Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707998
S. Veenadevi, A. Ananth
Fractal image compressions of Standard Lena and Satellite imageries have been carried out for the variable size range block method. The image is partitioned by considering maximum and minimum size of the range block and matching it with the domain block. The domain block size of window K*K are sliding over the entire image in steps of K/2. Affine transformation and entropy coding are applied to achieve fractal compression. The Matlab simulation for the standard Lena, and Satellite imageries have been carried out for three different cases of variable range block sizes. The image is reconstructed using iterative functions and inverse transforms. The results of the fractal compression scheme indicate that for the case Rmax = 16 and Rmin = 8, it is possible to achieve higher Compression Ratio (CR) ~ 16 and good Peak Signal to Noise Ratios (PSNR) ~21 dB for satellite imageries. The fractal compression scheme with variable range methods are found to be better than the fixed range methods for achieving higher compression ratios and PSNR values for satellite imageries. The results are presented and discussed in the paper.
{"title":"Fractal image compression of Satellite imageries using variable size of range block","authors":"S. Veenadevi, A. Ananth","doi":"10.1109/ICSIPA.2013.6707998","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707998","url":null,"abstract":"Fractal image compressions of Standard Lena and Satellite imageries have been carried out for the variable size range block method. The image is partitioned by considering maximum and minimum size of the range block and matching it with the domain block. The domain block size of window K*K are sliding over the entire image in steps of K/2. Affine transformation and entropy coding are applied to achieve fractal compression. The Matlab simulation for the standard Lena, and Satellite imageries have been carried out for three different cases of variable range block sizes. The image is reconstructed using iterative functions and inverse transforms. The results of the fractal compression scheme indicate that for the case Rmax = 16 and Rmin = 8, it is possible to achieve higher Compression Ratio (CR) ~ 16 and good Peak Signal to Noise Ratios (PSNR) ~21 dB for satellite imageries. The fractal compression scheme with variable range methods are found to be better than the fixed range methods for achieving higher compression ratios and PSNR values for satellite imageries. The results are presented and discussed in the paper.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121551080","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707973
Muhammad Shahin Uddin, M. Tahtali, A. Lambert, M. Pickering
Speckle noise is a major shortcoming of any type of ultrasound imaging. Hence, speckle reduction is vital in providing a better clinical diagnosis. The key objective of any speckle reduction algorithm is to attain a speckle free image, whilst preserving the important anatomical features. In this paper, we introduce a nonlinear multi-scale complex wavelet diffusion based algorithm for speckle reduction and sharp edge preservation of 2D ultrasound images. The proposed method exploits some useful features of the dual tree complex wavelet transform and nonlinear diffusion. Simulated experimental results demonstrate that our proposed algorithm significantly reduces speckle noise while preserving sharp edges without discernible distortions. The proposed approach performs better than the previous existing approaches in both qualitative and quantitative measures.
{"title":"Speckle reduction for ultrasound images using nonlinear multi-scale complex wavelet diffusion","authors":"Muhammad Shahin Uddin, M. Tahtali, A. Lambert, M. Pickering","doi":"10.1109/ICSIPA.2013.6707973","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707973","url":null,"abstract":"Speckle noise is a major shortcoming of any type of ultrasound imaging. Hence, speckle reduction is vital in providing a better clinical diagnosis. The key objective of any speckle reduction algorithm is to attain a speckle free image, whilst preserving the important anatomical features. In this paper, we introduce a nonlinear multi-scale complex wavelet diffusion based algorithm for speckle reduction and sharp edge preservation of 2D ultrasound images. The proposed method exploits some useful features of the dual tree complex wavelet transform and nonlinear diffusion. Simulated experimental results demonstrate that our proposed algorithm significantly reduces speckle noise while preserving sharp edges without discernible distortions. The proposed approach performs better than the previous existing approaches in both qualitative and quantitative measures.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"24 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114136263","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708037
A. Babiker, I. Faye, A. Malik
Emotion recognition process is proven to be an essential tool to increase human-computer reaction, interpret social relations, investigate mental health, and study human behavior. Pupil diameter (PD) has been addressed as the most reliable approach to identify emotions. This is because it is controlled by Automatic Nervous System (ANS) and is easy to detect. The goal of this paper is to identify the difference in PD due to individual's positive and negative emotional states. The paper introduces experimental results obtained using eye-tracking system with 30 participants. Initial results obtained by applying differently paired-sample t-test suggested a significant increase in pupil dilation during negative emotions compared to positive ones. It also shows steeper, higher, more sustained and longer dilation in high arousal negative stimuli.
