{"title":"Design of video transmission card based on PCI bus interface technology","authors":"Huaimin Sun, X. Ye","doi":"10.1109/ICALIP.2008.4590041","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590041","url":null,"abstract":"In this paper, the characteristics of CY7C09449 which is a dedicated interface chip for PCI bus are introduced. A design methodology of video data transmission card based on CY7C09449 and FPGA is proposed. Furthermore the timing, the hardware diagram and the program flow of this design are also presented. The result by running in actual system shows that the performance of design is up to the original target, and the card achieves accurate transmission of MPEG-1 video data. The design is also characterized by simple structure and low cost, and it can also be applied in other data transmission and data acquisition through modifying software.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132784969","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}
{"title":"Web pages tamper-proof method using virus-based watermarking","authors":"C. Jin, Hongfeng Xu, Xiao-Liang Zhang","doi":"10.1109/ICALIP.2008.4590184","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590184","url":null,"abstract":"A novel tamper-proof model of Web pages using virus-based watermarking is proposed in this paper. The model provides a good security and accuracy about judging the situation of Web page tampering. The classifying theory based on virus is applied when watermark embedded and extracted. The proposed scheme is applied in all kinds of HTML or XML files, not just for English letters but also for the rest of characters. More importantly, it can be restored to the original file completely when the watermark is extracted. Therefore, the proposed scheme, associated with 3rd generation technology of tamper-proof for web pages, exhibits a good property of real-time performance and security. Experiment results show that it overwhelms existing schemes of tamper-proof in that it does not increase the file size and it does not expend great computing time such as cryptography.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430161","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}
{"title":"Capacity analysis of steganography based on the digital images under the constraints of security","authors":"Cuiling Jiang, Jiajun Lin, Yilin Pang","doi":"10.1109/ICALIP.2008.4590288","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590288","url":null,"abstract":"This paper presents the recent research of capacity analysis based on the digital images. It emphasizes the capacity analysis of steganography in the security restrictions for different models of stego-channel. Finally, we classify the capacity analysis results, discuss the deficiencies of the existing methods and provide some next research aspects.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133131579","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}
{"title":"A hybridized clustering approach using particle swarm optimization for image segmentation","authors":"Wei Chen, Kang-ling Fang","doi":"10.1109/ICALIP.2008.4590208","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590208","url":null,"abstract":"Fuzzy C-means algorithm (FCM) is the most widely used fuzzy partitioning method for data cluster. The K-means algorithm implements fast, however the result is less accurate clustering. In this paper describes a hybridized clustering approach for image segmentation using particle swarm optimization to improve the classical FCM algorithm. The experimental results show that the hybridized clustering approach can provide better effectiveness on experiments of image segmentation.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133888066","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}
{"title":"Multi-inconsecutive-frames moving average for the frequency-domain blind source separation of convolutive mixtures","authors":"Wang Chao, Fang Yong","doi":"10.1109/ICALIP.2008.4590201","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590201","url":null,"abstract":"In frequency-domain blind source separation of convolutive mixtures, the DFT coefficients of mixture frame are employed to estimate the mixing matrix on each frequency bin. Based on the relation between partial convolution and circular convolution, we propose a multi-inconsecutive-frames moving average method to produce new frame for DFT to substitute the mixture frame. Its DFT coefficients could estimate the mixing matrix on each frequency bin more precisely than traditional way, which improves the separation performance. Simulation results verify the validity of proposed multi-inconsecutive-frames moving average method for frequency domain CMBSS.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132013464","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}
