Pub Date : 2017-03-31DOI: 10.1109/ICSIPA.2017.8120614
Kourosh Meshgi, Maryam Sadat Mirzaei, Shigeyuki Oba, S. Ishii
Adaptive tracking-by-detection approaches are popular for tracking arbitrary objects. They treat the tracking problem as a classification task and use online learning techniques to update the object model. However, these approaches are heavily invested in the efficiency and effectiveness of their detectors. Evaluating a massive number of samples for each frame (e.g., obtained by a sliding window) forces the detector to trade the accuracy in favor of speed. Furthermore, mis-classification of borderline samples in the detector introduce accumulating errors in tracking. In this study, we propose a co-tracking based on the efficient cooperation of two detectors: a rapid adaptive exemplar-based detector and another more sophisticated but slower detector with a long-term memory. The sampling labeling and co-learning of the detectors are conducted by an uncertainty sampling unit, which improves the speed and accuracy of the system. We also introduce a budgeting mechanism which prevents the unbounded growth in the number of examples in the first detector to maintain its rapid response. Experiments demonstrate the efficiency and effectiveness of the proposed tracker against its baselines and its superior performance against state-of-the-art trackers on various benchmark videos.
{"title":"Efficient asymmetric co-tracking using uncertainty sampling","authors":"Kourosh Meshgi, Maryam Sadat Mirzaei, Shigeyuki Oba, S. Ishii","doi":"10.1109/ICSIPA.2017.8120614","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120614","url":null,"abstract":"Adaptive tracking-by-detection approaches are popular for tracking arbitrary objects. They treat the tracking problem as a classification task and use online learning techniques to update the object model. However, these approaches are heavily invested in the efficiency and effectiveness of their detectors. Evaluating a massive number of samples for each frame (e.g., obtained by a sliding window) forces the detector to trade the accuracy in favor of speed. Furthermore, mis-classification of borderline samples in the detector introduce accumulating errors in tracking. In this study, we propose a co-tracking based on the efficient cooperation of two detectors: a rapid adaptive exemplar-based detector and another more sophisticated but slower detector with a long-term memory. The sampling labeling and co-learning of the detectors are conducted by an uncertainty sampling unit, which improves the speed and accuracy of the system. We also introduce a budgeting mechanism which prevents the unbounded growth in the number of examples in the first detector to maintain its rapid response. Experiments demonstrate the efficiency and effectiveness of the proposed tracker against its baselines and its superior performance against state-of-the-art trackers on various benchmark videos.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123833305","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120590
A. T. Amin, Ashrani Aizzuddin Abd. Rahni, S. S. Mokri, Rozilawati Ahmad
Cone-beam CT (CBCT) imaging is heavily being utilized in radiotherapy treatment as means of treating cancer patients. One of the platforms is the Varian On-Board Imager (oBI) where kilo-volts (kV) CBCT imaging is used. In this study, a model of the OBI is developed to simulate the two scan modes that are available, namely: Full-Fan (FF) and Half-Fan (HF) modes. By shifting the same set of 1024×768 detector panels laterally, a larger field-of-view (FOV) is achieved in the HF scan mode. Using a realistic XCAT phantom, the different FOVs are simulated using analytical Feldkamp-Davis-Kress (FDK) and iterative Simultaneous Algebraic Reconstruction Technique (SART) reconstruction methods. As suggested in literatures, ring and radiant artifacts can occur in the HF mode due to its geometry. To implement fast analytical method, an adequate weight factor needs to be applied on the projection data prior to reconstruction. The percentage normalized root mean squared error (NRMSE) value for FF and HF using analytical FDK reconstruction are 7.12% and 16.63% respectively. Using the iterative SART, the respective values are and 2.69% and 4.65%. The simulation model of the Varian OBI: CBCT operating mode is expected to encourage and enhance further studies on image guided radiation therapy (IGRT) during radiotherapy treatment delivery.
