Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474139
A. Khanna, N. Londhe, Shubhrata Gupta
The problem of pulmonary vessel detection from 3D pulmonary CT Scan is a very challenging one. The identification of vessels is important for clinical evaluation. In this paper, we proposed a vessel segmentation technique based on improved graph cut algorithm by designing the energy function. First of all, the enhanced image is modeled with adaptive k-means algorithm to give the regional parameter of the energy function. Then the improved energy function is given to graph cut algorithm for vessel segmentation. Graph cut algorithm creates a graph which is cut using minimum cut theory. The segmentation is done with the data provided in VESSEL12 site. This automatic segmentation gives quite satisfactory results.
{"title":"Detection of pulmonary vessels in 3D lung CT using improved Graph Cut","authors":"A. Khanna, N. Londhe, Shubhrata Gupta","doi":"10.1109/SPIN.2018.8474139","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474139","url":null,"abstract":"The problem of pulmonary vessel detection from 3D pulmonary CT Scan is a very challenging one. The identification of vessels is important for clinical evaluation. In this paper, we proposed a vessel segmentation technique based on improved graph cut algorithm by designing the energy function. First of all, the enhanced image is modeled with adaptive k-means algorithm to give the regional parameter of the energy function. Then the improved energy function is given to graph cut algorithm for vessel segmentation. Graph cut algorithm creates a graph which is cut using minimum cut theory. The segmentation is done with the data provided in VESSEL12 site. This automatic segmentation gives quite satisfactory results.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133070448","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474231
Padma Ganasala, A. D. Prasad
Medical image fusion presents the information given by different imaging modalities in a single composite image. Fused image provides more clinical information useful for the precise diagnosis, treatment planning and follow-up studies of various diseases. A medical image fusion method based on Frei-Chen operators in nonsubsampled shearlet transform (NSST) domain is presented in this research paper. The proposed method is tested on four multimodality medical image datasets. The visual and quantitative evaluation of fusion results exhibited the superior performance of the proposed image fusion approach.
{"title":"Medical Image Fusion based on Frei-Chen Masks in NSST Domain","authors":"Padma Ganasala, A. D. Prasad","doi":"10.1109/SPIN.2018.8474231","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474231","url":null,"abstract":"Medical image fusion presents the information given by different imaging modalities in a single composite image. Fused image provides more clinical information useful for the precise diagnosis, treatment planning and follow-up studies of various diseases. A medical image fusion method based on Frei-Chen operators in nonsubsampled shearlet transform (NSST) domain is presented in this research paper. The proposed method is tested on four multimodality medical image datasets. The visual and quantitative evaluation of fusion results exhibited the superior performance of the proposed image fusion approach.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133471838","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474052
Rajat Sharma, Nishtha Agarwal, Krittika Khanwalkar, Manasvee Singh, Dharmendra Kumar
In the direction of attaining greater robustness against various signal processing operations, this paper proposes a new image watermarking scheme in multiple transform domain. Firstly, the host image is decomposed using Discrete Wavelet Transform (DWT) and the lower frequency subband is obtained. This subband is further decomposed using two-level Coutourlet Transform(CT) wherein the first level approximate subband is used to evaluate the optimized modification parameters and the second level detail subband is used for watermark embedding. In counterpart of embedding, the watermark bits are extracted based on the guiding factor. Experimental results show higher robustness against various attacks without compromising the image quality.