{"title":"Adaptive FMO selection strategy for error resilient H.264 coding","authors":"Hao Chen, Zhen Han, R. Hu, Ruolin Ruan","doi":"10.1109/ICALIP.2008.4589969","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4589969","url":null,"abstract":"Flexible macroblock ordering (FMO) is one of the effective error resilient tools in H.264/AVC video coding standard. Nevertheless the issue of how to suitably arrange the macroblocks in suitable FMO mapping type for different video applications is yet to be clarified and investigated. In this paper, we are analyzing the tradeoff and effectiveness of the six fixed FMO types, and based these six fixed FMO types, using the joint source-channel rate distortion optimization (RDO) principle to propose an adaptive FMO type selection strategy for different video scenes and applications. The experiment results shows that our method has more compatibility and flexibility than the six fixed FMO types, and better error resilience than most of them.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132368963","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}
{"title":"On the relationship of MDCT transform kernels in Dolby AC-3","authors":"Zhang Tao, Jialin He, Cunbiao Chen","doi":"10.1109/ICALIP.2008.4590063","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590063","url":null,"abstract":"The modified discrete cosine transform (MDCT) is widely used in perceptual audio coding algorithm with various types, especially in Dolby AC-3 which has three types for a long transform and two short transforms respectively. A lot of research has been done to pursue fast algorithms of MDCT and efficient ways of implementation as well. In this paper, a developing roadmap of the fast algorithms of MDCT is firstly presented, followed by the analysis to prove that the three types of MDCT can be unified into any one type to simplify the MDCT computation structure in the AC-3 encoder. In the end, the computation complexity of three unifications is compared. The ones using short transform cores have a tiny advantage in the amount of addition. However, this advantage would be darkened due to more circular shifting which the unifications call for.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133226054","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}
{"title":"Using SIMD technology to speed up likelihood computation in HMM-based speech recognition systems","authors":"Jianlin Ou, Jun Cai, Qian Lin","doi":"10.1109/ICALIP.2008.4590086","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590086","url":null,"abstract":"Most state-of-the-art LVCSR systems are based on continuous density HMMs, which are typically implemented using Gaussian mixture distributions. Such statistical modeling systems usually operate slower than real-time, largely because of the heavy computational overhead of the likelihood computation. The objective of our research is to investigate application of modern SIMD technology to speed up the likelihood computation without degrading the recognition accuracy. In this paper, the likelihood computation of continuous density HMMs is analyzed to show that the conventional way of sequential computing is time-consuming and the likelihood computation itself can be implemented in parallel. A SIMD-based algorithm which can carry out parallel likelihood computation is presented in this paper. Likelihood computation modules in HTK3.4 toolkit have been modified with SIMD instructions to implement this algorithm. Experiments on TIMIT and WSJ0 corpora show that the SIMD-based data-level parallelism can significantly reduce the time overhead for likelihood computation.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133420418","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}
{"title":"A review of Traffic Visual Tracking technology","authors":"Meng Liu, Chengdong Wu, Yunzhou Zhang","doi":"10.1109/ICALIP.2008.4590198","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590198","url":null,"abstract":"Traffic visual tracking technology is currently one of the most active research topics in the domain of visual tracking. Normally, motion object segmentation, object classification, object tracking and behavior understanding are involved in traffic visual tracking technology. This paper firstly reviews the research contents as well as states of the traffic visual tracking technology from the four aspects. Research achievements on motion object segmentation and object tracking is emphatically introduced. Performances of each implementation algorithm are analyzed and the advantages and disadvantages are pointed out. At last the problems of current traffic visual tracking technology that should be urgently solved are discussed and the future developments in this field are provided.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132640259","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}
Guanglu Sun, Bingquan Liu, Xiaolong Wang, Yuanchao Liu
{"title":"Chinese chunking and its application on similarity computation","authors":"Guanglu Sun, Bingquan Liu, Xiaolong Wang, Yuanchao Liu","doi":"10.1109/ICALIP.2008.4590216","DOIUrl":"https://doi.org/10.1109/ICALIP.2008.4590216","url":null,"abstract":"This paper presents a new Chinese chunking algorithm based on conditional random fields. Conditional random fields overcome the label bias problem, model the labeling sequence and utilize many types of features. Furthermore, an algorithm of chunk similarity computation is proposed based on the systematic similarity method and semantic dictionary. The experimental results show that this approach achieves impressive accuracy in terms of the F-score: 92.00%. And the similarity computation algorithm performs well.","PeriodicalId":175885,"journal":{"name":"2008 International Conference on Audio, Language and Image Processing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116676057","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}