Pub Date : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055954
S. Rizwan, A. Jalal, Kibum Kim
In the past few years, facial features detection and landmarks analysis plays a vital role in several practical application such as surveillance system, crime detector and age estimation. In this paper, we proposed a novel approach of recognizing facial expressions based on multi landmark detectors, local transform features and recognizer classifier. The proposed system is divided into four stages. (a) Face detection using skin color segmentation and ellipse fitting, (b) Plotting landmarks on facial features, (c) Feature extraction using euclidean distance, HOG and LBP. While, (d) SVM classification learner is used to classify six basic facial expressions like Neutral, Happy, Sad, Anger, Disgust, and Surprise. The proposed method is applied on two facial expression datasets i-e. MMI facial expressions dataset and Chicago Face dataset and achieved accuracy rates of 80.8% and 83.01%, respectively. The proposed system outperforms the state-of-the-art facial expression recognition system in terms of recognition accuracy. The proposed system should be applicable to different consumer application domains such as online business negotiations, consumer behavior analysis, E-learning environments, and virtual reality practices.
{"title":"An Accurate Facial Expression Detector using Multi-Landmarks Selection and Local Transform Features","authors":"S. Rizwan, A. Jalal, Kibum Kim","doi":"10.1109/ICACS47775.2020.9055954","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055954","url":null,"abstract":"In the past few years, facial features detection and landmarks analysis plays a vital role in several practical application such as surveillance system, crime detector and age estimation. In this paper, we proposed a novel approach of recognizing facial expressions based on multi landmark detectors, local transform features and recognizer classifier. The proposed system is divided into four stages. (a) Face detection using skin color segmentation and ellipse fitting, (b) Plotting landmarks on facial features, (c) Feature extraction using euclidean distance, HOG and LBP. While, (d) SVM classification learner is used to classify six basic facial expressions like Neutral, Happy, Sad, Anger, Disgust, and Surprise. The proposed method is applied on two facial expression datasets i-e. MMI facial expressions dataset and Chicago Face dataset and achieved accuracy rates of 80.8% and 83.01%, respectively. The proposed system outperforms the state-of-the-art facial expression recognition system in terms of recognition accuracy. The proposed system should be applicable to different consumer application domains such as online business negotiations, consumer behavior analysis, E-learning environments, and virtual reality practices.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129232976","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055945
Hania Arif, A. Javed
Exponential growth of fake ID cards generation leads to increased tendency of forgery with severe security and privacy threats. University ID cards are used to authenticate actual employees and students of the university. Manual examination of ID cards is a laborious activity, therefore, in this paper, we propose an effective automated method for employee/student authentication based on analyzing the cards. Additionally, our method also identifies the department of concerned employee/student. For this purpose, we employ different image enhancement and morphological operators to improve the appearance of input image better suitable for recognition. More specifically, we employ median filtering to remove noise from the given input image. Next, we apply the histogram equalization to enhance the contrast of the image. We employ Canny edge detector to detect the edges from this equalized image. The resultant edge image contains the broken characters. To fill these gaps, we apply the dilation operator that increases the thickness of the characters. Dilation fills the broken characters, however, also add extra thickness that is then removed through applying the morphological thinning. Finally, dilation and thinning are applied in combination to Optical character recognition (OCR) to segment and recognize the characters including the name, ID, and department of the employee/student. Finally, after the OCR application on the morphed image, we obtain the name, ID, and department of the employee/student. If the concerned credentials of the employee/student are matched with his/her department, then access of the door is granted to that employee/student. Experimental results illustrate the effectiveness of the proposed method.