{"title":"Modeling the Varian On-Board Imager (OBI): Cone-beam CT (CBCT) operating modes","authors":"A. T. Amin, Ashrani Aizzuddin Abd. Rahni, S. S. Mokri, Rozilawati Ahmad","doi":"10.1109/ICSIPA.2017.8120590","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120590","url":null,"abstract":"Cone-beam CT (CBCT) imaging is heavily being utilized in radiotherapy treatment as means of treating cancer patients. One of the platforms is the Varian On-Board Imager (oBI) where kilo-volts (kV) CBCT imaging is used. In this study, a model of the OBI is developed to simulate the two scan modes that are available, namely: Full-Fan (FF) and Half-Fan (HF) modes. By shifting the same set of 1024×768 detector panels laterally, a larger field-of-view (FOV) is achieved in the HF scan mode. Using a realistic XCAT phantom, the different FOVs are simulated using analytical Feldkamp-Davis-Kress (FDK) and iterative Simultaneous Algebraic Reconstruction Technique (SART) reconstruction methods. As suggested in literatures, ring and radiant artifacts can occur in the HF mode due to its geometry. To implement fast analytical method, an adequate weight factor needs to be applied on the projection data prior to reconstruction. The percentage normalized root mean squared error (NRMSE) value for FF and HF using analytical FDK reconstruction are 7.12% and 16.63% respectively. Using the iterative SART, the respective values are and 2.69% and 4.65%. The simulation model of the Varian OBI: CBCT operating mode is expected to encourage and enhance further studies on image guided radiation therapy (IGRT) during radiotherapy treatment delivery.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114975623","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120583
M. Z. Baharuddin, Y. Izumi, J. Sumantyo, S. Demirci
Synthetic aperture radar (SAR) imaging is typically performed using linearly polarized (LP) signals. There are not many SAR systems utilizing circularly polarized (CP) signals. Recent trends show investigation into CP such as Compact SAR resulting in reduced system size and images with distinct characteristics due to CP signals. To gain insight into a full CP SAR system, we begin study in a controlled environment. This paper presents the design and testing of a wideband inverse synthetic aperture radar (ISAR) system using CP antennas for both receive and transmit. Data measurement setup was constructed in an anechoic chamber with the use of a vector network analyzer (VNA) and automated rotary turntable to revolve targets. We present the measurement procedures for CP imaging, followed by imaging results of canonical targets made using uncalibrated data for CP and compared them with LP ISAR images to illustrate the differences between the two polarizations. This work will lead to the investigation of generating images from CP receive and transmit signals, CP polarimetric decomposition, improvement of related imaging algorithms for CP signals and suitable antenna design.
{"title":"ISAR imaging using circularly polarized antennas in an anechoic chamber","authors":"M. Z. Baharuddin, Y. Izumi, J. Sumantyo, S. Demirci","doi":"10.1109/ICSIPA.2017.8120583","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120583","url":null,"abstract":"Synthetic aperture radar (SAR) imaging is typically performed using linearly polarized (LP) signals. There are not many SAR systems utilizing circularly polarized (CP) signals. Recent trends show investigation into CP such as Compact SAR resulting in reduced system size and images with distinct characteristics due to CP signals. To gain insight into a full CP SAR system, we begin study in a controlled environment. This paper presents the design and testing of a wideband inverse synthetic aperture radar (ISAR) system using CP antennas for both receive and transmit. Data measurement setup was constructed in an anechoic chamber with the use of a vector network analyzer (VNA) and automated rotary turntable to revolve targets. We present the measurement procedures for CP imaging, followed by imaging results of canonical targets made using uncalibrated data for CP and compared them with LP ISAR images to illustrate the differences between the two polarizations. This work will lead to the investigation of generating images from CP receive and transmit signals, CP polarimetric decomposition, improvement of related imaging algorithms for CP signals and suitable antenna design.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132953804","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120595
Ali Taheri Anaraki, U. U. Sheikh, A. Rahman, Z. Omar
Content-based image retrieval methods use color, texture and shape of an object for indexing and retrieval. Among these features, shape is a basic visual feature that holds significant information of the object. In this paper an alphabetic contour-based shape description method is proposed to facilitate shape classification and retrieval. The proposed method breaks down shape's contour into small segments and assigns unique alphabetic symbol for each segment based on its geometrical features. These symbols are used to create feature string which we call it, an alphabet string. The alphabet strings are compared together using dynamic programming during classification. The proposed method was tested on BROWN dataset that consists of occluded, articulated and missing part shapes. Results show the feasibility of the method and highlight its advantages over some state-of-the art methods.
