in this paper, we present the concatenative text-to-speech system and discuss the issues relevant to the development of a Marathi speech synthesizer using different choice of units: words, phonemes as a database. Quality of the synthesizer with different unit size indicates that the word synthesizer performs better than the phoneme synthesizer. The most important qualities of a speech synthesis system are naturalness and intelligibility. We synthesize the Marathi text and perform the subjective evaluations of the synthesized speech. As a result, (1) 81% of speech synthesized by the proposed method was preferred to that by the conventional method, (2) The error rate of TTS synthesizer is around 8.22%, (3) Speech synthesis runtime was reduced for proposed method. The results show the effectiveness of the proposed method.
{"title":"Marathi Language Speech Synthesizer Using Concatenative Synthesis Strategy (Spoken in Maharashtra, India)","authors":"S. Shirbahadurkar, D. Bormane","doi":"10.1109/ICMV.2009.52","DOIUrl":"https://doi.org/10.1109/ICMV.2009.52","url":null,"abstract":"in this paper, we present the concatenative text-to-speech system and discuss the issues relevant to the development of a Marathi speech synthesizer using different choice of units: words, phonemes as a database. Quality of the synthesizer with different unit size indicates that the word synthesizer performs better than the phoneme synthesizer. The most important qualities of a speech synthesis system are naturalness and intelligibility. We synthesize the Marathi text and perform the subjective evaluations of the synthesized speech. As a result, (1) 81% of speech synthesized by the proposed method was preferred to that by the conventional method, (2) The error rate of TTS synthesizer is around 8.22%, (3) Speech synthesis runtime was reduced for proposed method. The results show the effectiveness of the proposed method.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116695548","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}
Along with the rapid development of computer technology, image edge detection has become an important content of image processing. It is the basic problem of image analysis as well as the premise of image segmentation, feature extraction and image recognition. This paper discusses in detail two edge detection algorithms based on linear filtering technique, namely Marr-Hildreth algorithm and Canny algorithm.
{"title":"Compare between Several Linear Image Edge Detection Algorithm","authors":"Song Qiang, Lingxia Liu","doi":"10.1109/ICMV.2009.77","DOIUrl":"https://doi.org/10.1109/ICMV.2009.77","url":null,"abstract":"Along with the rapid development of computer technology, image edge detection has become an important content of image processing. It is the basic problem of image analysis as well as the premise of image segmentation, feature extraction and image recognition. This paper discusses in detail two edge detection algorithms based on linear filtering technique, namely Marr-Hildreth algorithm and Canny algorithm.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125015899","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 : 2009-12-28DOI: 10.1007/978-3-642-12712-0_16
C. Lakshmi, Dr. M. Ponnavaikko, Dr. M. Sundararajan
{"title":"Improved Kernel Common Vector Method for Face Recognition","authors":"C. Lakshmi, Dr. M. Ponnavaikko, Dr. M. Sundararajan","doi":"10.1007/978-3-642-12712-0_16","DOIUrl":"https://doi.org/10.1007/978-3-642-12712-0_16","url":null,"abstract":"","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116759318","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}
A. Rao, T. Sreenivasu, N. V. Rao, A. Sastry, L. Reddy, T. K. Prabhu
In this paper, a novel heuristic based approach adopted from George D.C. Calvacanti algorithm for removing background noise from all types of images with complex background is presented. In this approach Binarization is done by selecting two threshold values, one for foreground and another for background for the separation. Morphological techniques are used for improving the quality of the resultant image. In addition to this PSNR ratio is calculated for all the images and its variation with respect to the intensity of the background noise is observed.
本文采用George dc . Calvacanti算法，提出了一种新的基于启发式的方法，用于去除具有复杂背景的各类图像的背景噪声。在这种方法中，二值化是通过选择两个阈值来完成的，一个用于前景，另一个用于分离的背景。形态学技术用于提高所得图像的质量。除此之外，还计算了所有图像的PSNR比，并观察了其相对于背景噪声强度的变化。
{"title":"Binarization of Documents with Complex Backgrounds","authors":"A. Rao, T. Sreenivasu, N. V. Rao, A. Sastry, L. Reddy, T. K. Prabhu","doi":"10.1109/ICMV.2009.9","DOIUrl":"https://doi.org/10.1109/ICMV.2009.9","url":null,"abstract":"In this paper, a novel heuristic based approach adopted from George D.C. Calvacanti algorithm for removing background noise from all types of images with complex background is presented. In this approach Binarization is done by selecting two threshold values, one for foreground and another for background for the separation. Morphological techniques are used for improving the quality of the resultant image. In addition to this PSNR ratio is calculated for all the images and its variation with respect to the intensity of the background noise is observed.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133586710","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}
One of the ad-hoc networks challenges is the connectivity problem coming from changeable and dynamic topology of networks nodes. According to most of researches done on this problem, one of the solutions is adding static nodes in some points in network environment; and many attempts have been made to find these points by using different ways. However, in most of these studies no attention has been paid to network mobility model or the problem has been solved based on unrealistic mobility model such as Random waypoint. Thus previous works are not applicable in reality. This article presents an algorithm for adding static nodes which are located in best points of network to improve connectivity. This algorithm is based on realistic mobility model that can model both environmental obstacles and pathways, and furthermore can describe the realistic movement pattern of the nodes. Proposed algorithm uses Genetic algorithm to find the best points. Since simulation operation for evaluation of solution is time-consuming, this algorithm is independent from simulation operation and uses Voronoi diagram.
