Pub Date : 2018-05-03DOI: 10.1109/CATA.2018.8398648
Jing Jiang, Chunhui Wang, Yu Tian, Shaoyao Zhang, Yan Zhao
Information mining from large databases has become an important research topic for researchers in computer science and information technology. Data mining has been attractive to many researchers in different fields. Among these fields, urban activity summarization aims at modeling people's typical activities at different locations and time in a city. With the ever-increasing urbanization process, urban activity summarization is widely recognized as a crucial socioeconomic task. Previously, it was difficult to be done due to the lack of real-life geo-tagged social media (GTSM) data. In recent years, with the development of social media, such as tweeter and Weibo (widely used in China and similar with tweeter), there are sufficient acceptable data for solving this task. There are some progress made on the studies of geographical topics based on GTSM data, but their high computational costs and strong distributional assumptions prevent the release of GTSM data energy. In order to solve this problem, we propose a model of urban activity summarization. This model is based on the method of kernel density estimation to find out the spatiotemporal hot spots of people's activities and maximize the scarcity of GTSM data. Not only that, we have greatly reduced the time complexity by subdividing the space. Finally, we evaluate the validity of the model using the Weibo data, by comparing the results of the model prediction and the actual results, and give an answer to the proposed activities under a given time and place, as well as the recommendation of a given activity.
{"title":"Urban activity summarization with geo-tagged social media data","authors":"Jing Jiang, Chunhui Wang, Yu Tian, Shaoyao Zhang, Yan Zhao","doi":"10.1109/CATA.2018.8398648","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398648","url":null,"abstract":"Information mining from large databases has become an important research topic for researchers in computer science and information technology. Data mining has been attractive to many researchers in different fields. Among these fields, urban activity summarization aims at modeling people's typical activities at different locations and time in a city. With the ever-increasing urbanization process, urban activity summarization is widely recognized as a crucial socioeconomic task. Previously, it was difficult to be done due to the lack of real-life geo-tagged social media (GTSM) data. In recent years, with the development of social media, such as tweeter and Weibo (widely used in China and similar with tweeter), there are sufficient acceptable data for solving this task. There are some progress made on the studies of geographical topics based on GTSM data, but their high computational costs and strong distributional assumptions prevent the release of GTSM data energy. In order to solve this problem, we propose a model of urban activity summarization. This model is based on the method of kernel density estimation to find out the spatiotemporal hot spots of people's activities and maximize the scarcity of GTSM data. Not only that, we have greatly reduced the time complexity by subdividing the space. Finally, we evaluate the validity of the model using the Weibo data, by comparing the results of the model prediction and the actual results, and give an answer to the proposed activities under a given time and place, as well as the recommendation of a given activity.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125067037","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398675
F. Mohamad, M. Iqtait, F. Alsuhimat
Human age recognition becomes increasingly important due to its beneficial employments alongside security and computer applications. Age prediction from face picture has a lot of challenges, such as insufficiency of training data and uncontrollable situation. In this research, we address these critical issues by introducing an improved age prediction algorithm using Active Appearance Models (AAM) and three classifiers, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Support Vector Regression (SVR) to improve the precision of age prediction based on the present methods. In this algorithm, the traits of the facial pictures are explicated as traits vectors by AAM model, and the classifiers are utilized to estimate the age. We were able to recognize that the accuracy of SVR algorithm is better than the accuracy of KNN and SVM classifiers.
{"title":"Age prediction on face features via multiple classifiers","authors":"F. Mohamad, M. Iqtait, F. Alsuhimat","doi":"10.1109/CATA.2018.8398675","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398675","url":null,"abstract":"Human age recognition becomes increasingly important due to its beneficial employments alongside security and computer applications. Age prediction from face picture has a lot of challenges, such as insufficiency of training data and uncontrollable situation. In this research, we address these critical issues by introducing an improved age prediction algorithm using Active Appearance Models (AAM) and three classifiers, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Support Vector Regression (SVR) to improve the precision of age prediction based on the present methods. In this algorithm, the traits of the facial pictures are explicated as traits vectors by AAM model, and the classifiers are utilized to estimate the age. We were able to recognize that the accuracy of SVR algorithm is better than the accuracy of KNN and SVM classifiers.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116661112","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398669
Wedad Ahmed Al-Dhuraibi, J. Ali
In our day to day life, predictability of gold's price is significant in many domains such as economics, trading, investment, and financial and political environments. Better investment decision could be made when gold price values are accurately predicted. The main objective of this research is to forecasts whether the price of gold will rise or decline in the near future. Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Linear Regression are all different classification algorithms that have been used in this paper to predict the gold price movement direction. The performance of each of these algorithms has been investigated while using the Rapidminer software.
