Pub Date : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120638
R. Lim, Clarence Weihan Cheong, John See, I. Tan, L. Wong, Huai-Qian Khor
Car park video surveillance systems present a huge volume of data that can be beneficial for video analytics and data analysis. We present a vehicle state tracking method for long term video surveillance with the goal of obtaining trajectories and vehicle states of various car park users. However, this is a challenging task in outdoor scenarios due to non-optimal camera viewing angle compounded by ever-changing illumination & weather conditions. To address these challenges, we propose a parking state machine that tracks the vehicle state in a large outdoor car park area. The proposed method was tested on 10 hours of continuous video data with various illumination and environmental conditions. Owing to the imbalanced distribution of parking states, we report the precision, recall and F1 scores to determine the overall performance of the system. Our approach proves to be fairly accurate, fast and robust against severe scene variations.
{"title":"On vehicle state tracking for long-term carpark video surveillance","authors":"R. Lim, Clarence Weihan Cheong, John See, I. Tan, L. Wong, Huai-Qian Khor","doi":"10.1109/ICSIPA.2017.8120638","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120638","url":null,"abstract":"Car park video surveillance systems present a huge volume of data that can be beneficial for video analytics and data analysis. We present a vehicle state tracking method for long term video surveillance with the goal of obtaining trajectories and vehicle states of various car park users. However, this is a challenging task in outdoor scenarios due to non-optimal camera viewing angle compounded by ever-changing illumination & weather conditions. To address these challenges, we propose a parking state machine that tracks the vehicle state in a large outdoor car park area. The proposed method was tested on 10 hours of continuous video data with various illumination and environmental conditions. Owing to the imbalanced distribution of parking states, we report the precision, recall and F1 scores to determine the overall performance of the system. Our approach proves to be fairly accurate, fast and robust against severe scene variations.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115832987","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120580
J. Shah, Hassaan Haider, K. Kadir, Sheroz Khan
Compressed Sensing is a novel sampling technique that can be used to faithfully recover sparse signals from fewer measurements than those proposed by the Nyquist theorem. A simple and intuitive measure of sparsity in a signal is ℓ0-norm. However, the ℓ0-norm function does not satisfy all the axiomatic properties of a true mathematical norm. The discrete and discontinuous nature of ℓ0-norm poses many challenges in its applications to recover sparse signals from their subsampled measurements. This paper presents, a novel mathematical function that can be used to closely approximate the ℓ0-norm. The proposed function is smooth and differentiable that allows gradient based algorithms to be used in the reconstruction of sparse signals. We use the proposed approximation along with steepest ascent method to develop a complete sparse signal recovery algorithm for the compressed sensing framework. Experimental results have shown that the proposed recovery algorithm outperforms the conventional SL0 method in terms of reconstruction accuracy such as Mean Square Error (MSE) and Signal-to-Noise Ratio (SNR).
{"title":"Sparse signal reconstruction of compressively sampled signals using smoothed ℓ0-norm","authors":"J. Shah, Hassaan Haider, K. Kadir, Sheroz Khan","doi":"10.1109/ICSIPA.2017.8120580","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120580","url":null,"abstract":"Compressed Sensing is a novel sampling technique that can be used to faithfully recover sparse signals from fewer measurements than those proposed by the Nyquist theorem. A simple and intuitive measure of sparsity in a signal is ℓ0-norm. However, the ℓ0-norm function does not satisfy all the axiomatic properties of a true mathematical norm. The discrete and discontinuous nature of ℓ0-norm poses many challenges in its applications to recover sparse signals from their subsampled measurements. This paper presents, a novel mathematical function that can be used to closely approximate the ℓ0-norm. The proposed function is smooth and differentiable that allows gradient based algorithms to be used in the reconstruction of sparse signals. We use the proposed approximation along with steepest ascent method to develop a complete sparse signal recovery algorithm for the compressed sensing framework. Experimental results have shown that the proposed recovery algorithm outperforms the conventional SL0 method in terms of reconstruction accuracy such as Mean Square Error (MSE) and Signal-to-Noise Ratio (SNR).","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116196817","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120625
E. Hasan, R. Ibrahim, Kishore Bingi, S. Hassan, Syed Faizan-ul-Haq Gilani
Nonlinear behaviour of the systems happens to be a common problem in industrial processes. They cause a large amount of time, resources and efforts to be utilized in order to deal with them. A Major hurdle in Nonlinear Industrial Processes is system modeling. Due to this reason, several methods and techniques have been designed and developed in order to improve the overall control performance in industrial process control. Model based controllers have been developed and implemented on various applications with promising results. Their main benefit is they can identify and tune unknown system parameters in real-time. This paper focuses on real-time controller development and its implementation on Gas Pressure Process Plant using MPC. MPC is considered to be one of the robust and effective controllers due to impressive control performance in different applications previously. MPC makes use of a model for system identification and based upon that, it can dynamically send next control move for the system. This research work incorporates State-Space Model for unknown system-parameter identification. The identified parameters will be utilized by MPC for control law development. The proposed methodology is validated by real-time experimental results on the aforementioned system.
