Pub Date : 2018-09-01DOI: 10.23919/IConAC.2018.8749108
M. A. Irfan, Sahib Khan, Syed Ali Hassan, Nasir Ahmad
A novel method of image super resolution using sparse representation has been discussed in this paper. The main purpose is to acquire the super-resolved image from the down scaled and blurred images. With the small number of elements from a huge set of vectors, sparse signal model approximates signals and this large dataset is called a dictionary. For construction of high and low-resolution dictionaries from the condensed atoms extracted from the training image patches, the Orthogonal Matching Pursuit approach has been used. The blurred and down-scaled version of the image is super resolved using the above-mentioned dictionaries. The outcomes are compared both instinctively by the visual assessment of the resulting super-resolve images by means of the proposed scheme and the bi-cubic interpolation method, and by comparing the Peak Signal-to-Noise Ratio (PSNR) obtained by the two approaches. Both the comparison metrics, i.e. visual quality of acquired super resolved images and PSNR measures show that the proposed approach is superior to the existing state of the art Bi-Cubic interpolation.
{"title":"A Novel Technique for Image Super Resolution Based on Sparse Representations and Compact Entity Extraction","authors":"M. A. Irfan, Sahib Khan, Syed Ali Hassan, Nasir Ahmad","doi":"10.23919/IConAC.2018.8749108","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749108","url":null,"abstract":"A novel method of image super resolution using sparse representation has been discussed in this paper. The main purpose is to acquire the super-resolved image from the down scaled and blurred images. With the small number of elements from a huge set of vectors, sparse signal model approximates signals and this large dataset is called a dictionary. For construction of high and low-resolution dictionaries from the condensed atoms extracted from the training image patches, the Orthogonal Matching Pursuit approach has been used. The blurred and down-scaled version of the image is super resolved using the above-mentioned dictionaries. The outcomes are compared both instinctively by the visual assessment of the resulting super-resolve images by means of the proposed scheme and the bi-cubic interpolation method, and by comparing the Peak Signal-to-Noise Ratio (PSNR) obtained by the two approaches. Both the comparison metrics, i.e. visual quality of acquired super resolved images and PSNR measures show that the proposed approach is superior to the existing state of the art Bi-Cubic interpolation.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130458824","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749028
M. Rehman, M. A. Shah, M. Khan, Shaheed Ahmad
With the increasing number of vehicles in the last decade, car parking in congested areas and cities has become a big challenge. To resolve this problem, researchers have proposed Smart Parking System (SPS) which integrate new techniques and approaches into the traditional parking system. A SPS merges traditional parking with Internet of Things (IoT), Wireless sensor network (WSN) and other hardware. All type of existing SPSs are efficient and increase the performance, however the installation cost is too high due to which the system is not used widely. In this paper, a Vehicular Ad-hoc Network (VANET) based routing algorithm for SPS is proposed called Updating Block Route Algorithm (UBRA). It works by detecting congestion and by calculating the average speed of the vehicles. The proposed UBRA updates the route with a congestion less route and has low installation cost. Furthermore, it offers minimization of parking area searching time, fuel consumption and carbon dioxide (CO2) emission. The results and show that proposed UBRA saves up to 23.6%, fuel consumption and 9% CO2 emission when compared with existing approach.
