{"title":"Context-based hierarchical saliency detection for mobile hotspot","authors":"Sirimamayvadee Siratanita, K. Chamnongthai","doi":"10.1109/ICDSP.2015.7252040","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7252040","url":null,"abstract":"Embedded hotspot applications, especially advertisements, supporting by 3/4G technology are now rising rapidly. Defining hotspot by finding attention region using saliency is one of interesting. In this paper, we proposed context-based hierarchical saliency feature detection. To construct saliency map, two main features are considered as the context, local and global features. The areas that have distinctive color which obtains high saliency, and blurred areas which give low saliency are considered as local. Moreover, the frequency-occurring information is consider as background which is pressed is considered as global. In experiments, our proposed method comparing with conventional hierarchical saliency framework shows high the recall and F-measure value.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134094998","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":"An adaptive redundant image elimination for Wireless Capsule Endoscopy review based on temporal correlation and color-texture feature similarity","authors":"J. Chen, Y. Wang, Y. Zou","doi":"10.1109/ICDSP.2015.7251973","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251973","url":null,"abstract":"This paper proposes an approach to eliminate redundant images adaptively for Wireless Capsule Endoscopy (WCE) video summarization by considering temporal correlation and feature similarity between adjacent WCE frames. The color and texture features, generated by HSV color histogram model and Gray Level Co-occurrence Matrix, have been taken into account. It is noted that frames from different WCE videos may have different dynamic information ranges. Hence a data-driven threshold termed as W-parametric mean value threshold (W-MVT) is developed to improve robustness of the proposed method. By comparing the color-texture feature similarity of adjacent WCE frames with W-MVT sequentially, the temporal correlated images with certain similarity are grouped into the same clip. Eventually, to consider gradient varying characteristic in one clip, the adaptive K-means clustering algorithm is adopted to keep key frames while remove redundant frames further. Experimental results show that two evaluation indicators-F-measure and compression ratio achieve 81.94% and 80.31%, which validates the effectiveness of the proposed WCE redundant image elimination (WCE-RIE) method.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134369270","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":"Compact and short critical path finite field inverter for cryptographic S-box","authors":"M. Wong, M. Wong, C. Zhang, I. Hijazin","doi":"10.1109/ICDSP.2015.7251981","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251981","url":null,"abstract":"A substitution box (S-box) plays a crucial role in symmetric key cryptography with block ciphers, such as those found in the Data Encryption Standard (DES) and the Advanced Encryption Standard (AES). It serves as the predominant component in most block ciphers, of which the computational complexity impacts the security of the ciphers directly. In essence, a S-box performs a non-linear transformation of the input data block through a finite field inversion, which is incidentally the most expensive operation in digital computation of finite field arithmetic. Consequently, its computational cost will also increase the overall hardware requirements and in turn, decrease the overall performance of the ciphers. With the emergence of Internet of Things (IoT), the need for highly secured yet lightweight implementation protocols is becoming increasingly more observable. In this paper, we propose a new finite field inverter over GF(28) with a significant area cost saving, achieved through direct computation and followed by algebraic factorization and common sub-expression elimination (CSE). The proposed inverter could be deployed into AES cipher on highly area-constrained digital platforms.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130868498","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}
Fraser K. Coutts, D. Gaglione, C. Clemente, Gang Li, I. Proudler, J. Soraghan
{"title":"Label Consistent K-SVD for sparse micro-Doppler classification","authors":"Fraser K. Coutts, D. Gaglione, C. Clemente, Gang Li, I. Proudler, J. Soraghan","doi":"10.1109/ICDSP.2015.7251836","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251836","url":null,"abstract":"Secondary motions of targets observed by radar introduce non-stationary returns containing the so-called micro-Doppler information. This is characterizing information that can be exploited to enhance automatic target recognition systems. In this paper, the challenge of classifying the micro-Doppler return of helicopters is addressed. A robust dictionary learning algorithm, Label Consistent K-SVD (LC-KSVD), is applied to identify effectively and efficiently helicopters. The effectiveness of the proposed algorithm is demonstrated on both synthetic and real radar data.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130969999","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}
M. Islam, Toshihisa Tanaka, Naoki Morikawa, M. I. Molla
