Pub Date : 2016-07-01DOI: 10.1109/CSIT.2016.7549479
A. Cheddad
Historical documents are essentially formed of handwritten texts that exhibit a variety of perceptual environment complexities. The cursive and connected nature of text lines on one hand and the presence of artefacts and noise on the other hand hinder achieving plausible results using current image processing algorithm. In this paper, we present a new algorithm which we termed QTE (Query by Text Example) that allows for training-free and binarisation-free pattern spotting in scanned handwritten historical documents. Our algorithm gives promising results on a subset of our database revealing ~83% success rate in locating word patterns supplied by the user.
历史文献基本上是由手写文本构成的,这些文本表现出各种感知环境的复杂性。一方面,文本行的草书和连接性质,另一方面,人工制品和噪声的存在阻碍了使用当前的图像处理算法获得可信的结果。在本文中,我们提出了一种新的算法,我们称之为QTE (Query by Text Example),它允许在扫描的手写历史文档中进行无训练和无二值化的模式识别。我们的算法在数据库的一个子集上给出了有希望的结果,在定位用户提供的单词模式方面成功率约为83%。
{"title":"Towards Query By Text Example for pattern spotting in historical documents","authors":"A. Cheddad","doi":"10.1109/CSIT.2016.7549479","DOIUrl":"https://doi.org/10.1109/CSIT.2016.7549479","url":null,"abstract":"Historical documents are essentially formed of handwritten texts that exhibit a variety of perceptual environment complexities. The cursive and connected nature of text lines on one hand and the presence of artefacts and noise on the other hand hinder achieving plausible results using current image processing algorithm. In this paper, we present a new algorithm which we termed QTE (Query by Text Example) that allows for training-free and binarisation-free pattern spotting in scanned handwritten historical documents. Our algorithm gives promising results on a subset of our database revealing ~83% success rate in locating word patterns supplied by the user.","PeriodicalId":210905,"journal":{"name":"2016 7th International Conference on Computer Science and Information Technology (CSIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128320236","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 : 2016-07-01DOI: 10.1109/CSIT.2016.7549481
Sara Tedmori, Rashed Al-Lahaseh
Web 2.0 has witnessed increased focus on more user generated content and eventually on data analyzed and queried in meaningful ways. Selfies, a new form of user-generated content, have become an important part of the visual communication in social media. A large portion of images posted on some social networks are selfies. Behind each of these selfies lie the sentiments of the person in the photo posted. The authors of this paper believe that adding quantified sentiment indicators to these selfies can be a valuable addition to not only the social network users but also to the many networks already in existence. Motivated by the idea, the authors propose an addition to social networks that automatically captures the sentiments expressed in selfies as they are being posted. The captured sentiments are then presented along with the selfies' on the users' timeline. In this research, the authors propose Momented, a selfie social network. Momented works by tracking the sentiments expressed in the selfies posted on the Momented social network. Based on the emotions tracked from a particular selfie, the system automatically generates sentiment bearing hashtags. Tthe selfie along with the automatically generated hash tags are posted on the user's dashboard timeline.
Web 2.0见证了更多地关注用户生成的内容,并最终关注以有意义的方式分析和查询数据。自拍作为一种用户生成内容的新形式,已经成为社交媒体视觉传播的重要组成部分。在一些社交网络上发布的照片中,有很大一部分是自拍照。在每一张自拍的背后都隐藏着照片中的人的情感。这篇论文的作者认为,在这些自拍中添加量化的情绪指标,不仅对社交网络用户来说是一个有价值的补充,对许多已经存在的网络来说也是如此。受这一想法的启发,作者提出在社交网络上增加一项功能,可以在自拍发布时自动捕捉其中表达的情绪。然后,捕捉到的情绪会和自拍一起出现在用户的时间轴上。在这项研究中,作者提出了一个自拍社交网络moments。“瞬间”通过追踪社交网络“瞬间”上发布的自拍所表达的情感来工作。根据从一张特定的自拍中追踪到的情绪,该系统会自动生成带有情绪的标签。自拍和自动生成的散列标签一起发布在用户的仪表板时间轴上。
{"title":"Towards a selfie social network with automatically generated sentiment-bearing hashtags","authors":"Sara Tedmori, Rashed Al-Lahaseh","doi":"10.1109/CSIT.2016.7549481","DOIUrl":"https://doi.org/10.1109/CSIT.2016.7549481","url":null,"abstract":"Web 2.0 has witnessed increased focus on more user generated content and eventually on data analyzed and queried in meaningful ways. Selfies, a new form of user-generated content, have become an important part of the visual communication in social media. A large portion of images posted on some social networks are selfies. Behind each of these selfies lie the sentiments of the person in the photo posted. The authors of this paper believe that adding quantified sentiment indicators to these selfies can be a valuable addition to not only the social network users but also to the many networks already in existence. Motivated by the idea, the authors propose an addition to social networks that automatically captures the sentiments expressed in selfies as they are being posted. The captured sentiments are then presented along with the selfies' on the users' timeline. In this research, the authors propose Momented, a selfie social network. Momented works by tracking the sentiments expressed in the selfies posted on the Momented social network. Based on the emotions tracked from a particular selfie, the system automatically generates sentiment bearing hashtags. Tthe selfie along with the automatically generated hash tags are posted on the user's dashboard timeline.","PeriodicalId":210905,"journal":{"name":"2016 7th International Conference on Computer Science and Information Technology (CSIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114228363","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 : 2016-07-01DOI: 10.1109/CSIT.2016.7549469