{"title":"Using classification techniques to predict gold price movement","authors":"Wedad Ahmed Al-Dhuraibi, J. Ali","doi":"10.1109/CATA.2018.8398669","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398669","url":null,"abstract":"In our day to day life, predictability of gold's price is significant in many domains such as economics, trading, investment, and financial and political environments. Better investment decision could be made when gold price values are accurately predicted. The main objective of this research is to forecasts whether the price of gold will rise or decline in the near future. Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Linear Regression are all different classification algorithms that have been used in this paper to predict the gold price movement direction. The performance of each of these algorithms has been investigated while using the Rapidminer software.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125328431","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398681
H. S. Harba, E. Harba, S. Hussein, M. Farttoos
Medical images have recently played a significant role in the diagnosis and detection of various diseases. Medical imaging can provide a means of direct visualization to observe through the human body and notice the small anatomical change and biological processes associated by different biological and physical parameters. To achieve a more accurate and reliable diagnosis, nowadays, varieties of computer aided detection (CAD) and computer-aided diagnosis (CADx) approaches have been established to help interpretation of the medical images. The CAD has become among the many major research subjects in diagnostic radiology and medical imaging. In this work we study the improvement in accuracy of detection of CAD system when combined principal component analysis and feed forward back propagation neural network. This work has investigated the ability to improve the CAD system in order to use in detection abnormality even with low cost diagnosis methods (such as mammogram images or X-ray). The results show that the reduction of correlated details within the training data by using the PCA method can enhance the recognition performance. The performance of the neural network diagnostic to discriminate the normal cases from cancerous cases, evaluated by using recognition analysis show a high accuracy in detection. The proposed approach can be considered as a potential tool for diagnosis breast cancer from x-ray and mammography images and prediction for non-experts and clinicians.
{"title":"Improving accuracy of CADx system by hybrid PCA and backpropagation","authors":"H. S. Harba, E. Harba, S. Hussein, M. Farttoos","doi":"10.1109/CATA.2018.8398681","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398681","url":null,"abstract":"Medical images have recently played a significant role in the diagnosis and detection of various diseases. Medical imaging can provide a means of direct visualization to observe through the human body and notice the small anatomical change and biological processes associated by different biological and physical parameters. To achieve a more accurate and reliable diagnosis, nowadays, varieties of computer aided detection (CAD) and computer-aided diagnosis (CADx) approaches have been established to help interpretation of the medical images. The CAD has become among the many major research subjects in diagnostic radiology and medical imaging. In this work we study the improvement in accuracy of detection of CAD system when combined principal component analysis and feed forward back propagation neural network. This work has investigated the ability to improve the CAD system in order to use in detection abnormality even with low cost diagnosis methods (such as mammogram images or X-ray). The results show that the reduction of correlated details within the training data by using the PCA method can enhance the recognition performance. The performance of the neural network diagnostic to discriminate the normal cases from cancerous cases, evaluated by using recognition analysis show a high accuracy in detection. The proposed approach can be considered as a potential tool for diagnosis breast cancer from x-ray and mammography images and prediction for non-experts and clinicians.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122524808","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398685
Z. Bohari, R. Ghazali, N. N. Atira, M. F. Sulaima, A. A. Rahman, M. K. Nor
This paper suggests on a study of building energy saving by using Analysis of Variance (ANOVA) system to analyze the reduction of energy consumption. This research is significant to reduce the impact of climate change via energy management. In this project, lighting system in UTeM's library is emphasized. The purpose of this research is to investigate the energy demand and determine the possibility of the aspect of energy saving by optimizing current lighting system. Data then used to investigate and analyze the data of total power consumption in the building and analyzed the saving using ANOVA method. This is to identify the best way for improving the energy performance and reporting them. The Analysis of Variance is the method that was suggested in this project; where the MATLAB and EXCEL are applied in analyzing the data and explored to understand the technique and flow of the software. The result proved that ANOVA method is among suitable method to analyze energy saving with more accurate and simple approach.
{"title":"Building energy management saving by considering lighting system optimization via ANOVA method","authors":"Z. Bohari, R. Ghazali, N. N. Atira, M. F. Sulaima, A. A. Rahman, M. K. Nor","doi":"10.1109/CATA.2018.8398685","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398685","url":null,"abstract":"This paper suggests on a study of building energy saving by using Analysis of Variance (ANOVA) system to analyze the reduction of energy consumption. This research is significant to reduce the impact of climate change via energy management. In this project, lighting system in UTeM's library is emphasized. The purpose of this research is to investigate the energy demand and determine the possibility of the aspect of energy saving by optimizing current lighting system. Data then used to investigate and analyze the data of total power consumption in the building and analyzed the saving using ANOVA method. This is to identify the best way for improving the energy performance and reporting them. The Analysis of Variance is the method that was suggested in this project; where the MATLAB and EXCEL are applied in analyzing the data and explored to understand the technique and flow of the software. The result proved that ANOVA method is among suitable method to analyze energy saving with more accurate and simple approach.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128925246","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398667
Yudo Ekanata, I. Budi
The number of user reviews for a mobile app can reach thousands so it will take a lot of time for app developers to sort through and find information that is important for further app development. Therefore, this study aims to automatically classify mobile application user reviews. Automatic classification conducted in this study is using machine learning approach. The features extracted from user review are unigram, bigram, star rating, review length, as well as the ratio of the number of words with positive and negative sentiment. For classification algorithms, we used Naïve Bayes, Support Vector Machine, Logistic Regression and Decision Tree. The experiment result shows that Logistic Regression gives the best F-Measure of 85% when combined with unigram plus sentence length and sentiment score. Unigram was proven as the most important feature since the additional features like sentence length and sentiment score only increased the F-measure around 1%. Bigram and star rating has negative impact on the classifier performance.