{"title":"Improvement of Connectivity in Mobile Ad Hoc Networks by Adding Static Nodes Based on a Realistic Mobility Model","authors":"Morteza Romoozi, S. M. Vahidipour, H. Babaei","doi":"10.1109/ICMV.2009.56","DOIUrl":"https://doi.org/10.1109/ICMV.2009.56","url":null,"abstract":"One of the ad-hoc networks challenges is the connectivity problem coming from changeable and dynamic topology of networks nodes. According to most of researches done on this problem, one of the solutions is adding static nodes in some points in network environment; and many attempts have been made to find these points by using different ways. However, in most of these studies no attention has been paid to network mobility model or the problem has been solved based on unrealistic mobility model such as Random waypoint. Thus previous works are not applicable in reality. This article presents an algorithm for adding static nodes which are located in best points of network to improve connectivity. This algorithm is based on realistic mobility model that can model both environmental obstacles and pathways, and furthermore can describe the realistic movement pattern of the nodes. Proposed algorithm uses Genetic algorithm to find the best points. Since simulation operation for evaluation of solution is time-consuming, this algorithm is independent from simulation operation and uses Voronoi diagram.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233564","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}
In this paper, we study the discriminative models like CRFs, HCRFs and LDCRFs to recognize alphabet characters (A-Z) and numbers (0-9) in real-time from stereo color image sequences. To handle isolated gesture, CRFs, HCRFs and LDCRFs with different number of window size are applied on 3D combined features of location, orientation and velocity. The gesture recognition rate is improved initially as the window size increase, but degrades as window size increase further. In contrast to generative approaches such as HMMs, experimental results show that the LDCRFs are the best in terms of results than CRFs, HCRFs and HMMs at window size equal 4. Additionally, our results show that; an overall recognition rates are 91.52%, 95.28% and 98.05% for CRFs, HCRFs, and LDCRFs respectively.
{"title":"Discriminative Models-Based Hand Gesture Recognition","authors":"M. Elmezain, A. Al-Hamadi, B. Michaelis","doi":"10.1109/ICMV.2009.29","DOIUrl":"https://doi.org/10.1109/ICMV.2009.29","url":null,"abstract":"In this paper, we study the discriminative models like CRFs, HCRFs and LDCRFs to recognize alphabet characters (A-Z) and numbers (0-9) in real-time from stereo color image sequences. To handle isolated gesture, CRFs, HCRFs and LDCRFs with different number of window size are applied on 3D combined features of location, orientation and velocity. The gesture recognition rate is improved initially as the window size increase, but degrades as window size increase further. In contrast to generative approaches such as HMMs, experimental results show that the LDCRFs are the best in terms of results than CRFs, HCRFs and HMMs at window size equal 4. Additionally, our results show that; an overall recognition rates are 91.52%, 95.28% and 98.05% for CRFs, HCRFs, and LDCRFs respectively.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133059983","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}
Augmented reality (AR) environment allows user or multi-user to interact with 2D and 3D data. AR simply can provide a collaborative interactive AR environment for urban simulation, where users can interact naturally and intuitively. AR collaboration approach can be effectively used to develop different interfaces for face-to-face and remote collaboration. This is because AR provides seamless interaction between real and virtual environments, the ability to enhance reality, the presence of spatial cues for face-to-face and remote collaboration, support of a tangible interface metaphor, the ability to transition smoothly between reality and virtuality. In addition, the collaborative AR makes multi-user in urban simulation to share simultaneously a real world and virtual world. The fusion between real and virtual world, existed in AR environment by see-through HMDs, achieves higher interactivity as a key features of collaborative AR. In real-time, precise registration between both worlds and multi-user are crucial for the collaborations. Collaborative AR approach allows multi-user to simultaneously share a real world surrounding them and a virtual world. Common problems in AR environment will be discussed and major issues in collaborative AR will be explained details in this survey. The features of collaboration in AR environment are will be identified and the requirements of collaborative AR will be defined. This paper will give an overview on collaborative AR environment for multi-user in urban studies and planning. The work will also cover numerous systems of collaborative AR environments for multi-user.