{"title":"Pupillary behavior in positive and negative emotions","authors":"A. Babiker, I. Faye, A. Malik","doi":"10.1109/ICSIPA.2013.6708037","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708037","url":null,"abstract":"Emotion recognition process is proven to be an essential tool to increase human-computer reaction, interpret social relations, investigate mental health, and study human behavior. Pupil diameter (PD) has been addressed as the most reliable approach to identify emotions. This is because it is controlled by Automatic Nervous System (ANS) and is easy to detect. The goal of this paper is to identify the difference in PD due to individual's positive and negative emotional states. The paper introduces experimental results obtained using eye-tracking system with 30 participants. Initial results obtained by applying differently paired-sample t-test suggested a significant increase in pupil dilation during negative emotions compared to positive ones. It also shows steeper, higher, more sustained and longer dilation in high arousal negative stimuli.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"03 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131286053","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708010
Rabiu Habibu, M. Saripan, M. Marhaban, S. Mashohor
Face detection and segmentation is an important prerequisite step for many face related processes such as face recognition and facial expression recognition. A method that automatically segments the given faces images irrespective of their different sizes and orientations will not only ease the subsequent face analysis task but will as well enhances its performance. In this work, an adaptive radius based face segmentation method is presented. We utilised the face's intrinsic properties derived from Gaussian and mean curvature of the face surface to segment each face. The UPM-3DFE and Gavab 3D face databases were used in testing the new method. Visual inspection of the result indicated that the novel method can attained up to 99.23% segmentation accuracy.
{"title":"3d-based face segmentation using adaptive radius","authors":"Rabiu Habibu, M. Saripan, M. Marhaban, S. Mashohor","doi":"10.1109/ICSIPA.2013.6708010","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708010","url":null,"abstract":"Face detection and segmentation is an important prerequisite step for many face related processes such as face recognition and facial expression recognition. A method that automatically segments the given faces images irrespective of their different sizes and orientations will not only ease the subsequent face analysis task but will as well enhances its performance. In this work, an adaptive radius based face segmentation method is presented. We utilised the face's intrinsic properties derived from Gaussian and mean curvature of the face surface to segment each face. The UPM-3DFE and Gavab 3D face databases were used in testing the new method. Visual inspection of the result indicated that the novel method can attained up to 99.23% segmentation accuracy.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133715141","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708007
Arif Sameh Arif, R. Logeswaran, Sarina Mansor, Hezerul Abdul Karim
Enormous amounts of sequential medical images are produced in modern medical examinations, typically in Fluoroscopy. Although highly effective, such large quantities of images incur a high cost in terms of storage, processing time and transmission. This paper proposes a method for lossless compression of targeted parts within Fluoroscopy images, extracting the region of interest (ROI) - in this case the pharynx and esophagus, and employing customized correlation and the combination of Run Length and Huffman coding, to increase compression efficiency. The experimental results show that the proposed method improved performance with a compression ratio of 300% better than conventional methods.