{"title":"Robust Image Watermarking Technique Using Contourlet Transform and Optimized Edge Detection Algorithm","authors":"Rajat Sharma, Nishtha Agarwal, Krittika Khanwalkar, Manasvee Singh, Dharmendra Kumar","doi":"10.1109/SPIN.2018.8474052","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474052","url":null,"abstract":"In the direction of attaining greater robustness against various signal processing operations, this paper proposes a new image watermarking scheme in multiple transform domain. Firstly, the host image is decomposed using Discrete Wavelet Transform (DWT) and the lower frequency subband is obtained. This subband is further decomposed using two-level Coutourlet Transform(CT) wherein the first level approximate subband is used to evaluate the optimized modification parameters and the second level detail subband is used for watermark embedding. In counterpart of embedding, the watermark bits are extracted based on the guiding factor. Experimental results show higher robustness against various attacks without compromising the image quality.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132700856","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474056
Aman Kumar, R. K. Sunkaria, Lakhan Dev Sharma
In this paper, a PSO based design of CM-NUFB is presented. The coefficients of the prototype filter have been optimized to minimize the passband and stopband energy. Firstly, a uniform CMFB has been designed, and the CM-NUFB has been obtained using merging of adjacent channels of uniform CMFBs. In this work, three, four and five-channel CM-NUFBs have been designed using the proposed method. Pass band energy (Ep), stop band energy (Es) and PRE has been considered for the performance evaluation of CM-NUFB.
{"title":"Design of Cosine Modulated Non-uniform filter bank using Particle Swarm Optimization","authors":"Aman Kumar, R. K. Sunkaria, Lakhan Dev Sharma","doi":"10.1109/SPIN.2018.8474056","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474056","url":null,"abstract":"In this paper, a PSO based design of CM-NUFB is presented. The coefficients of the prototype filter have been optimized to minimize the passband and stopband energy. Firstly, a uniform CMFB has been designed, and the CM-NUFB has been obtained using merging of adjacent channels of uniform CMFBs. In this work, three, four and five-channel CM-NUFBs have been designed using the proposed method. Pass band energy (Ep), stop band energy (Es) and PRE has been considered for the performance evaluation of CM-NUFB.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"352 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131460303","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474202
Roshan Bharti, Rishika Trivedi, P. Padhy
In this paper, a new structure of PID type fuzzy logic controller is proposed in which Fuzzy PI controller and conventional PD controller are connected in parallel. The gains of the proposed controller are calculated by Gradient descent optimization method. Illustrative examples are considered to validate the performance of the proposed structure. The proposed controller outperforms the Conventional PID Controller and existing fuzzy PID Controllers in terms of performance indices for a different plant.
{"title":"Design of Optimized PID Type Fuzzy Logic Controller for Higher Order System","authors":"Roshan Bharti, Rishika Trivedi, P. Padhy","doi":"10.1109/SPIN.2018.8474202","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474202","url":null,"abstract":"In this paper, a new structure of PID type fuzzy logic controller is proposed in which Fuzzy PI controller and conventional PD controller are connected in parallel. The gains of the proposed controller are calculated by Gradient descent optimization method. Illustrative examples are considered to validate the performance of the proposed structure. The proposed controller outperforms the Conventional PID Controller and existing fuzzy PID Controllers in terms of performance indices for a different plant.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115548827","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474037
Gaurav V. Deshmukh, S. Bhandari
Humans interact socially with the help of facial expressions. Even health states or pains are reflected through facial expressions and hence can be useful in healthcare. Here, a facial expression recognition system is proposed. The bandlet transform is performed on face image to generate quadtree. Then on the output of bandlet transform centre symmetric - local binary pattern (CS-LBP) is applied. A feature vector of the image is generated by taking the histogram of CS-LBP. The support vector machine (SVM) is used to classify expressions in six categories. The experiments are performed using a publically available CK+ dataset. The initial results with LBP and CS-LBP are reported.