{"title":"Multi-user Interaction in Collaborative Augmented Reality for Urban Simulation","authors":"A. W. Ismail, M. S. Sunar","doi":"10.1109/ICMV.2009.40","DOIUrl":"https://doi.org/10.1109/ICMV.2009.40","url":null,"abstract":"Augmented reality (AR) environment allows user or multi-user to interact with 2D and 3D data. AR simply can provide a collaborative interactive AR environment for urban simulation, where users can interact naturally and intuitively. AR collaboration approach can be effectively used to develop different interfaces for face-to-face and remote collaboration. This is because AR provides seamless interaction between real and virtual environments, the ability to enhance reality, the presence of spatial cues for face-to-face and remote collaboration, support of a tangible interface metaphor, the ability to transition smoothly between reality and virtuality. In addition, the collaborative AR makes multi-user in urban simulation to share simultaneously a real world and virtual world. The fusion between real and virtual world, existed in AR environment by see-through HMDs, achieves higher interactivity as a key features of collaborative AR. In real-time, precise registration between both worlds and multi-user are crucial for the collaborations. Collaborative AR approach allows multi-user to simultaneously share a real world surrounding them and a virtual world. Common problems in AR environment will be discussed and major issues in collaborative AR will be explained details in this survey. The features of collaboration in AR environment are will be identified and the requirements of collaborative AR will be defined. This paper will give an overview on collaborative AR environment for multi-user in urban studies and planning. The work will also cover numerous systems of collaborative AR environments for multi-user.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122889729","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}
Recent researches have investigated the impact of feature selection methods on the performance of support vector machine (SVM) and claimed that no feature selection methods improve it in high dimension. However, they have based this argument on their experiments with simulated data. We have taken this claim as a research issue and investigated different feature selection methods on the real time micro array gene expression data. Our research outcome indicates that feature selection methods do have a positive impact on the performance of SVM in classifying micro array gene expression data.
{"title":"Impact of Feature Selection on Support Vector Machine Using Microarray Gene Expression Data","authors":"C. Wahid, A. Ali, K. Tickle","doi":"10.1109/ICMV.2009.46","DOIUrl":"https://doi.org/10.1109/ICMV.2009.46","url":null,"abstract":"Recent researches have investigated the impact of feature selection methods on the performance of support vector machine (SVM) and claimed that no feature selection methods improve it in high dimension. However, they have based this argument on their experiments with simulated data. We have taken this claim as a research issue and investigated different feature selection methods on the real time micro array gene expression data. Our research outcome indicates that feature selection methods do have a positive impact on the performance of SVM in classifying micro array gene expression data.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126011004","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}
Brain tumor is one of the leading cause of death in recent years. This paper proposes the tumor detection in CT scan brain images, which can assist the medical image diagnosis system. The method proposed here makes use of association rule mining technique to classify the CT scan brain images. It combines the low-level features extracted from images and high level knowledge from specialists. The proposed system consists of: a pre-processing phase, feature extraction phase, a phase for mining the resultant transaction database, a final phase to build the classifier and generating the suggestion of diagnosis. The classifier built in this method has an important characteristic that it can suggest multiple keywords per image, which improves the accuracy. Experimental results on pre-diagnosed database of brain images shows high accuracy (up to 95%), allowing us to claim that the use of associative classifier is an efficient technique to assist in the diagnosing task.
{"title":"Pruned Associative Classification Technique for the Medical Image Diagnosis System","authors":"P. Rajendran, M. Madheswaran","doi":"10.1109/ICMV.2009.55","DOIUrl":"https://doi.org/10.1109/ICMV.2009.55","url":null,"abstract":"Brain tumor is one of the leading cause of death in recent years. This paper proposes the tumor detection in CT scan brain images, which can assist the medical image diagnosis system. The method proposed here makes use of association rule mining technique to classify the CT scan brain images. It combines the low-level features extracted from images and high level knowledge from specialists. The proposed system consists of: a pre-processing phase, feature extraction phase, a phase for mining the resultant transaction database, a final phase to build the classifier and generating the suggestion of diagnosis. The classifier built in this method has an important characteristic that it can suggest multiple keywords per image, which improves the accuracy. Experimental results on pre-diagnosed database of brain images shows high accuracy (up to 95%), allowing us to claim that the use of associative classifier is an efficient technique to assist in the diagnosing task.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192738","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}
A. Rao, Golla Sunil, N. V. Rao, T. K. Prabhu, L. Reddy, A. Sastry
It is common for libraries to provide public access to historical and ancient document image collections. Such document images to require specialized processing in order to remove background noise and become more legible. In this paper the proposed approach is adapted from the kavallieratov’s algorithm for cleaning background noise from the ancient documents by iterative global thresholding and local thresholding technique. Finally the image quality is enhanced by using morphological technique and compared with other methods in the process of cleaning.
{"title":"Adaptive Binarization of Ancient Documents","authors":"A. Rao, Golla Sunil, N. V. Rao, T. K. Prabhu, L. Reddy, A. Sastry","doi":"10.1109/ICMV.2009.8","DOIUrl":"https://doi.org/10.1109/ICMV.2009.8","url":null,"abstract":"It is common for libraries to provide public access to historical and ancient document image collections. Such document images to require specialized processing in order to remove background noise and become more legible. In this paper the proposed approach is adapted from the kavallieratov’s algorithm for cleaning background noise from the ancient documents by iterative global thresholding and local thresholding technique. Finally the image quality is enhanced by using morphological technique and compared with other methods in the process of cleaning.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125391930","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：