{"title":"An alphabetic contour-based descriptor for shape-based image retrieval","authors":"Ali Taheri Anaraki, U. U. Sheikh, A. Rahman, Z. Omar","doi":"10.1109/ICSIPA.2017.8120595","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120595","url":null,"abstract":"Content-based image retrieval methods use color, texture and shape of an object for indexing and retrieval. Among these features, shape is a basic visual feature that holds significant information of the object. In this paper an alphabetic contour-based shape description method is proposed to facilitate shape classification and retrieval. The proposed method breaks down shape's contour into small segments and assigns unique alphabetic symbol for each segment based on its geometrical features. These symbols are used to create feature string which we call it, an alphabet string. The alphabet strings are compared together using dynamic programming during classification. The proposed method was tested on BROWN dataset that consists of occluded, articulated and missing part shapes. Results show the feasibility of the method and highlight its advantages over some state-of-the art methods.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"482 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134339535","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120616
F. Jumain, N. A. A. Nazari, Muhammad Fadzil Bin Mashor, Wan Mohamed Haikal Bin Wan Nizamuddin, Ian Ng Jheng, S. A. Jalil, N. Noor
Most people feel sad or irritable from time to time. They may say they're in a bad mood. A mood disorder is different. It affects a person's everyday emotional state. In psychology, the mood is referred as a positive or a negative emotional state. Due to the complexity and instability of personal mood, assessing and analyzing mood is difficult and inconvenient. This study aims to assess the human psychological mood using human electromagnetic radiation. The body radiation frequencies are measured using body radiation wave detector at the frontal region. The detector is a hand-held frequency meter operated on Mega Hertz range. Twelve healthy students will participate in the experiment. Six of them will be from both gender male and female, from the age 20–24 years old. All of them are free from any disease and medication. Before the experiment is conducted, the background interference is measured using frequency wave detector to ensure that the interference is almost zero. The experiment is conducted in a room for men and a corridor for a woman which is less interference of background reading. After collecting the data statistically, the analysis is being done to validate the data. The measurement is taken after they Prayer (salat) and watch a funny video to get a contra mood which is calm and happy. First, the validation is being performed on the change of mood (increase or decrease in frequency) then if the data show a significant result a relationship between gender and mood is investigated using ANOVA and MANOVA. The result shows a significant result between different in gender and mood assessment.
{"title":"Mood assessment using human electromagnetic radiation","authors":"F. Jumain, N. A. A. Nazari, Muhammad Fadzil Bin Mashor, Wan Mohamed Haikal Bin Wan Nizamuddin, Ian Ng Jheng, S. A. Jalil, N. Noor","doi":"10.1109/ICSIPA.2017.8120616","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120616","url":null,"abstract":"Most people feel sad or irritable from time to time. They may say they're in a bad mood. A mood disorder is different. It affects a person's everyday emotional state. In psychology, the mood is referred as a positive or a negative emotional state. Due to the complexity and instability of personal mood, assessing and analyzing mood is difficult and inconvenient. This study aims to assess the human psychological mood using human electromagnetic radiation. The body radiation frequencies are measured using body radiation wave detector at the frontal region. The detector is a hand-held frequency meter operated on Mega Hertz range. Twelve healthy students will participate in the experiment. Six of them will be from both gender male and female, from the age 20–24 years old. All of them are free from any disease and medication. Before the experiment is conducted, the background interference is measured using frequency wave detector to ensure that the interference is almost zero. The experiment is conducted in a room for men and a corridor for a woman which is less interference of background reading. After collecting the data statistically, the analysis is being done to validate the data. The measurement is taken after they Prayer (salat) and watch a funny video to get a contra mood which is calm and happy. First, the validation is being performed on the change of mood (increase or decrease in frequency) then if the data show a significant result a relationship between gender and mood is investigated using ANOVA and MANOVA. The result shows a significant result between different in gender and mood assessment.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130015964","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120618
Yeng Weng Leong, A. Zuhdi, H. Seki, K. Sahari, N. Razali
Solid-state lighting is a field that has developed rapidly over the recent years. Visible Light Emitting Diode (LED) has achieved higher luminous efficacy than that of incandescent light, subsequently incorporated into many lighting systems in household or in workplaces. Energy saving can be achieved by utilizing adaptive lighting systems which can adapt to ambient lighting. We discuss the ability of LED as an ambient light detector and subsequently propose a solution that would enable the LED to be used to illuminate and detect ambient light simultaneously. The proposed solution simplifies the circuit for illumination and light detection that could potentially reduce hardware cost for detection. This can potentially be used in automated light intensity control based on ambient brightness.