{"title":"Facial Expression Recognition using Bandlet Transform and Centre Symmetric – Local Binary Pattern","authors":"Gaurav V. Deshmukh, S. Bhandari","doi":"10.1109/SPIN.2018.8474037","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474037","url":null,"abstract":"Humans interact socially with the help of facial expressions. Even health states or pains are reflected through facial expressions and hence can be useful in healthcare. Here, a facial expression recognition system is proposed. The bandlet transform is performed on face image to generate quadtree. Then on the output of bandlet transform centre symmetric - local binary pattern (CS-LBP) is applied. A feature vector of the image is generated by taking the histogram of CS-LBP. The support vector machine (SVM) is used to classify expressions in six categories. The experiments are performed using a publically available CK+ dataset. The initial results with LBP and CS-LBP are reported.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124364857","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474146
Sachin Kumar, S. Palaniswamy, Shobhit Saxena, Rahul Tiwari, Shalini Sah
A planar monopole antenna with enhanced bandwidth and dual-band notching is proposed. The presented UWB monopole antenna is consisting of modified square patch loaded with inverted U-slot to reject WLAN frequencies in the range of 5.15–5.35 and 5.725–5.825 GHz. The ground surface of designed antenna is made up of two L-shaped and two C-shaped slots for achieving wide impedance bandwidth. The rejection of the WiMAX frequencies operating at 3.5 and 5.8 GHz is realized by extruding a C-shaped stub from the modified ground surface. The radiating square plane of the proposed structure is also loaded with six small symmetric shaped square slots for making antenna operable in the 2.4 GHz Bluetooth band. The antenna structure proposed operates from 2.3 GHz to 19.4 GHz band by creating additional resonance even at upper frequencies. The optimization of designed antenna is conducted using FEM based tool Ansys HFSS and found simulated outcomes in a decent match with measured.
{"title":"Dual-Band Low Profile Notched Printed UWB Monopole Antenna with Enhanced Bandwidth","authors":"Sachin Kumar, S. Palaniswamy, Shobhit Saxena, Rahul Tiwari, Shalini Sah","doi":"10.1109/SPIN.2018.8474146","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474146","url":null,"abstract":"A planar monopole antenna with enhanced bandwidth and dual-band notching is proposed. The presented UWB monopole antenna is consisting of modified square patch loaded with inverted U-slot to reject WLAN frequencies in the range of 5.15–5.35 and 5.725–5.825 GHz. The ground surface of designed antenna is made up of two L-shaped and two C-shaped slots for achieving wide impedance bandwidth. The rejection of the WiMAX frequencies operating at 3.5 and 5.8 GHz is realized by extruding a C-shaped stub from the modified ground surface. The radiating square plane of the proposed structure is also loaded with six small symmetric shaped square slots for making antenna operable in the 2.4 GHz Bluetooth band. The antenna structure proposed operates from 2.3 GHz to 19.4 GHz band by creating additional resonance even at upper frequencies. The optimization of designed antenna is conducted using FEM based tool Ansys HFSS and found simulated outcomes in a decent match with measured.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114722492","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474208
Nishtha Joshi, N. Arora, Divya Upadhyay, Ashwani Kumar Dubey
The effect of time synchronization within the sensor nodes in Wireless Sensor Networks is an ongoing research area. It has received a huge amount of attention in the last decade. This paper discusses nature inspired algorithm, Ant Colony Optimization based Time-Sync(ACOTS) algorithm to provide an energy optimized solution to resolve time synchronization in WSN. Ant Colony optimization algorithm is implemented, and it was observed that it drastically reduces the number of packets transmitted and received during the synchronization process. This would help to solve time synchronization problem as well as it will also create an energy efficient network. The proposed algorithm ACOTS is compared with the already existing algorithms for e.g. Reference-Broadcast Synchronization (RBS) and Time-Sync Protocol for Sensor Network (TPSN). Comparative results suggested ACOTS uses less exchange of messages than other schemes.
{"title":"Optimized Time Synchronization Algorithm Inspired By Nature","authors":"Nishtha Joshi, N. Arora, Divya Upadhyay, Ashwani Kumar Dubey","doi":"10.1109/SPIN.2018.8474208","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474208","url":null,"abstract":"The effect of time synchronization within the sensor nodes in Wireless Sensor Networks is an ongoing research area. It has received a huge amount of attention in the last decade. This paper discusses nature inspired algorithm, Ant Colony Optimization based Time-Sync(ACOTS) algorithm to provide an energy optimized solution to resolve time synchronization in WSN. Ant Colony optimization algorithm is implemented, and it was observed that it drastically reduces the number of packets transmitted and received during the synchronization process. This would help to solve time synchronization problem as well as it will also create an energy efficient network. The proposed algorithm ACOTS is compared with the already existing algorithms for e.g. Reference-Broadcast Synchronization (RBS) and Time-Sync Protocol for Sensor Network (TPSN). Comparative results suggested ACOTS uses less exchange of messages than other schemes.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115055356","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474051
Sanjoy Debnath, Anand Jee, S. Baishya, W. Arif, P. Saikia, Shoaib Naafi
Need of communication in a disaster scenario is very crucial, so this has been an important task for the communication network to provide access to each and every user during and post disaster (DPD) event. Regarding this here we propose a planning for access point (AP) deployment to cover the mention area optimally through providing adequate data rate to every user. The planning of AP has a significant advantage in respect of coverage, capacity and number of AP. Here in locating optimal location for the deployment of AP in a considered zone we consider the key objective would be maximizing the utilization of each AP, considering the coverage and capacity of an AP as a constraint, while taking into account the mutual interference between nearby APs should be at lower level. Here for optimal solution of AP location, we use recently developed heuristic and evolutionary Dragonfly Algorithm (DA) optimization technique.