{"title":"An Effective Card Scanning Framework for User Authentication System","authors":"Hania Arif, A. Javed","doi":"10.1109/ICACS47775.2020.9055945","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055945","url":null,"abstract":"Exponential growth of fake ID cards generation leads to increased tendency of forgery with severe security and privacy threats. University ID cards are used to authenticate actual employees and students of the university. Manual examination of ID cards is a laborious activity, therefore, in this paper, we propose an effective automated method for employee/student authentication based on analyzing the cards. Additionally, our method also identifies the department of concerned employee/student. For this purpose, we employ different image enhancement and morphological operators to improve the appearance of input image better suitable for recognition. More specifically, we employ median filtering to remove noise from the given input image. Next, we apply the histogram equalization to enhance the contrast of the image. We employ Canny edge detector to detect the edges from this equalized image. The resultant edge image contains the broken characters. To fill these gaps, we apply the dilation operator that increases the thickness of the characters. Dilation fills the broken characters, however, also add extra thickness that is then removed through applying the morphological thinning. Finally, dilation and thinning are applied in combination to Optical character recognition (OCR) to segment and recognize the characters including the name, ID, and department of the employee/student. Finally, after the OCR application on the morphed image, we obtain the name, ID, and department of the employee/student. If the concerned credentials of the employee/student are matched with his/her department, then access of the door is granted to that employee/student. Experimental results illustrate the effectiveness of the proposed method.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123503715","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055956
Huda Tariq, Maliha Arshad, W. Basit
The goal of this paper is to analyze the effects of refactoring on time complexity of an algorithm. For this purpose a problem in which time complexity is highly sensitive, is chosen for studying. As it is known by computer scientists, they use refactoring in order to improve quality of design while preserving external behavior (functional properties). Sustainability of nonfunctional properties are not guaranteed. Hence, for learning its effects on non-functional properties such as time, a multiobjective task assignment problem is selected. The chosen problem has been implemented through an Evolutionary Genetic Algorithm. The problem chosen is an NP -hard problem because of being time sensitive. Initially, code smells are detected & refactoring is applied. In order to observe the improvement in design of code, several metrics of quality such as cohesion, coupling, complexity & inheritance, are calculated and compared before & after applying refactoring. Also, computation time of the improved code is compared with the original code, in order to analyze effects of refactoring on computation time. For problems that are time sensitive, refactoring may not be a good choice depending upon the requirements. Results of the experimentation nullify the approach that refactoring improves the computational cost of the software. Increase in the length of code eventually may prove as a tradeoff in terms of memory consumption.
{"title":"Effects of Refactoring upon Efficiency of an NP-Hard Task Assignment Problem: A case study","authors":"Huda Tariq, Maliha Arshad, W. Basit","doi":"10.1109/ICACS47775.2020.9055956","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055956","url":null,"abstract":"The goal of this paper is to analyze the effects of refactoring on time complexity of an algorithm. For this purpose a problem in which time complexity is highly sensitive, is chosen for studying. As it is known by computer scientists, they use refactoring in order to improve quality of design while preserving external behavior (functional properties). Sustainability of nonfunctional properties are not guaranteed. Hence, for learning its effects on non-functional properties such as time, a multiobjective task assignment problem is selected. The chosen problem has been implemented through an Evolutionary Genetic Algorithm. The problem chosen is an NP -hard problem because of being time sensitive. Initially, code smells are detected & refactoring is applied. In order to observe the improvement in design of code, several metrics of quality such as cohesion, coupling, complexity & inheritance, are calculated and compared before & after applying refactoring. Also, computation time of the improved code is compared with the original code, in order to analyze effects of refactoring on computation time. For problems that are time sensitive, refactoring may not be a good choice depending upon the requirements. Results of the experimentation nullify the approach that refactoring improves the computational cost of the software. Increase in the length of code eventually may prove as a tradeoff in terms of memory consumption.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115652711","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055948
Alia Samreen, Adnan Ahmad, Furkh Zeshan
Despite the increasing use of social media platforms for information and data collection, its immoderate nature often leads to the spread of rumors - unverified information. At the same time, the opening of social media platforms offers the opportunity to explore how users share and discuss input, as well as to automatically evaluate the assessment of their verification using techniques and different methodologies. To overcome these problems, this study aims to contribute effectively to the area of rumor verification by scraping the web and verifying the information provided. To this end, a Rumor Tracking System is proposed in which a web scraping technique is used to evaluate the news verification based on various sources and features for news checking. The proposed system automatically detects these sources and features on the websites and verifies the content by consulting an information matching algorithm and completing a truth table of the sources and features provided. A combination of information on all the sources and features gathered through the websites is maintained by the system, which is used to determine whether an article is based on rumor or not.