{"title":"A VANET based Smart Car Parking System to Minimize Searching Time, Fuel Consumption and CO2 Emission","authors":"M. Rehman, M. A. Shah, M. Khan, Shaheed Ahmad","doi":"10.23919/IConAC.2018.8749028","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749028","url":null,"abstract":"With the increasing number of vehicles in the last decade, car parking in congested areas and cities has become a big challenge. To resolve this problem, researchers have proposed Smart Parking System (SPS) which integrate new techniques and approaches into the traditional parking system. A SPS merges traditional parking with Internet of Things (IoT), Wireless sensor network (WSN) and other hardware. All type of existing SPSs are efficient and increase the performance, however the installation cost is too high due to which the system is not used widely. In this paper, a Vehicular Ad-hoc Network (VANET) based routing algorithm for SPS is proposed called Updating Block Route Algorithm (UBRA). It works by detecting congestion and by calculating the average speed of the vehicles. The proposed UBRA updates the route with a congestion less route and has low installation cost. Furthermore, it offers minimization of parking area searching time, fuel consumption and carbon dioxide (CO2) emission. The results and show that proposed UBRA saves up to 23.6%, fuel consumption and 9% CO2 emission when compared with existing approach.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132687291","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8748995
C. A. U. Hassan, Muhammad Sufyan Khan, M. A. Shah
Data Mining is used to extract the valuable information from raw data. The task of data mining is to utilize the historical data to discover hidden patterns that helpful for future decisions. To analyze the data machine learning classifiers are used. Various data mining approaches and machine learning classifiers are applied for prediction of diseases. Where can supports, in timely treatment. The aim of this work is to compare the performance of ML classifier. These ML classifiers are Logistic Regression, Decision Tree, Niven Bayes, k-Nearest Neighbors, Support Vector Machine and Random Forests classifiers on two datasets on the basis of its accuracy, precision and f measure. The experimental results reveal that it's found that the Random Forests performance is better than the other classifiers. It gives 83% accuracy in heart data sets and 85% accuracy in hepatitis disease prediction
{"title":"Comparison of Machine Learning Algorithms in Data classification","authors":"C. A. U. Hassan, Muhammad Sufyan Khan, M. A. Shah","doi":"10.23919/IConAC.2018.8748995","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8748995","url":null,"abstract":"Data Mining is used to extract the valuable information from raw data. The task of data mining is to utilize the historical data to discover hidden patterns that helpful for future decisions. To analyze the data machine learning classifiers are used. Various data mining approaches and machine learning classifiers are applied for prediction of diseases. Where can supports, in timely treatment. The aim of this work is to compare the performance of ML classifier. These ML classifiers are Logistic Regression, Decision Tree, Niven Bayes, k-Nearest Neighbors, Support Vector Machine and Random Forests classifiers on two datasets on the basis of its accuracy, precision and f measure. The experimental results reveal that it's found that the Random Forests performance is better than the other classifiers. It gives 83% accuracy in heart data sets and 85% accuracy in hepatitis disease prediction","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"23 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131614605","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749109
Samir Alabied, Usama Haba, Alsadak Daraz, F. Gu, A. Ball
Motor current signature analysis (MCSA) is an important, reliable and non-invasive technique for monitoring rotation machines. Spectrum analysis is a common way to implement MCSA, which allows large faults such as severe mechanical imbalance to be extracted successfully, but is often ineffective in the detection of incipient faults such as supporting bearings from motor drive systems because of noise and nonlinear interferences. To improve the performance of MSCA, this paper exploits the use of Empirical Mode Decomposition (EMD) method as an advanced tool to process motor current signals for noise reduction and nonlinear signature enhancement. The nonlinear demodulation property of EMD is firstly reviewed in association with the motor current signal models with fault cases. Then EMD is applied to signals from different fault cases from a centrifuge pump system to verify its performances in extracting the fault signatures for separating different faults. In conjunction with the envelope spectrum of separated intrinsic mode function (IMF), it shows that the proposed EMD based approach produces a better result in diagnosing common pump faults: small defects on impeller and bearings, which cannot be separated based on spectrum analysis.
{"title":"Empirical Mode Decomposition of Motor Current Signatures for Centrifugal Pump Diagnostics","authors":"Samir Alabied, Usama Haba, Alsadak Daraz, F. Gu, A. Ball","doi":"10.23919/IConAC.2018.8749109","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749109","url":null,"abstract":"Motor current signature analysis (MCSA) is an important, reliable and non-invasive technique for monitoring rotation machines. Spectrum analysis is a common way to implement MCSA, which allows large faults such as severe mechanical imbalance to be extracted successfully, but is often ineffective in the detection of incipient faults such as supporting bearings from motor drive systems because of noise and nonlinear interferences. To improve the performance of MSCA, this paper exploits the use of Empirical Mode Decomposition (EMD) method as an advanced tool to process motor current signals for noise reduction and nonlinear signature enhancement. The nonlinear demodulation property of EMD is firstly reviewed in association with the motor current signal models with fault cases. Then EMD is applied to signals from different fault cases from a centrifuge pump system to verify its performances in extracting the fault signatures for separating different faults. In conjunction with the envelope spectrum of separated intrinsic mode function (IMF), it shows that the proposed EMD based approach produces a better result in diagnosing common pump faults: small defects on impeller and bearings, which cannot be separated based on spectrum analysis.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124131116","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749096
Fahad Mira, Wei Huang
Conventional signature-based malware detection techniques have been used for many years because of their high detection rates and low false positive rates. However, signature-based detection techniques are regarded as ineffective due to their inability to detect unseen, new, polymorphic and metamorphic malware. To affect the weaknesses of the signature-based detection techniques, researchers have turned into behavioural-based detection techniques whereby a malware behavioural is constructed by capturing malware API calls during execution. In this context, API call sequences matching techniques are widely used to compute malware similarities. However, API call sequences matching techniques require large processing resources which make the process slow due to computational complexity and therefore, cannot scale to large API call sequences. To mitigate its problem, Longest Common Substring and Longest Common Subsequence have been used in this paper for strings matching in order to detect malware and their variants. In this paper we evaluate these two algorithms in the context of malware detection rate and false alarm rate.
