2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)最新文献

{"title":"Using Color Difference Equations for Calculating Gradient Images","authors":"S. A. Amirshahi, S. H. Amirshahi, Joachim Denzler","doi":"10.1109/SITIS.2017.54","DOIUrl":"https://doi.org/10.1109/SITIS.2017.54","url":null,"abstract":"Recent studies have pointed out to properties such as self-similarity, complexity, and anisotropy as some of the universal characteristics seen in aesthetic paintings. New measures for evaluating the mentioned properties in images were introduced based on the Pyramid Histogram of Gradients (PHOG) features. It is clear that an influential step in calculating PHOG features is how the gradient image is calculated. While such calculations seem straightforward for greyscale images the same could not be said for color images. In this paper, we use color difference equations to propose a new method to calculate the gradient of a color image. Such approach seems a good option to point out the color difference between two patches from a standard observer. Results show that compared to previous methods, the proposed approach gives comparable results. Keeping in mind that color difference equations are specifically proposed to evaluate color difference it seems suitable to use the proposed approach for future color image gradient calculations.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115273907","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":"Segmentation of Synthetic Textures Employing Gabor Filter Magnitude in a Multi-Channeling Environment","authors":"Mudassir Rafi, S. Mukhopadhyay","doi":"10.1109/SITIS.2017.53","DOIUrl":"https://doi.org/10.1109/SITIS.2017.53","url":null,"abstract":"Texture segmentation refers to splitting of an image into homogeneous textured regions. The proposed approach is influenced by the multi-channel filtering theory of the human visual system. Authors have used gabor filter as a means of decomposing the textured mosaics into constituent magnitude response images which are subjected to non-linear function, in addition to this the results thus obtained are used in computing the texture energy as proposed by Jain et al. Subsequently, maximum texture energy is selected pixel wise out of these obtained feature images. The resultant image is normalized and smoothened for unnecessary perturbation and subjected to K-means clustering meanwhile pixel co-ordinates are also used as additional features. The method has been devised, enforced and tested on the benchmark texture mosaics. The empirical data along with performance measures have entrenched the efficacy of the proposed approach.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124241851","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 Large Scale Crowd Density Classification Using Spatio-Temporal Local Binary Pattern","authors":"Sonu Lamba, N. Nain","doi":"10.1109/SITIS.2017.57","DOIUrl":"https://doi.org/10.1109/SITIS.2017.57","url":null,"abstract":"Increasing world wide population is leading to dense crowd gathering at public places. Due to mass gathering at large scale, crowd related disaster has been frequently occurred. In order to prevent crowd calamities, automated crowd scene analysis has been a topic of great interest. Density is the status of crowd which is essential to classify in visual surveillance system primarily for security aspects. Most of the existing techniques work on detection and tracking of individuals. Due to fewer pixels per target, multiple occlusion and perspective effects etc., detection and tracking of individuals is a complex task in dense crowd scenarios. This paper presents a novel strategy for large scale crowd density classification powered by dynamic texture analysis. This approach consists of an interest points detection followed by spatio-temporal feature extraction. A rotation invariant spatio-temporal local binary (RIST-LBP) pattern is proposed to extract dynamic texture of the moving crowd. Further, a multi-class support vector regression is adopted for density classification. We also include a tracking step which tracks the selected interest points over the video frames for crow flow estimation. We validate our proposed approach on three different datasets such as PETS, UCF and CUHK which vary in density ranging from low to very dense. The performance of our proposed approach is compared with most commonly used pixel based statistics. Our approach has the advantage of low computational complexity with high efficiency in real world applications of video surveillance.