces the dependence and reason of choosing standard test signal. The cross correlation criterion is a normalized, quantitative, time domain evaluation method.","PeriodicalId":272579,"journal":{"name":"2006 International Conference on Intelligent Information Hiding and Multimedia","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129138295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：