{"title":"Performance Evaluation of String Based Malware Detection Methods","authors":"Fahad Mira, Wei Huang","doi":"10.23919/IConAC.2018.8749096","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749096","url":null,"abstract":"Conventional signature-based malware detection techniques have been used for many years because of their high detection rates and low false positive rates. However, signature-based detection techniques are regarded as ineffective due to their inability to detect unseen, new, polymorphic and metamorphic malware. To affect the weaknesses of the signature-based detection techniques, researchers have turned into behavioural-based detection techniques whereby a malware behavioural is constructed by capturing malware API calls during execution. In this context, API call sequences matching techniques are widely used to compute malware similarities. However, API call sequences matching techniques require large processing resources which make the process slow due to computational complexity and therefore, cannot scale to large API call sequences. To mitigate its problem, Longest Common Substring and Longest Common Subsequence have been used in this paper for strings matching in order to detect malware and their variants. In this paper we evaluate these two algorithms in the context of malware detection rate and false alarm rate.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"28 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126043997","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749006
Jephin Thekemuriyil Philip, Omar H. Rashed, A. Onsy, M. Varley
The paper describes design and development of a new ‘Personal Mobility Pod’ using low cost systems proposed for use in urban areas. Recent studies have shown increased use of personal mobility, suggesting the scope for further research. Adding to Mobility-on-Demand and vehicle share, such mobility pods could bridge the gap in driverless vehicle research and possibly be a solution to road traffic and congestion in urban areas. The proposed platform is a combination of sensory fusion with feedback managed by a main controller. The navigation system considers offline mapping and localisation with user interface, illustrating waypoints through Google Maps. A Pure Pursuit technique is used to track the vehicle along the given path. The scooters robust, reliable, safe design allows operation in various terrains. The developed platform is moreover proposed as a suitable test platform for driverless vehicle sub-system for testing and experimentation. The reliability of the pod has been tested and validated in two stages: laboratory testing and field testing.
{"title":"Development of a Driverless Personal Mobility Pod","authors":"Jephin Thekemuriyil Philip, Omar H. Rashed, A. Onsy, M. Varley","doi":"10.23919/IConAC.2018.8749006","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749006","url":null,"abstract":"The paper describes design and development of a new ‘Personal Mobility Pod’ using low cost systems proposed for use in urban areas. Recent studies have shown increased use of personal mobility, suggesting the scope for further research. Adding to Mobility-on-Demand and vehicle share, such mobility pods could bridge the gap in driverless vehicle research and possibly be a solution to road traffic and congestion in urban areas. The proposed platform is a combination of sensory fusion with feedback managed by a main controller. The navigation system considers offline mapping and localisation with user interface, illustrating waypoints through Google Maps. A Pure Pursuit technique is used to track the vehicle along the given path. The scooters robust, reliable, safe design allows operation in various terrains. The developed platform is moreover proposed as a suitable test platform for driverless vehicle sub-system for testing and experimentation. The reliability of the pod has been tested and validated in two stages: laboratory testing and field testing.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126336139","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749053
Alsadak Daraz, Samir Alabied, Ann Smith, F. Gu, A. Ball
As key components in centrifugal pumps rolling bearings work to reduce friction and maintain the impeller rotor in correct alignment with stationary parts under the action of radial and transverse loads. Effective fault detection of bearings allows appropriate preventive action to be taken timely, where required, and enhances performance operation. To develop an easy implementation and yet effective method for detecting and diagnosing pump bearing faults, the focus of this study is on utilising airborne sound signals which can be acquired more remotely and at lower cost, compared with vibration based methods which needs high numbers of sensors for monitoring a pump system. However, acoustic signals are much noisy, and it is difficult to detect machine faults using conventional signal processing methods such as time domain features, where the results have a limited and weak fault signatures. Thus, a more advanced signal processing technique: the envelope spectrum is adopted to establish accurate diagnostic fault patterns. The evaluating results show that the proposed method is effective and accurate to enhance the amplitudes at bearing characteristic frequencies, allowing diagnostic information to be extracted reliably, which also makes the Root Mean Square (RMS) of the envelope signals give a full separation between faulty and healthy cases over a wide range of pump operation, outperforming the vibration signals.