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124292380","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":"Automatic Extraction of Breast Region in Raw Mammograms Using a Combined Strategy","authors":"C. Feudjio, A. Tiedeu, J. Klein, O. Colot","doi":"10.1109/SITIS.2017.35","DOIUrl":"https://doi.org/10.1109/SITIS.2017.35","url":null,"abstract":"Breast region segmentation is a preliminary task in computer-aided-diagnosis (CAD) systems for breast cancer detection. Its accurate extraction improves CAD performances in terms of false positive and computation time. This paper presents a method for automatic breast region extraction in raw mammograms using a two-step strategy. First, a contrast-correction is applied to uniform gray level in breast region then a clustering algorithm is used to assign pixels to their respective class distribution prior to breast region segmentation. The performances of the proposed method tested on images from MIAS database are 95.6%, 96.0% and 99.8% for accuracy, completeness and correctness respectively.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121839661","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":"Trust Inference Using Implicit Influence for Item Recommendation","authors":"Bithika Pal, M. Jenamani","doi":"10.1109/SITIS.2017.15","DOIUrl":"https://doi.org/10.1109/SITIS.2017.15","url":null,"abstract":"Trust plays a very important role in many existing ecommerce recommendation applications. Social or trust network among users provides an additional information along with the ratings for improving the user reliability on the recommendation. However, in real world, trust data is sparse in nature. So, many algorithms are built for inferring trust. In this paper, we propose a new trust inference method based on the implicit influence information available in the existing trust network. This approach uses the transitivity property of the trust for trust propagation and scale-free complex network property to limit the propagation length in the network. In this regard, we define a new terminology, degree of trustworthiness for a user, which adds the global influence in the inferred trust. This process improves the recommendation accuracy from the existing trust-based recommendation and neighborhood-based collaborative filtering. Due to the availability of users preference from trust network which is absent in rating data, it also alleviates the very well-known cold start users problem of a recommender system. We evaluate the proposed approach on two established real world datasets and report the obtained results.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130579964","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":"First Experiences on an Accurate SPH Method on GPUs","authors":"E. Francomano, A. Galletti, L. Marcellino, M. Paliaga","doi":"10.1109/SITIS.2017.79","DOIUrl":"https://doi.org/10.1109/SITIS.2017.79","url":null,"abstract":"It is well known that the standard formulation of the Smoothed Particle Hydrodynamics is usually poor when scattered data distribution is considered or when the approximation near the boundary occurs. Moreover, the method is computational demanding when a high number of data sites and evaluation points are employed. In this paper an enhanced version of the method is proposed improving the accuracy and the efficiency by using a HPC environment. Our implementation exploits the processing power of GPUs for the basic computational kernel resolution. The performance gain demonstrates the method to be accurate and suitable to deal with large sets of data.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130221326","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":"Performance Comparison of High Efficiency Video Coding (HEVC) with H.264 AVC","authors":"C. Ram, S. Panwar","doi":"10.1109/SITIS.2017.58","DOIUrl":"https://doi.org/10.1109/SITIS.2017.58","url":null,"abstract":"To fulfil the increasing demand for high resolution video, several compression standards have been developed in last two decades. Besides the requirement of real-time processing, the goal of video coding is to ensure good video quality within the provision of transmission and storage. This paper provides thorough study of video coding standards and video quality evaluation techniques. It also includes implementation and in-depth comparison of video coding standards like High Efficiency Video Coding (HEVC) and H.264/MPEG-4 part 10 AVC. The analysis of video coding standards has been carried out by using objective video quality metrics like PSNR, SSIM, MS-SSIM and VQM for three QCIF and three CIF resolution video sequences. Based on the obtained values of these performance metrics and compression factor, it is concluded that High Efficiency Video Coding standard is best suited for low bit rate and low-delay communication applications. The compression performance improved in HEVC relative to existing H.264 AVC standard is around 42% in terms of bit-rate reduction for nearly equivalent objective video quality.