{"title":"Mobile application review classification for the Indonesian language using machine learning approach","authors":"Yudo Ekanata, I. Budi","doi":"10.1109/CATA.2018.8398667","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398667","url":null,"abstract":"The number of user reviews for a mobile app can reach thousands so it will take a lot of time for app developers to sort through and find information that is important for further app development. Therefore, this study aims to automatically classify mobile application user reviews. Automatic classification conducted in this study is using machine learning approach. The features extracted from user review are unigram, bigram, star rating, review length, as well as the ratio of the number of words with positive and negative sentiment. For classification algorithms, we used Naïve Bayes, Support Vector Machine, Logistic Regression and Decision Tree. The experiment result shows that Logistic Regression gives the best F-Measure of 85% when combined with unigram plus sentence length and sentiment score. Unigram was proven as the most important feature since the additional features like sentence length and sentiment score only increased the F-measure around 1%. Bigram and star rating has negative impact on the classifier performance.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686355","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398645
S. Zhuzbayev, D. Sabitova, B. Sarsenov
This work is devoted to computer modeling of wave processes. As an example, we took an ideal elastic body with distributed transient normal load. A mathematical model of the wave process has been constructed, a method has been determined to analyse wave propagation. We have defined the point scheme and selected the pattern. The conditions have been determined for the interior, boundary and corner points of the area. A software had been developed and the result of calculations was checked. Oscillograms of longitudinal velocities and normal stresses, as well as isolines of normal stresses have been obtained.
{"title":"Computer mathematical modeling of wave processes","authors":"S. Zhuzbayev, D. Sabitova, B. Sarsenov","doi":"10.1109/CATA.2018.8398645","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398645","url":null,"abstract":"This work is devoted to computer modeling of wave processes. As an example, we took an ideal elastic body with distributed transient normal load. A mathematical model of the wave process has been constructed, a method has been determined to analyse wave propagation. We have defined the point scheme and selected the pattern. The conditions have been determined for the interior, boundary and corner points of the area. A software had been developed and the result of calculations was checked. Oscillograms of longitudinal velocities and normal stresses, as well as isolines of normal stresses have been obtained.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132284880","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398683
Zarina Mohamad, Lim Yan Thong, Aznida Hayati Zakaria, W. S. W. Awang
One of the most critical concerns in information security today is user authentication. There is a great security when using the text-based strong password schemes but often remembering those good passwords is very hard and users writing them down on a piece of paper or saving inside the smart phone. There is an alternative solution to the text-based authentication which is the Graphical User Authentication (GUA) or simply image-based Password based on the fact that humans tend to memorize images better. This type of approach allows users to create and remember passwords easily. However, one big issues that is plaguing GUA is shoulder surfing attack that can capture the users mouse clicks and eavesdropping. In this paper, a new algorithm that using zero-knowledge protocol as the solution to solving the eavesdropping and shoulder surfing attack to provide better system security. In zero-knowledge protocol, users prove that they know the graphical password without sending it. In other words, the user does not send the password to the verifier or reveal it to the people nearby. Hackers who try to eavesdrop the password will be failed since the password is not sent over the insecure channel such as Internet nor reveal. Therefore it is a secured approach to prevent interception by unwanted parties or adversary. The result that is going to be yielded in this project is a secured authentication approach which is user-friendly.