{"title":"Searching for Truth in the Post-Truth Age","authors":"Alia Samreen, Adnan Ahmad, Furkh Zeshan","doi":"10.1109/ICACS47775.2020.9055948","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055948","url":null,"abstract":"Despite the increasing use of social media platforms for information and data collection, its immoderate nature often leads to the spread of rumors - unverified information. At the same time, the opening of social media platforms offers the opportunity to explore how users share and discuss input, as well as to automatically evaluate the assessment of their verification using techniques and different methodologies. To overcome these problems, this study aims to contribute effectively to the area of rumor verification by scraping the web and verifying the information provided. To this end, a Rumor Tracking System is proposed in which a web scraping technique is used to evaluate the news verification based on various sources and features for news checking. The proposed system automatically detects these sources and features on the websites and verifies the content by consulting an information matching algorithm and completing a truth table of the sources and features provided. A combination of information on all the sources and features gathered through the websites is maintained by the system, which is used to determine whether an article is based on rumor or not.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128918656","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055952
Sadaqat Ali Rammy, Muhammad Abrar, Sadia Jabbar Anwar, Wu Zhang
Deep Learning has grasped great attention for recognition of Electroencephalography. For the analysis of brain dynamics, non-stationary motor imagery signals are used. Although a number of studies have been carried out for the extraction of hidden patterns and classification of EEG signals, temporal information has rarely been incorporated. In this paper, we propose a spatio-temporal energy maps generation scheme followed by deep learning classification model. Common spatial pattern filters and Fast Fourier Transform Energy Maps are deployed to obtain discriminative and spatio-temporal features. Long-Short-Term-Memory (LSTM) based neural network has been proposed to classify the temporal series of energy maps. This research also investigates preprocessing techniques to obtain optimal parameters which include frequency bands selection and temporal segmentation. The proposed model is evaluated on BCI Competition IV dataset 2a and achieved 0.64 mean kappa for multi-class EEG classification, which is the current state of the art. Furthermore, several empirical findings are also presented, that may be of significant interest to the BCI community.
{"title":"Recurrent Deep Learning for EEG-based Motor Imagination Recognition","authors":"Sadaqat Ali Rammy, Muhammad Abrar, Sadia Jabbar Anwar, Wu Zhang","doi":"10.1109/ICACS47775.2020.9055952","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055952","url":null,"abstract":"Deep Learning has grasped great attention for recognition of Electroencephalography. For the analysis of brain dynamics, non-stationary motor imagery signals are used. Although a number of studies have been carried out for the extraction of hidden patterns and classification of EEG signals, temporal information has rarely been incorporated. In this paper, we propose a spatio-temporal energy maps generation scheme followed by deep learning classification model. Common spatial pattern filters and Fast Fourier Transform Energy Maps are deployed to obtain discriminative and spatio-temporal features. Long-Short-Term-Memory (LSTM) based neural network has been proposed to classify the temporal series of energy maps. This research also investigates preprocessing techniques to obtain optimal parameters which include frequency bands selection and temporal segmentation. The proposed model is evaluated on BCI Competition IV dataset 2a and achieved 0.64 mean kappa for multi-class EEG classification, which is the current state of the art. Furthermore, several empirical findings are also presented, that may be of significant interest to the BCI community.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132198425","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055951
A. Nadeem, A. Jalal, Kibum Kim
Human body action recognition has drawn a good deal of interest in the community of computer vision, owing to its wide range of applications. Recently, the video / image sequence base action recognition techniques are believed to be ideal for its efficiency and lower cost compared to other techniques such as the ambient sensor and the wearable sensor. However, given to a large amount of variation in human pose and image quality, reliable detection of human action is still a very challenging job for scientists. In this document, we used linear discriminant analysis for the generation of features from the body parts detected. The primary goal of this study is to combine linear discriminant analysis with an artificial neural network for precise human action detection and recognition. Our proposed mechanism detects complicated human actions in two state-of-the-art datasets, i.e. KTH-dataset and Weizmann Human Action. We obtained multidimensional features from twelve body parts, which are estimated from body models. These multidimensional characteristics are used as inputs for the artificial neural network. To access the efficiency of our suggested method, we compared the outcomes with other state-of-the-art classifiers. Experimental results show that our proposed technique is reliable and applicable in health exercise systems, smart surveillance, e-learning, abnormal behavioral detection, protection for child abuse, care of the elderly people, virtual reality, intelligent image retrieval and human computer interaction.