{"title":"Segmentation and compression of pharynx and esophagus fluoroscopic images","authors":"Arif Sameh Arif, R. Logeswaran, Sarina Mansor, Hezerul Abdul Karim","doi":"10.1109/ICSIPA.2013.6708007","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708007","url":null,"abstract":"Enormous amounts of sequential medical images are produced in modern medical examinations, typically in Fluoroscopy. Although highly effective, such large quantities of images incur a high cost in terms of storage, processing time and transmission. This paper proposes a method for lossless compression of targeted parts within Fluoroscopy images, extracting the region of interest (ROI) - in this case the pharynx and esophagus, and employing customized correlation and the combination of Run Length and Huffman coding, to increase compression efficiency. The experimental results show that the proposed method improved performance with a compression ratio of 300% better than conventional methods.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125662817","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707976
M. Shimizu
This paper presents a proposal of a method to estimate a light environment using a single image of cylinder as a calibration object with a Lambertian surface. The light environment to be estimated is modeled as a single light source with size and an ambient light. The proposed method estimates the model parameter directly from pixel values of a single cylinder image. Experimental results demonstrate the effectiveness of the proposed method, which can estimate the model parameter with sufficient resolution for rendering a computer graphics object superimposed to a real image.
{"title":"Light environment estimation from a single cylinder image","authors":"M. Shimizu","doi":"10.1109/ICSIPA.2013.6707976","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707976","url":null,"abstract":"This paper presents a proposal of a method to estimate a light environment using a single image of cylinder as a calibration object with a Lambertian surface. The light environment to be estimated is modeled as a single light source with size and an ambient light. The proposed method estimates the model parameter directly from pixel values of a single cylinder image. Experimental results demonstrate the effectiveness of the proposed method, which can estimate the model parameter with sufficient resolution for rendering a computer graphics object superimposed to a real image.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125503181","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708012
Madjid Maidi, M. Preda, M. Dailey, Sirisilp Kongsilp
This paper presents a natural feature tracking system for object recognition in real-life environments. The system is based on a local keypoint descriptor method optimized and adapted to extract salient regions within the image. Each object in the gallery is characterized by keypoints and corresponding local descriptors. The method first identifies gallery object features in new images using nearest neighbor classification. It then estimates camera pose and augments the image with registered synthetic graphics. We describe the optimizations necessary to enable real-time performance on a mobile tablet. An experimental evaluation of the system in real environments demonstrates that the method is accurate and robust.
{"title":"Natural feature tracking on a mobile handheld Tablet","authors":"Madjid Maidi, M. Preda, M. Dailey, Sirisilp Kongsilp","doi":"10.1109/ICSIPA.2013.6708012","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708012","url":null,"abstract":"This paper presents a natural feature tracking system for object recognition in real-life environments. The system is based on a local keypoint descriptor method optimized and adapted to extract salient regions within the image. Each object in the gallery is characterized by keypoints and corresponding local descriptors. The method first identifies gallery object features in new images using nearest neighbor classification. It then estimates camera pose and augments the image with registered synthetic graphics. We describe the optimizations necessary to enable real-time performance on a mobile tablet. An experimental evaluation of the system in real environments demonstrates that the method is accurate and robust.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134278836","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707959
R. Logeswaran
Selamat Datang (Welcome!) to the 2013 IEEE International Conference on Signal and Image Processing Applications or more fondly known as IEEE ICSIPA 2013. As the 3rd in the series, this flagship conference of the IEEE Signal Processing Society (Malaysia) (awarded Best Signal Processing Chapter 2011) has a good reputation for quality and a forum for valuable exchange of knowledge. It gains participation of esteemed researchers from both the local and international arena. This year, 169 papers were submitted by authors from various countries, with the majority being international authors. Of these, about 48% the papers were accepted and are to be presented at the conference.