Mohamed Atibi, Issam Atouf, M. Boussaa, A. Bennis
Currently, in the field of road safety, research is moving towards the use of electronic driving support systems that are capable of simulating human perception. These systems have more and more facilities, flexibilities and human development, to respond effectively against the delicate situations in the real world, which require the development of more efficient, fast, accurate signal processing and decision algorithms. This paper presents a classification of intelligent real-time roadway into 4 classes: asphalt, gravel, snow-covered road, stone road. This system combines between a descriptor, the acoustic signal produced by the tire-road friction, based either on the Mel Frequency Cepstrum Coefficient algorithm or on the Discrete Wavelet Transform algorithm and a classifier of artificial neuron like Multilayer Perception network. This paper also presents a comparison of results obtained in terms of execution time and in terms of the correct classification for the 2 systems: a system consisting of Mel Frequency Cepstrum Coefficient descriptor and an artificial neuron network classifier Multilayer Perception type and another system composed of a Discrete Wavelet Transform descriptor and the same type of classifier.
{"title":"Comparison between the MFCC and DWT applied to the roadway classification","authors":"Mohamed Atibi, Issam Atouf, M. Boussaa, A. Bennis","doi":"10.1109/CSIT.2016.7549469","DOIUrl":"https://doi.org/10.1109/CSIT.2016.7549469","url":null,"abstract":"Currently, in the field of road safety, research is moving towards the use of electronic driving support systems that are capable of simulating human perception. These systems have more and more facilities, flexibilities and human development, to respond effectively against the delicate situations in the real world, which require the development of more efficient, fast, accurate signal processing and decision algorithms. This paper presents a classification of intelligent real-time roadway into 4 classes: asphalt, gravel, snow-covered road, stone road. This system combines between a descriptor, the acoustic signal produced by the tire-road friction, based either on the Mel Frequency Cepstrum Coefficient algorithm or on the Discrete Wavelet Transform algorithm and a classifier of artificial neuron like Multilayer Perception network. This paper also presents a comparison of results obtained in terms of execution time and in terms of the correct classification for the 2 systems: a system consisting of Mel Frequency Cepstrum Coefficient descriptor and an artificial neuron network classifier Multilayer Perception type and another system composed of a Discrete Wavelet Transform descriptor and the same type of classifier.","PeriodicalId":210905,"journal":{"name":"2016 7th International Conference on Computer Science and Information Technology (CSIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132628532","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 : 2016-07-01DOI: 10.1109/CSIT.2016.7549472
A. Baqais, M. Amro, M. Alshayeb
It is assumed that stability and maintainability are relating to each other. We attempt to verify and validate this assumption in object-oriented paradigm. Two candidate metrics were chosen, one for stability and one for maintainability. CSM is used in stability due to its high accuracy and wide coverage. MI was chosen for maintainability due to its clarity, ease of use and solely based on source code. The experiment shows that there is fluctuation in the correlation behavior between these two metrics and a direct causality cannot be concluded. However, in-depth analysis and through tracing of all the steps of these experiments reveal promising results. These observations can aid researchers to measure the correlation between CSM and MI correctly.
{"title":"Analysis of the correlation between class stability and maintainability","authors":"A. Baqais, M. Amro, M. Alshayeb","doi":"10.1109/CSIT.2016.7549472","DOIUrl":"https://doi.org/10.1109/CSIT.2016.7549472","url":null,"abstract":"It is assumed that stability and maintainability are relating to each other. We attempt to verify and validate this assumption in object-oriented paradigm. Two candidate metrics were chosen, one for stability and one for maintainability. CSM is used in stability due to its high accuracy and wide coverage. MI was chosen for maintainability due to its clarity, ease of use and solely based on source code. The experiment shows that there is fluctuation in the correlation behavior between these two metrics and a direct causality cannot be concluded. However, in-depth analysis and through tracing of all the steps of these experiments reveal promising results. These observations can aid researchers to measure the correlation between CSM and MI correctly.","PeriodicalId":210905,"journal":{"name":"2016 7th International Conference on Computer Science and Information Technology (CSIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133515110","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}