{"title":"Real-time model predictive control for nonlinear gas pressure process plant","authors":"E. Hasan, R. Ibrahim, Kishore Bingi, S. Hassan, Syed Faizan-ul-Haq Gilani","doi":"10.1109/ICSIPA.2017.8120625","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120625","url":null,"abstract":"Nonlinear behaviour of the systems happens to be a common problem in industrial processes. They cause a large amount of time, resources and efforts to be utilized in order to deal with them. A Major hurdle in Nonlinear Industrial Processes is system modeling. Due to this reason, several methods and techniques have been designed and developed in order to improve the overall control performance in industrial process control. Model based controllers have been developed and implemented on various applications with promising results. Their main benefit is they can identify and tune unknown system parameters in real-time. This paper focuses on real-time controller development and its implementation on Gas Pressure Process Plant using MPC. MPC is considered to be one of the robust and effective controllers due to impressive control performance in different applications previously. MPC makes use of a model for system identification and based upon that, it can dynamically send next control move for the system. This research work incorporates State-Space Model for unknown system-parameter identification. The identified parameters will be utilized by MPC for control law development. The proposed methodology is validated by real-time experimental results on the aforementioned system.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120951366","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120587
Afiqah Abu Samah, M. F. A. Fauzi, Sarina Mansor
Breast cancer leads the list of cancer that act on women worldwide. It starts when cells in the breast begin to build up beyond control. These cells normally create a tumour that can usually be seen on an x-ray or felt as a lump. Analysing and grading the tumour will take up much of a pathologist time. Pathologists have been largely diagnosing disease the same way for the past years, by manually reviewing images under a microscope. Thus, to help the pathologists improve accuracy and significantly change the way breast cancer been diagnosed, this paper presents an automated classification program. BreakHis dataset was used which build of 7909 breast tumor images gathered from 82 patients. This system is developed in order to categorize the cancer cells into two classes of cancer which are benign and malignant. The classification system compared different types of feature extractors using k-nearest neighbours classifier to efficiently observe the performance of the classification system. An extensive set of experiments showed that the overall accuracy rates range from 83% to 86%.
{"title":"Classification of benign and malignant tumors in histopathology images","authors":"Afiqah Abu Samah, M. F. A. Fauzi, Sarina Mansor","doi":"10.1109/ICSIPA.2017.8120587","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120587","url":null,"abstract":"Breast cancer leads the list of cancer that act on women worldwide. It starts when cells in the breast begin to build up beyond control. These cells normally create a tumour that can usually be seen on an x-ray or felt as a lump. Analysing and grading the tumour will take up much of a pathologist time. Pathologists have been largely diagnosing disease the same way for the past years, by manually reviewing images under a microscope. Thus, to help the pathologists improve accuracy and significantly change the way breast cancer been diagnosed, this paper presents an automated classification program. BreakHis dataset was used which build of 7909 breast tumor images gathered from 82 patients. This system is developed in order to categorize the cancer cells into two classes of cancer which are benign and malignant. The classification system compared different types of feature extractors using k-nearest neighbours classifier to efficiently observe the performance of the classification system. An extensive set of experiments showed that the overall accuracy rates range from 83% to 86%.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116585274","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120652
A. Kale, S. Sonavane
The crucial objective of this paper is to design a hybrid model of the genetic algorithm for fuzzy extreme learning machine classifier (GA-FELM), which selects an optimal feature subset by using the multilevel parameter optimization technique. Feature subset selection is an important task in pattern classification and knowledge discovery problems. The generalization performance of the system is not only depending on optimal features but also dependent upon the classifier (learning algorithm). Therefore, it is an important task to select a fast and efficient classifier. Research efforts have affirmed that extreme learning machine (ELM) has superior and accurate classification ability. However, ELM is failed to handle the uncertain data. One of the alternative solutions is fuzzy-ELM, which combines the advantages of fuzzy logic and ELM. GA-FELM is able to handle curse of dimensionality problem, optimization problem and weighted classification problem with maximizing classification accuracy by minimizing the number of features. In order to validate the efficiency of GA-FELM, the comparative performance is evaluated by using three different approaches viz. 1. ELM and GA-ELM 2. GA-ELM and GA-FELM 3. GA-FELM and GA-existing classifier. The result analysis shows that classification accuracy is improved with 9% while reducing 62% features.