{"title":"Image based authentication using zero-knowledge protocol","authors":"Zarina Mohamad, Lim Yan Thong, Aznida Hayati Zakaria, W. S. W. Awang","doi":"10.1109/CATA.2018.8398683","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398683","url":null,"abstract":"One of the most critical concerns in information security today is user authentication. There is a great security when using the text-based strong password schemes but often remembering those good passwords is very hard and users writing them down on a piece of paper or saving inside the smart phone. There is an alternative solution to the text-based authentication which is the Graphical User Authentication (GUA) or simply image-based Password based on the fact that humans tend to memorize images better. This type of approach allows users to create and remember passwords easily. However, one big issues that is plaguing GUA is shoulder surfing attack that can capture the users mouse clicks and eavesdropping. In this paper, a new algorithm that using zero-knowledge protocol as the solution to solving the eavesdropping and shoulder surfing attack to provide better system security. In zero-knowledge protocol, users prove that they know the graphical password without sending it. In other words, the user does not send the password to the verifier or reveal it to the people nearby. Hackers who try to eavesdrop the password will be failed since the password is not sent over the insecure channel such as Internet nor reveal. Therefore it is a secured approach to prevent interception by unwanted parties or adversary. The result that is going to be yielded in this project is a secured authentication approach which is user-friendly.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131279206","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398670
Amir Matallaoui
Context: By definition, gamification is the application of game design elements in non-game contexts. This deployment of gamification usually induces a further layer of complexity on top of the current task. Thus, to minimize the caused cognitive load, we argue that taking account of the gamification aesthetics is as important as deploying different and elaborated gamification mechanics. Objective: In this paper, we deal with the cognitive overload made by the deployment of gamification in serious contexts such as education, health and work. We thereby emphasize on the importance of applying established design theories such as semiotics (the signs theory) in reducing the caused cognitive load. Method: We have therefore designed a quantitative study, to which we have invited participants with different ages and backgrounds. The study consists of a series of puzzles (taken from a prior study of ours), to which two achievement systems with different badges (icons) were designed. The participants have afterwards to answer various weighted questions related to their perceptions of both achievement systems. Hypothesis: In this work, we argue that badges, whose icon design takes consideration of the signs theory are better perceived than badges, whose design did not follow this theory.
{"title":"Towards more effective gamification: Does deploying semiotics help design better perceivable badges?","authors":"Amir Matallaoui","doi":"10.1109/CATA.2018.8398670","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398670","url":null,"abstract":"Context: By definition, gamification is the application of game design elements in non-game contexts. This deployment of gamification usually induces a further layer of complexity on top of the current task. Thus, to minimize the caused cognitive load, we argue that taking account of the gamification aesthetics is as important as deploying different and elaborated gamification mechanics. Objective: In this paper, we deal with the cognitive overload made by the deployment of gamification in serious contexts such as education, health and work. We thereby emphasize on the importance of applying established design theories such as semiotics (the signs theory) in reducing the caused cognitive load. Method: We have therefore designed a quantitative study, to which we have invited participants with different ages and backgrounds. The study consists of a series of puzzles (taken from a prior study of ours), to which two achievement systems with different badges (icons) were designed. The participants have afterwards to answer various weighted questions related to their perceptions of both achievement systems. Hypothesis: In this work, we argue that badges, whose icon design takes consideration of the signs theory are better perceived than badges, whose design did not follow this theory.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"123 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132482958","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 : 2018-05-01DOI: 10.1109/CATA.2018.8398673
Jianpeng Xu, Sheng Lin, Aoxue Teng
How to adjust the feature points number adaptively according to the images in different scenes is one of the key issues in improving detection efficiency. In this paper, an improved SIFT algorithm based on adaptive contrast threshold was proposed. Firstly, back propagation neural network and analytic hierarchy process were used to analyze the mathematical models of feature points number, image information and SIFT contrast threshold in different scenes from the perspective of image complexity, so as to realize the dynamic adjustability of contrast threshold. Then, a new SIFT algorithm framework was constructed by using the adaptive control module based on the mathematical model, and ultimately the number of feature points was coordinated. Compared with the two existing algorithms, the experimental data verified that the proposed algorithm had higher efficiency and accuracy, and that it realized the efficient control of feature point number in multi-scene.
{"title":"Improved SIFT algorithm based on adaptive contrast threshold","authors":"Jianpeng Xu, Sheng Lin, Aoxue Teng","doi":"10.1109/CATA.2018.8398673","DOIUrl":"https://doi.org/10.1109/CATA.2018.8398673","url":null,"abstract":"How to adjust the feature points number adaptively according to the images in different scenes is one of the key issues in improving detection efficiency. In this paper, an improved SIFT algorithm based on adaptive contrast threshold was proposed. Firstly, back propagation neural network and analytic hierarchy process were used to analyze the mathematical models of feature points number, image information and SIFT contrast threshold in different scenes from the perspective of image complexity, so as to realize the dynamic adjustability of contrast threshold. Then, a new SIFT algorithm framework was constructed by using the adaptive control module based on the mathematical model, and ultimately the number of feature points was coordinated. Compared with the two existing algorithms, the experimental data verified that the proposed algorithm had higher efficiency and accuracy, and that it realized the efficient control of feature point number in multi-scene.","PeriodicalId":231024,"journal":{"name":"2018 4th International Conference on Computer and Technology Applications (ICCTA)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127075055","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：