{"title":"Access Point Planning for Disaster Scenario using Dragonfly Algorithm","authors":"Sanjoy Debnath, Anand Jee, S. Baishya, W. Arif, P. Saikia, Shoaib Naafi","doi":"10.1109/SPIN.2018.8474051","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474051","url":null,"abstract":"Need of communication in a disaster scenario is very crucial, so this has been an important task for the communication network to provide access to each and every user during and post disaster (DPD) event. Regarding this here we propose a planning for access point (AP) deployment to cover the mention area optimally through providing adequate data rate to every user. The planning of AP has a significant advantage in respect of coverage, capacity and number of AP. Here in locating optimal location for the deployment of AP in a considered zone we consider the key objective would be maximizing the utilization of each AP, considering the coverage and capacity of an AP as a constraint, while taking into account the mutual interference between nearby APs should be at lower level. Here for optimal solution of AP location, we use recently developed heuristic and evolutionary Dragonfly Algorithm (DA) optimization technique.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116432473","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 : 2018-02-01DOI: 10.1109/SPIN.2018.8474199
Piyush Bhandari, Rakesh Kumar Bijarniya, Subhamoy Chatterjee, M. Kolekar
Using a deep Learning approach for any classification task demands the availability of a large labeled dataset. Such datasets are not only hard to find but also quite tedious to generate. Whereas unlabeled and un-organized sets of information is largely available in the world wide web. Especially in emotion or expression recognition, quality datasets, which are organized and freely available are very limited in number. In order to tackle such problems of small sized dataset, we analyze approaches such as self-taught and transfer learning for the expression classification, along with the extent to which the weights are transferable to the expression classification task. The base model for both types of learning is trained using the cifar10 database. We do not assume that the base data follows the same class labels or generative distribution as the test data. For testing our algorithm we use JAFFE dataset and draw inferences from the results obtained. We document that self taught learning forces the neural network to settle at a local minima rather than the global minimum. Transfer learning outperforms self taught learning and we also observe the correlation between the layers of a deep network when transferring the weights in a layer wise fashion.
{"title":"Analysis for Self-taught and Transfer Learning Based Approaches for Emotion Recognition","authors":"Piyush Bhandari, Rakesh Kumar Bijarniya, Subhamoy Chatterjee, M. Kolekar","doi":"10.1109/SPIN.2018.8474199","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474199","url":null,"abstract":"Using a deep Learning approach for any classification task demands the availability of a large labeled dataset. Such datasets are not only hard to find but also quite tedious to generate. Whereas unlabeled and un-organized sets of information is largely available in the world wide web. Especially in emotion or expression recognition, quality datasets, which are organized and freely available are very limited in number. In order to tackle such problems of small sized dataset, we analyze approaches such as self-taught and transfer learning for the expression classification, along with the extent to which the weights are transferable to the expression classification task. The base model for both types of learning is trained using the cifar10 database. We do not assume that the base data follows the same class labels or generative distribution as the test data. For testing our algorithm we use JAFFE dataset and draw inferences from the results obtained. We document that self taught learning forces the neural network to settle at a local minima rather than the global minimum. Transfer learning outperforms self taught learning and we also observe the correlation between the layers of a deep network when transferring the weights in a layer wise fashion.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123549767","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：