{"title":"Optimal feature subset selection for fuzzy extreme learning machine using genetic algorithm with multilevel parameter optimization","authors":"A. Kale, S. Sonavane","doi":"10.1109/ICSIPA.2017.8120652","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120652","url":null,"abstract":"The crucial objective of this paper is to design a hybrid model of the genetic algorithm for fuzzy extreme learning machine classifier (GA-FELM), which selects an optimal feature subset by using the multilevel parameter optimization technique. Feature subset selection is an important task in pattern classification and knowledge discovery problems. The generalization performance of the system is not only depending on optimal features but also dependent upon the classifier (learning algorithm). Therefore, it is an important task to select a fast and efficient classifier. Research efforts have affirmed that extreme learning machine (ELM) has superior and accurate classification ability. However, ELM is failed to handle the uncertain data. One of the alternative solutions is fuzzy-ELM, which combines the advantages of fuzzy logic and ELM. GA-FELM is able to handle curse of dimensionality problem, optimization problem and weighted classification problem with maximizing classification accuracy by minimizing the number of features. In order to validate the efficiency of GA-FELM, the comparative performance is evaluated by using three different approaches viz. 1. ELM and GA-ELM 2. GA-ELM and GA-FELM 3. GA-FELM and GA-existing classifier. The result analysis shows that classification accuracy is improved with 9% while reducing 62% features.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132384930","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120663
Rahul Hooda, S. Sofat, Simranpreet Kaur, Ajay Mittal, F. Mériaudeau
Tuberculosis (TB) is a major health threat in the developing countries. Many patients die every year due to lack of treatment and error in diagnosis. Developing a computer-aided diagnosis (CAD) system for TB detection can help in early diagnosis and containing the disease. Most of the current CAD systems use handcrafted features, however, lately there is a shift towards deep-learning-based automatic feature extractors. In this paper, we present a potential method for tuberculosis detection using deep-learning which classifies CXR images into two categories, that is, normal and abnormal. We have used CNN architecture with 7 convolutional layers and 3 fully connected layers. The performance of three different optimizers has been compared. Out of these, Adam optimizer with an overall accuracy of 94.73% and validation accuracy of 82.09% performed best amongst them. All the results are obtained using Montgomery and Shenzhen datasets which are available in public domain.
{"title":"Deep-learning: A potential method for tuberculosis detection using chest radiography","authors":"Rahul Hooda, S. Sofat, Simranpreet Kaur, Ajay Mittal, F. Mériaudeau","doi":"10.1109/ICSIPA.2017.8120663","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120663","url":null,"abstract":"Tuberculosis (TB) is a major health threat in the developing countries. Many patients die every year due to lack of treatment and error in diagnosis. Developing a computer-aided diagnosis (CAD) system for TB detection can help in early diagnosis and containing the disease. Most of the current CAD systems use handcrafted features, however, lately there is a shift towards deep-learning-based automatic feature extractors. In this paper, we present a potential method for tuberculosis detection using deep-learning which classifies CXR images into two categories, that is, normal and abnormal. We have used CNN architecture with 7 convolutional layers and 3 fully connected layers. The performance of three different optimizers has been compared. Out of these, Adam optimizer with an overall accuracy of 94.73% and validation accuracy of 82.09% performed best amongst them. All the results are obtained using Montgomery and Shenzhen datasets which are available in public domain.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134080171","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120630
R. Zafar, A. Malik, Aliyu Nuhu Shuaibu, M. J. U. Rehman, S. Dass
In recent years convolutional neural network have obtained more popularity because of its progressive performance for different applications especially for object recognition. In neuroimaging, data varies from person to person and condition to condition so it is always a challenging job to model the brain data. Any analysis in neuroimaging is also dependent on the quality of data and currently, functional magnetic resonance imaging is considered as the best among all techniques. It is most reliable and popular modality to measure the brain activity patterns. In fMRI, region of interest is a common method of analysis in which data is taken from a specific brain region based on the structural or functional information. In this study, convolutional neural network is applied to the significant voxels obtained through the t-contrast of the design matrix during the ROI analysis. Data is taken against two conditions and 1000 significant voxels with highest absolute values are taken for each condition for further analysis. During the proposed method, analysis is performed using convolutional neural network along with ROI analysis. Support vector machine is used in the classification of both methods; ROI and proposed methods. In conclusion, it is shown that the features extracted through convolutional neural network can provide better significant results compared to the other one.