{"title":"Detection and Diagnosis of Centrifugal Pump Bearing Faults Based on the Envelope Analysis of Airborne Sound Signals","authors":"Alsadak Daraz, Samir Alabied, Ann Smith, F. Gu, A. Ball","doi":"10.23919/IConAC.2018.8749053","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749053","url":null,"abstract":"As key components in centrifugal pumps rolling bearings work to reduce friction and maintain the impeller rotor in correct alignment with stationary parts under the action of radial and transverse loads. Effective fault detection of bearings allows appropriate preventive action to be taken timely, where required, and enhances performance operation. To develop an easy implementation and yet effective method for detecting and diagnosing pump bearing faults, the focus of this study is on utilising airborne sound signals which can be acquired more remotely and at lower cost, compared with vibration based methods which needs high numbers of sensors for monitoring a pump system. However, acoustic signals are much noisy, and it is difficult to detect machine faults using conventional signal processing methods such as time domain features, where the results have a limited and weak fault signatures. Thus, a more advanced signal processing technique: the envelope spectrum is adopted to establish accurate diagnostic fault patterns. The evaluating results show that the proposed method is effective and accurate to enhance the amplitudes at bearing characteristic frequencies, allowing diagnostic information to be extracted reliably, which also makes the Root Mean Square (RMS) of the envelope signals give a full separation between faulty and healthy cases over a wide range of pump operation, outperforming the vibration signals.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122076153","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8748989
S. Al-Fedaghi, Reem Al-Azmi
Several different modeling languages and notations are used in diverse engineering disciplines for modeling of system processes and for control and monitoring functions. This paper applies a recently proposed diagrammatic language called the Flowthing Machine (FM) model to modeling the process diagrams of a currently existing waste water treatment facility. The modeling includes depictions of components and operations of the project to achieve a holistic picture for engineers. The resultant schemata demonstrate the advantages of the proposed modeling technique in comparison with other types of modeling methodologies (e.g., UL and SysML) and its viability as a conceptual base for the management and control of engineering systems.
{"title":"Control of Waste Water Treatment as a Flow Machine: A Case Study","authors":"S. Al-Fedaghi, Reem Al-Azmi","doi":"10.23919/IConAC.2018.8748989","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8748989","url":null,"abstract":"Several different modeling languages and notations are used in diverse engineering disciplines for modeling of system processes and for control and monitoring functions. This paper applies a recently proposed diagrammatic language called the Flowthing Machine (FM) model to modeling the process diagrams of a currently existing waste water treatment facility. The modeling includes depictions of components and operations of the project to achieve a holistic picture for engineers. The resultant schemata demonstrate the advantages of the proposed modeling technique in comparison with other types of modeling methodologies (e.g., UL and SysML) and its viability as a conceptual base for the management and control of engineering systems.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114824376","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749011
Xiaoke Su, H. Yue
The high demand side cost of electric vehicles (EVs) affects the wide use of EVs in practice. In this paper, a mathematical model is built to investigate the cost of the demand side by controlling EVs charging and discharging status, so that the demand side cost can be minimised under given tariffs. The battery degradation cost, the driving probability and the vehicle-to-grid (V2G) rebates are considered in the model. The most economic charging and discharging strategy for each EV can be determined through global optimisation. Simulation studies demonstrate the cost reduction through optimization.
{"title":"Cost Minimization Control for Smart Electric Vehicle Car Parks","authors":"Xiaoke Su, H. Yue","doi":"10.23919/IConAC.2018.8749011","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749011","url":null,"abstract":"The high demand side cost of electric vehicles (EVs) affects the wide use of EVs in practice. In this paper, a mathematical model is built to investigate the cost of the demand side by controlling EVs charging and discharging status, so that the demand side cost can be minimised under given tariffs. The battery degradation cost, the driving probability and the vehicle-to-grid (V2G) rebates are considered in the model. The most economic charging and discharging strategy for each EV can be determined through global optimisation. Simulation studies demonstrate the cost reduction through optimization.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114216037","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749063
Xude Dong, Yuanping Xu, Zhijie Xu, Jian Huang, Jun Lu, Chaolong Zhang, Li Lu
In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.
{"title":"A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN","authors":"Xude Dong, Yuanping Xu, Zhijie Xu, Jian Huang, Jun Lu, Chaolong Zhang, Li Lu","doi":"10.23919/IConAC.2018.8749063","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749063","url":null,"abstract":"In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126587524","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：