{"title":"Foreword from general chair: “Technical knowledge sharing in signal processing with a historic backdrop”","authors":"R. Logeswaran","doi":"10.1109/ICSIPA.2013.6707959","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707959","url":null,"abstract":"Selamat Datang (Welcome!) to the 2013 IEEE International Conference on Signal and Image Processing Applications or more fondly known as IEEE ICSIPA 2013. As the 3rd in the series, this flagship conference of the IEEE Signal Processing Society (Malaysia) (awarded Best Signal Processing Chapter 2011) has a good reputation for quality and a forum for valuable exchange of knowledge. It gains participation of esteemed researchers from both the local and international arena. This year, 169 papers were submitted by authors from various countries, with the majority being international authors. Of these, about 48% the papers were accepted and are to be presented at the conference.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"517 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133336381","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707964
B. Vo
Summary form only given. A multi-object system is a generalisation of the standard state space system to one with a randomly varying set of states. An example of such a system is the collection of mobile sensors monitoring an unknown and time varying number of targets in a surveillance region. A biological example is a swarm of insects moving about performing a certain set of tasks. Indeed most systems in nature are multi-object systems. Traditionally driven by applications in radar and sonar, today, multi-object system has found applications in many diverse disciplines, including oceanography, autonomous vehicles, and biomedical research. This talk provides an introduction to the theory of multi-object system and describes of some of the recent developments in the filed together with applications.
{"title":"Keynote speaker II: Multi-object systems and their applications","authors":"B. Vo","doi":"10.1109/ICSIPA.2013.6707964","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707964","url":null,"abstract":"Summary form only given. A multi-object system is a generalisation of the standard state space system to one with a randomly varying set of states. An example of such a system is the collection of mobile sensors monitoring an unknown and time varying number of targets in a surveillance region. A biological example is a swarm of insects moving about performing a certain set of tasks. Indeed most systems in nature are multi-object systems. Traditionally driven by applications in radar and sonar, today, multi-object system has found applications in many diverse disciplines, including oceanography, autonomous vehicles, and biomedical research. This talk provides an introduction to the theory of multi-object system and describes of some of the recent developments in the filed together with applications.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122217862","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708018
Ismail M. El-Badawy, A. Aziz, S. Gasser, M. Khedr
Prediction of exons locations in deoxyribonucleic acid (DNA) sequences is a significant issue for biologists. This paper proposes a new method to solve this problem. Unlike the published studies, in which the prediction of exons locations depends on hard decisions from a single classifier, the proposed prediction approach depends on fusion of soft decisions from two classifiers. In the proposed approach we utilize the sliding window discrete Fourier transform (DFT), which is normally used to detect exons 3-base periodicity feature, in a different manner. The novelty here depends on obtaining soft decisions, rather than hard decisions, from two classifiers using different numerical mapping schemes, and fuses them in a decision fusion center to obtain a final global decision about the prediction of exons locations. Simulation results based on real data performed on the HMR195 dataset showed that the proposed soft decisions fusion method achieves better prediction performance compared to the traditional hard decision single classifier method. Moreover the proposed method can easily be extended to more than two classifiers.
{"title":"A new multiple classifiers soft decisions fusion approach for exons prediction in DNA sequences","authors":"Ismail M. El-Badawy, A. Aziz, S. Gasser, M. Khedr","doi":"10.1109/ICSIPA.2013.6708018","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708018","url":null,"abstract":"Prediction of exons locations in deoxyribonucleic acid (DNA) sequences is a significant issue for biologists. This paper proposes a new method to solve this problem. Unlike the published studies, in which the prediction of exons locations depends on hard decisions from a single classifier, the proposed prediction approach depends on fusion of soft decisions from two classifiers. In the proposed approach we utilize the sliding window discrete Fourier transform (DFT), which is normally used to detect exons 3-base periodicity feature, in a different manner. The novelty here depends on obtaining soft decisions, rather than hard decisions, from two classifiers using different numerical mapping schemes, and fuses them in a decision fusion center to obtain a final global decision about the prediction of exons locations. Simulation results based on real data performed on the HMR195 dataset showed that the proposed soft decisions fusion method achieves better prediction performance compared to the traditional hard decision single classifier method. Moreover the proposed method can easily be extended to more than two classifiers.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116003672","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：