{"title":"Human Actions Tracking and Recognition Based on Body Parts Detection via Artificial Neural Network","authors":"A. Nadeem, A. Jalal, Kibum Kim","doi":"10.1109/ICACS47775.2020.9055951","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055951","url":null,"abstract":"Human body action recognition has drawn a good deal of interest in the community of computer vision, owing to its wide range of applications. Recently, the video / image sequence base action recognition techniques are believed to be ideal for its efficiency and lower cost compared to other techniques such as the ambient sensor and the wearable sensor. However, given to a large amount of variation in human pose and image quality, reliable detection of human action is still a very challenging job for scientists. In this document, we used linear discriminant analysis for the generation of features from the body parts detected. The primary goal of this study is to combine linear discriminant analysis with an artificial neural network for precise human action detection and recognition. Our proposed mechanism detects complicated human actions in two state-of-the-art datasets, i.e. KTH-dataset and Weizmann Human Action. We obtained multidimensional features from twelve body parts, which are estimated from body models. These multidimensional characteristics are used as inputs for the artificial neural network. To access the efficiency of our suggested method, we compared the outcomes with other state-of-the-art classifiers. Experimental results show that our proposed technique is reliable and applicable in health exercise systems, smart surveillance, e-learning, abnormal behavioral detection, protection for child abuse, care of the elderly people, virtual reality, intelligent image retrieval and human computer interaction.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"422 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123048251","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 : 2020-02-01DOI: 10.1109/ICACS47775.2020.9055941
S. Yasear, K. Ku-Mahamud
This paper proposes an enhanced non-dominated sorting Harris's hawk multi-objective optimizer (ENDSHHMO) algorithm. In the original non-dominated sorting Harris's hawk multi-objective optimizer (NDSHHMO) algorithm, the convergence parameter is used to control the diversification and intensification during the search process. The parameter value decreases linearly as the number of iterations of the algorithm increases. This adjustment strategy of the parameter cannot fully reflect the actual optimization search process. Therefore, an improved adjustment strategy has been proposed and integrated with the NDSHHMO algorithm. This strategy can ensure that the proposed algorithm has a better diversification and intensification ability during the optimization process and improves the convergence to the Pareto front. The performance of the proposed enhanced NDSHHMO algorithm has been evaluated using a set of well-known multi-objective optimization problems. The results of the ENDSHHMO are compared with the NDSHHMO algorithm, which shows that the proposed algorithm is superior.
{"title":"Enhanced Non-dominated Sorting Harris's Hawk Multi-objective Optimizer","authors":"S. Yasear, K. Ku-Mahamud","doi":"10.1109/ICACS47775.2020.9055941","DOIUrl":"https://doi.org/10.1109/ICACS47775.2020.9055941","url":null,"abstract":"This paper proposes an enhanced non-dominated sorting Harris's hawk multi-objective optimizer (ENDSHHMO) algorithm. In the original non-dominated sorting Harris's hawk multi-objective optimizer (NDSHHMO) algorithm, the convergence parameter is used to control the diversification and intensification during the search process. The parameter value decreases linearly as the number of iterations of the algorithm increases. This adjustment strategy of the parameter cannot fully reflect the actual optimization search process. Therefore, an improved adjustment strategy has been proposed and integrated with the NDSHHMO algorithm. This strategy can ensure that the proposed algorithm has a better diversification and intensification ability during the optimization process and improves the convergence to the Pareto front. The performance of the proposed enhanced NDSHHMO algorithm has been evaluated using a set of well-known multi-objective optimization problems. The results of the ENDSHHMO are compared with the NDSHHMO algorithm, which shows that the proposed algorithm is superior.","PeriodicalId":268675,"journal":{"name":"2020 3rd International Conference on Advancements in Computational Sciences (ICACS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123755263","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：