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116451541","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 Efficient Hybrid-Clustream Algorithm for Stream Mining","authors":"Ashish Kumar, Ajmer Singh, Rajvir Singh","doi":"10.1109/SITIS.2017.77","DOIUrl":"https://doi.org/10.1109/SITIS.2017.77","url":null,"abstract":"Stream clustering is a standout amongst the most imperative fields in machine learning. Traditional unsupervised clustering tasks have been normally carried out in batch mode where data could be somehow fitted in memory and therefore several passes on the data are allowed. However the new Big Data paradigm has created a new environment where data can be potentially non-finite and arrive continuously. Such streams of data can reach computing systems at high speeds and contain data generation processes which might be non-stationary. For clustering tasks, this implies inconceivability to store all information in memory and obscure number and size of clusters. Noise levels can also be high due to either data generation or transmission. All these factors make traditional clustering methods not suitable to cope. As a consequence, stream clustering has emerged as a field of intense research with the aim of tackling these challenges. Clustream is one of the most advanced state of the art stream clustering algorithm. It normally requires two phases: first online micro-clustering phase, where statistics are gathered describing the incoming data; and a second offline macro-clustering phase, where a conventional non-stream clustering algorithm is executed using the high level statistics resulting from the online step. Because of its design, it requires expert-level parametrization or suffers from low runtime performance or has high sensitivity to noise or degrade considerably in high dimensional spaces because of their offline step. We propose a new stream clustering algorithm, the Clustream-hybrid based on Clustream clustering principles. It extends the same process used in Clustream but uses k-means++ instead of k-means in macro-clustering phase enabling it to accomplish quick runtime calculation while additionally keeping accuracy in high dimensional settings. We integrate it in MOA (Massive Online Analysis) tool. We evaluated the results with nine clustering quality metrics and compared the performance with Clustream for both synthetic and real data sets. The results are encproposedaging, outperforming in most of the cases in quality metrics.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133218038","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":"Overview of Event-Based Collective Knowledge Management in Multimedia Digital Ecosystems","authors":"M. A. Abebe, Joe Tekli, Fekade Getahun Taddesse, R. Chbeir, Gilbert Tekli","doi":"10.1109/SITIS.2017.18","DOIUrl":"https://doi.org/10.1109/SITIS.2017.18","url":null,"abstract":"This paper provides an overview on the problem of event-based collective knowledge management from shared multimedia data. We start by introducing key concepts and constructs related to the problem, including multimedia digital ecosystems, collaborative environments, and collective knowledge management. Then, we utilize a real world motivating scenario to highlight some of the major challenges facing event-based knowledge organization in a multimedia collaborative environment, mainly the need to handle: i) heterogeneous data sources and their unstructured content, ii) large and growing volumes of data published online, iii) non-consistent and ambiguous multimedia data annotations, iv) misleading contents (that are not event related) published by non-experienced users, and vi) multimedia data with missing event-related meta-data. Consequently, we provide a short review of existing methods related to event detection from shared social multimedia data on the Web, contrasting their characteristics with respect to the above challenges, before highlighting potential research directions.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124087153","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":"Mesh Visual Quality Assessment Metrics: A Comparison Study","authors":"Ilyass Abouelaziz, A. Chetouani, M. Hassouni, H. Cherifi","doi":"10.1109/SITIS.2017.55","DOIUrl":"https://doi.org/10.1109/SITIS.2017.55","url":null,"abstract":"3D graphics technologies have known a developed progress in the last years, and several processing operations can be applied on 3D meshes such as watermarking, compression, simplification and so forth. Mesh visual quality assessment becomes an important issue to evaluate the visual appearance of the 3D shape after specific modifications. Several metrics have been proposed in this context, from the classical distance-based metrics to the perceptual-based metrics which include perceptual information about the human visual system. In this paper, we propose to study the performance of several mesh visual quality metrics. First, the comparison is conducted regardless the distortion types neither the areas where these distortions are applied. Then, the degradation applied on the whole objects are considered. Finally, the comparison is conducted considering specific areas (smooth and rough). This study allows us to determine which metric is appropriate for such attribute. Experiments are conducted on the General-Purpose database and show that correlation score may vary by changing the attributes.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127128865","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}