{"title":"Classification of fMRI data using support vector machine and convolutional neural network","authors":"R. Zafar, A. Malik, Aliyu Nuhu Shuaibu, M. J. U. Rehman, S. Dass","doi":"10.1109/ICSIPA.2017.8120630","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120630","url":null,"abstract":"In recent years convolutional neural network have obtained more popularity because of its progressive performance for different applications especially for object recognition. In neuroimaging, data varies from person to person and condition to condition so it is always a challenging job to model the brain data. Any analysis in neuroimaging is also dependent on the quality of data and currently, functional magnetic resonance imaging is considered as the best among all techniques. It is most reliable and popular modality to measure the brain activity patterns. In fMRI, region of interest is a common method of analysis in which data is taken from a specific brain region based on the structural or functional information. In this study, convolutional neural network is applied to the significant voxels obtained through the t-contrast of the design matrix during the ROI analysis. Data is taken against two conditions and 1000 significant voxels with highest absolute values are taken for each condition for further analysis. During the proposed method, analysis is performed using convolutional neural network along with ROI analysis. Support vector machine is used in the classification of both methods; ROI and proposed methods. In conclusion, it is shown that the features extracted through convolutional neural network can provide better significant results compared to the other one.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"106 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133136146","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120643
F. Goodarzi, F. Rokhani, M. Saripan, M. Marhaban
The problem of recognizing and discriminating mixed emotions in multi view faces using a web camera is discussed in this paper. Based on the literature, there are mainly seven basic emotions that humans can express and understand. However, in some faces in databases, there are characteristics of two or more of this basic emotions. The two databases of BU3DFE and UPM3DFE were tested for mixed emotion accuracy using the proposed multi view face emotion recognition method. The results show an improvement over existing works in mixed emotions recognition.
{"title":"Mixed emotions in multi view face emotion recognition","authors":"F. Goodarzi, F. Rokhani, M. Saripan, M. Marhaban","doi":"10.1109/ICSIPA.2017.8120643","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120643","url":null,"abstract":"The problem of recognizing and discriminating mixed emotions in multi view faces using a web camera is discussed in this paper. Based on the literature, there are mainly seven basic emotions that humans can express and understand. However, in some faces in databases, there are characteristics of two or more of this basic emotions. The two databases of BU3DFE and UPM3DFE were tested for mixed emotion accuracy using the proposed multi view face emotion recognition method. The results show an improvement over existing works in mixed emotions recognition.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133710779","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120660
S. J. S. Gardezi, M. Awais, I. Faye, F. Mériaudeau
This paper presents a method for classification of normal and abnormal tissues in mammograms using a deep learning approach. VGG-16 CNN deep learning architecture with convolutional filter of (3×3) is implemented on mammograms ROIs from the IRMA dataset. The deep feature matrix is computed from first fully connected layer. The results are evaluated using 10 fold cross validation on SVM, binary trees, simple logistics and KNN (with k=1, 3, 5) classifiers. The method produced 100% classification accuracies with AUC 1.0.
{"title":"Mammogram classification using deep learning features","authors":"S. J. S. Gardezi, M. Awais, I. Faye, F. Mériaudeau","doi":"10.1109/ICSIPA.2017.8120660","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120660","url":null,"abstract":"This paper presents a method for classification of normal and abnormal tissues in mammograms using a deep learning approach. VGG-16 CNN deep learning architecture with convolutional filter of (3×3) is implemented on mammograms ROIs from the IRMA dataset. The deep feature matrix is computed from first fully connected layer. The results are evaluated using 10 fold cross validation on SVM, binary trees, simple logistics and KNN (with k=1, 3, 5) classifiers. The method produced 100% classification accuracies with AUC 1.0.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121210210","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120574
Rija Hasan, S. Monir
In this paper an efficient approach of fruit maturity classification based on apparent color of the specimen is implemented by the aid of fuzzy inference system (FIS). Heuristically acquired hue and its corresponding saturation and lightness are the attributes of choice, which are utilized to classify the sample into three classes; Raw, Ripe, and Overripe. The membership functions and fuzzy rules required by the Mamdani FIS are estimated by the approach of classification tree. The experimentation is performed upon 200 guava samples. The fuzzy system is trained upon 60% of the dataset, yielding 93.4% classification accuracy.
{"title":"Fruit maturity estimation based on fuzzy classification","authors":"Rija Hasan, S. Monir","doi":"10.1109/ICSIPA.2017.8120574","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120574","url":null,"abstract":"In this paper an efficient approach of fruit maturity classification based on apparent color of the specimen is implemented by the aid of fuzzy inference system (FIS). Heuristically acquired hue and its corresponding saturation and lightness are the attributes of choice, which are utilized to classify the sample into three classes; Raw, Ripe, and Overripe. The membership functions and fuzzy rules required by the Mamdani FIS are estimated by the approach of classification tree. The experimentation is performed upon 200 guava samples. The fuzzy system is trained upon 60% of the dataset, yielding 93.4% classification accuracy.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128488604","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：