{"title":"Feasibility of proposed simplified circuit in utilizing LED for both lighting and sensing","authors":"Yeng Weng Leong, A. Zuhdi, H. Seki, K. Sahari, N. Razali","doi":"10.1109/ICSIPA.2017.8120618","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120618","url":null,"abstract":"Solid-state lighting is a field that has developed rapidly over the recent years. Visible Light Emitting Diode (LED) has achieved higher luminous efficacy than that of incandescent light, subsequently incorporated into many lighting systems in household or in workplaces. Energy saving can be achieved by utilizing adaptive lighting systems which can adapt to ambient lighting. We discuss the ability of LED as an ambient light detector and subsequently propose a solution that would enable the LED to be used to illuminate and detect ambient light simultaneously. The proposed solution simplifies the circuit for illumination and light detection that could potentially reduce hardware cost for detection. This can potentially be used in automated light intensity control based on ambient brightness.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123613920","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120572
Hadri Hussain, C. Ting, Fuad Numan, M. N. Ibrahim, Nur Fariza Izan, M. M. Mohammad, Hadrina Sh-Hussain
The most common application for a recognition system of speech signal, finger print, iris, etc. are used for biometrie applications. While other biometric signals like electrocardiogram (ECG) and the Heart Sound (HS) are generally used to identify cluster-related diseases. Nonetheless, performance of a traditional biometric system can be easily compromised as it is prone to spoof attack. This paper proposes a unimodal biometric security system that is based on ECG. Physiological biometrics characteristic are based on a human body's, such as the hand geometry, face, palm, ECG and even brain signal. The biosignal data collected by a biometric system would initially be segmented. The Mel-Frequency Cepstral Coefficients (MFCC) method is used for extracting each segmented feature. The Hidden Markov Model (HMM) is used to model the client, and categorize unknown input based on the model. The recognition system involved training and testing of the collected features, known as Client Identification (CID). In this paper, 20 clients were tested with this developed system. The best overall performance for 20 clients at 16 kHz was 71.4% for ECG trained at 50% of the training data, while the worst overall performance was 66.6% for 30% training data.
{"title":"Analysis of ECG biosignal recognition for client identifiction","authors":"Hadri Hussain, C. Ting, Fuad Numan, M. N. Ibrahim, Nur Fariza Izan, M. M. Mohammad, Hadrina Sh-Hussain","doi":"10.1109/ICSIPA.2017.8120572","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120572","url":null,"abstract":"The most common application for a recognition system of speech signal, finger print, iris, etc. are used for biometrie applications. While other biometric signals like electrocardiogram (ECG) and the Heart Sound (HS) are generally used to identify cluster-related diseases. Nonetheless, performance of a traditional biometric system can be easily compromised as it is prone to spoof attack. This paper proposes a unimodal biometric security system that is based on ECG. Physiological biometrics characteristic are based on a human body's, such as the hand geometry, face, palm, ECG and even brain signal. The biosignal data collected by a biometric system would initially be segmented. The Mel-Frequency Cepstral Coefficients (MFCC) method is used for extracting each segmented feature. The Hidden Markov Model (HMM) is used to model the client, and categorize unknown input based on the model. The recognition system involved training and testing of the collected features, known as Client Identification (CID). In this paper, 20 clients were tested with this developed system. The best overall performance for 20 clients at 16 kHz was 71.4% for ECG trained at 50% of the training data, while the worst overall performance was 66.6% for 30% training data.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129937417","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120674
N. A. A. Nazari, N. M. Fauzi, N. Rosli, S. N. Zakaria, S. A. Jalil, N. Noor
This technical paper investigates the physiology of human fatigue using human electromagnetic radiation. Fatigue is a feeling of tiredness that arrives from the excessive working time or workload, prolong exertion, sleep loss or and or disruption of the internal clock. It can be divided into two, mental and physical causes which decline in mental or physical performances. The purpose of this study is basically to study the frequency of human fatigue before and after exercise also to evaluate the physiological characteristic frequency of human fatigue by using human electromagnetic radiation. The frequency measurement is taken from 10 students including 5 male and 5 female. The data were analyzed using a T-test to find differences in frequency of mean before and after exercise. The results demonstrate that there were statistically significant differences at the certain measured point. Based on the result presented, it can conclude that there were statistically significant differences between mean before and after exercise. Consequently, mean before exercise is higher than mean after exercise.