{"title":"Frequency recognition for SSVEP-based BCI with data adaptive reference signals","authors":"M. Islam, Toshihisa Tanaka, Naoki Morikawa, M. I. Molla","doi":"10.1109/ICDSP.2015.7251986","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251986","url":null,"abstract":"Steady-state visual evoked potential (SSVEP) is an effective electrophysiological source to implement a brain-computer interface (BCI). In this paper, a novel frequency recognition method is introduced using two levels of reference signals derived from the training set of real world SSVEP signals with canonical correlation analysis (CCA). The first level reference signals are obtained by averaging the training trials of respective stimulus frequency. Standard CCA with thus obtained reference signals is applied to the training trails to measure the dominance of the stimulus frequency component. Several training trials containing more prominent target (stimulus) frequency component are selected as the second level reference signals. Both the obtained reference signals are used with CCA to derive an effective spatial filter for frequency recognition. The experimental results show that the proposed approach significantly improves the recognition accuracy of SSVEP as well as the information transfer rate (ITR) compared to the state-of-the-art recognition methods.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132860819","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":"Automated localization of anatomical landmark points in 3D medical images","authors":"K. Gan","doi":"10.1109/ICDSP.2015.7251847","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251847","url":null,"abstract":"Anatomical landmark point are 3D points in a well-defined anatomical structure in which correspondences between and within the population of the anatomical structure are preserved. Accurate delineation of the landmark points is crucial task for many medical imaging applications. However, in most current clinical applications, the anatomical landmark points are usually manually delineated by experts, which is time-consuming and irreproducible. In this study, an automated method for identification of anatomical landmark points in 3D medical images is presented. A 3D rotationally-invariant image descriptor was adopted to extract image information of pre-defined landmark points in a template image, and then use the information to identify corresponding landmark points in transformed images. This method was implemented and tested on 3D magnetic resonance images of human brain. Experimental results suggested this method can be potentially useful for identification of anatomical landmark points in 3D medical images.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133726012","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":"Distributed beamformer design under mixed SINR balancing and SINR-target-constraints","authors":"Bokamoso Basutli, S. Lambotharan","doi":"10.1109/ICDSP.2015.7251929","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251929","url":null,"abstract":"This work outlines how mixed quality-of-service (QoS) optimization in multi-cell coordinated beamforming (MCBF) can be effectively implemented using distributed algorithms. An alternating direction method of multipliers (ADMM) based algorithm has been adopted to provide distributed beamformer design based on the joint signal-to-interference-plus-noise ratio (SINR) balancing and SINR-target criterion. It is shown through simulations that the proposed algorithm has the ability to converge to optimal centralized solution.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115399888","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":"Beamformer design with sparse filters","authors":"M. Gao, K. Yiu","doi":"10.1109/ICDSP.2015.7252056","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7252056","url":null,"abstract":"In designing broadband beamformers, when the number of microphone increases and the filters are long, the complexity can grow significantly. It is advantageous if many of the filter coefficients are zeroes so that the implementation can be executed with less computation. In this paper, the sparse design of beamformers is studied. We employ the penalty decomposition method to constrain the l0-norm of the filters and investigate the performance of the designed frequency responses. Numerical results show that sparsity of the designed beamformers can be reduced without affecting very much of the performance.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115442028","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":"Improving convergence in finite word length nonlinear active noise control systems","authors":"Raj Shah, Sandeep Reddy, Vinal Patel, N. George","doi":"10.1109/ICDSP.2015.7251936","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7251936","url":null,"abstract":"An attempt has been made in this paper to improve the convergence of functional link artificial neural network (FLANN) based nonlinear active noise control (ANC) systems. This improvement has been achieved by formulating a recursive least square (RLS) training mechanism. However, FLANN-RLS ANC systems are not effective in noise mitigation when implemented in a finite word length scenario. A QR-RLS based training mechanism has been designed to improved convergence even in reduced word length implementations. A simulation study has been carried out to study the effectiveness of the proposed scheme in improving convergence when finite word length implementation is attempted. The proposed FLANN-QRRLS scheme has been shown to improve convergence behaviour in comparison with other schemes compared.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115527376","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 robust PHD filter with deep learning updating for multiple human tracking","authors":"P. Feng, Wenwu Wang, S. M. Naqvi, J. Chambers","doi":"10.1109/ICDSP.2015.7252076","DOIUrl":"https://doi.org/10.1109/ICDSP.2015.7252076","url":null,"abstract":"We propose a novel robust probability hypothesis density (PHD) filter for multiple target tracking in an enclosed environment, where a deep learning method is used in the update step for combining different human features to mitigate the effect of measurement noise on the calculation of particle weights. Deep belief networks (DBNs) are trained based on both colour and oriented gradient (HOG) histogram features and then used to mitigate the measurement noise from the particle selection and PHD update step, thereby improving the tracking performance. To evaluate the proposed PHD filter, two sequences with 383 frames from the CAVIAR dataset are employed and both the optimal subpattern assignment (OSPA) and mean of error from each target method are used as objective measures. The results show that the proposed robust PHD filter outperforms the traditional PHD filter.","PeriodicalId":216293,"journal":{"name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114900274","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}