{"title":"Physiological studies of human fatigue using human electromagnetic radiation","authors":"N. A. A. Nazari, N. M. Fauzi, N. Rosli, S. N. Zakaria, S. A. Jalil, N. Noor","doi":"10.1109/ICSIPA.2017.8120674","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120674","url":null,"abstract":"This technical paper investigates the physiology of human fatigue using human electromagnetic radiation. Fatigue is a feeling of tiredness that arrives from the excessive working time or workload, prolong exertion, sleep loss or and or disruption of the internal clock. It can be divided into two, mental and physical causes which decline in mental or physical performances. The purpose of this study is basically to study the frequency of human fatigue before and after exercise also to evaluate the physiological characteristic frequency of human fatigue by using human electromagnetic radiation. The frequency measurement is taken from 10 students including 5 male and 5 female. The data were analyzed using a T-test to find differences in frequency of mean before and after exercise. The results demonstrate that there were statistically significant differences at the certain measured point. Based on the result presented, it can conclude that there were statistically significant differences between mean before and after exercise. Consequently, mean before exercise is higher than mean after exercise.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122507416","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120640
Mohd Salzahrin Mohd Hamzah, O. M. Rijal, N. A. Mokhtar, N. Noor
A novel procedure to determine foot shape is propose. The relationship between shape features is used to discriminate shape. Five foot shape features that are Left Foot Length (LFL), Left Foot Breadth (LFB), Left Ball Girth Circumference (LBGC), Left Instep Length (LIL) and Left Fibulare Instep Length (LFIL) from a random sample of 161 Malaysians ladies were studied. Two groups of foot shape feature obtained from standard clustering procedure were then used to discriminate foot shape using piecewise regression. A two component piecewise regression model using LFB and LBGC give the best fit to the data showing two categories of foot shape.
{"title":"Piecewise regression for determining Malaysian woman foot shape","authors":"Mohd Salzahrin Mohd Hamzah, O. M. Rijal, N. A. Mokhtar, N. Noor","doi":"10.1109/ICSIPA.2017.8120640","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120640","url":null,"abstract":"A novel procedure to determine foot shape is propose. The relationship between shape features is used to discriminate shape. Five foot shape features that are Left Foot Length (LFL), Left Foot Breadth (LFB), Left Ball Girth Circumference (LBGC), Left Instep Length (LIL) and Left Fibulare Instep Length (LFIL) from a random sample of 161 Malaysians ladies were studied. Two groups of foot shape feature obtained from standard clustering procedure were then used to discriminate foot shape using piecewise regression. A two component piecewise regression model using LFB and LBGC give the best fit to the data showing two categories of foot shape.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"263 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115287696","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 : 1900-01-01DOI: 10.1109/ICSIPA.2017.8120569
Mok Win Soon, Muhammad Ikmal Hanafi Anuar, Mohamad Hafizat Zainal Abidin, Ahmad Syukri Azaman, N. Noor
This paper presents a study of speech recognition based on electromyographic biosignals captured from the articulatory muscles in the face using surface electrodes. This paper compares the speech recognition system for spoken English and Malay words by a group of Malay native speakers. Feature extraction was done in both temporal and time-frequency domains. Temporal features used are integrated EMG (IEMG), mean absolute value (MAV), root mean square (RMS), variance (VAR), standard deviation (SD), and simple square integral (SSI) where time-frequency domain features were obtained using discrete wavelet transform. For classification, random forest classifier and ANNs multilayer perceptron both gave the overall best performance on using temporal features and time-frequency features respectively. The result of the classification shows that the Malay language is can be used in sEMG speech recognition.
{"title":"Speech recognition using facial sEMG","authors":"Mok Win Soon, Muhammad Ikmal Hanafi Anuar, Mohamad Hafizat Zainal Abidin, Ahmad Syukri Azaman, N. Noor","doi":"10.1109/ICSIPA.2017.8120569","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120569","url":null,"abstract":"This paper presents a study of speech recognition based on electromyographic biosignals captured from the articulatory muscles in the face using surface electrodes. This paper compares the speech recognition system for spoken English and Malay words by a group of Malay native speakers. Feature extraction was done in both temporal and time-frequency domains. Temporal features used are integrated EMG (IEMG), mean absolute value (MAV), root mean square (RMS), variance (VAR), standard deviation (SD), and simple square integral (SSI) where time-frequency domain features were obtained using discrete wavelet transform. For classification, random forest classifier and ANNs multilayer perceptron both gave the overall best performance on using temporal features and time-frequency features respectively. The result of the classification shows that the Malay language is can be used in sEMG speech recognition.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127329368","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：