Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776216
B. Anami, Prakash H. Unki
The different tissues namely gray matter (GM) white matter (WM), and cerebrospinal fluid (CSF) are spread over the entire brain. It is difficult to demarcate them individually when a brain image is considered. The boundaries are not well defined. Modified fuzzy C means (MFCM) and level sets segmentation based methodology is proposed in this paper for automated brain MRI image segmentation into WM, GM and CSF. The initial segmentation is done by MFCM approach and the results thus obtained are input to the level set methodology. We have tested the methodology on 100 different brain MRI images. The results are compared by using individual MFCM and level set segmentation methods. We took the opinion of 10 expert radiologists to corroborate our results. The results are validated by radiologists as `Accurate', `Satisfactory', `Adequate' and `Not acceptable'. The results obtained using only level set are `not acceptable'. Most of the results obtained using MFCM are `Adequate'. The results obtained using combined method are `Satisfactory'. Hence, the results obtained using combined MFCM and level sets based segmentation are considered better than using individual MFCM and level set segmentation methods. The manual intervention is avoided in the combined approach. The time required to segment using combined approach is also less compared to level set method. The segmentation using proposed methodology is helpful for radiologists in hospitals for brain MRI image analysis.
{"title":"A combined fuzzy and level sets' based approach for brain MRI image segmentation","authors":"B. Anami, Prakash H. Unki","doi":"10.1109/NCVPRIPG.2013.6776216","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776216","url":null,"abstract":"The different tissues namely gray matter (GM) white matter (WM), and cerebrospinal fluid (CSF) are spread over the entire brain. It is difficult to demarcate them individually when a brain image is considered. The boundaries are not well defined. Modified fuzzy C means (MFCM) and level sets segmentation based methodology is proposed in this paper for automated brain MRI image segmentation into WM, GM and CSF. The initial segmentation is done by MFCM approach and the results thus obtained are input to the level set methodology. We have tested the methodology on 100 different brain MRI images. The results are compared by using individual MFCM and level set segmentation methods. We took the opinion of 10 expert radiologists to corroborate our results. The results are validated by radiologists as `Accurate', `Satisfactory', `Adequate' and `Not acceptable'. The results obtained using only level set are `not acceptable'. Most of the results obtained using MFCM are `Adequate'. The results obtained using combined method are `Satisfactory'. Hence, the results obtained using combined MFCM and level sets based segmentation are considered better than using individual MFCM and level set segmentation methods. The manual intervention is avoided in the combined approach. The time required to segment using combined approach is also less compared to level set method. The segmentation using proposed methodology is helpful for radiologists in hospitals for brain MRI image analysis.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116158753","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776247
R. Tabib, Ujwala Patil, Syed Altaf Ganihar, N. Trivedi, U. Mudenagudi
In this paper, we address the problem of decision fusion for robust horizon estimation using Dempster Shafer Combination Rule (DSCR). We provide a framework for decision fusion to select robust horizon estimate out of `n' estimates, based on confidence factor. Vision-based attitude estimation depends on robust horizon estimation and no single algorithm gives accurate results for different kind of scenarios. We propose to combine the evidence parameters to generate confidence factor using DSCR to justify the correctness of the estimated horizon. We compute Confidence Interval (CI) based on Gaussian Mixture Model (GMM). We also propose two techniques to provide evidence parameters for the estimated horizon using CI. We demonstrate the effectiveness of the decision framework on clear and noisy data sets of simulated and real images/videos captured by Micro Air Vehicle (MAV).
{"title":"Decision fusion for robust horizon estimation using Dempster Shafer Combination Rule","authors":"R. Tabib, Ujwala Patil, Syed Altaf Ganihar, N. Trivedi, U. Mudenagudi","doi":"10.1109/NCVPRIPG.2013.6776247","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776247","url":null,"abstract":"In this paper, we address the problem of decision fusion for robust horizon estimation using Dempster Shafer Combination Rule (DSCR). We provide a framework for decision fusion to select robust horizon estimate out of `n' estimates, based on confidence factor. Vision-based attitude estimation depends on robust horizon estimation and no single algorithm gives accurate results for different kind of scenarios. We propose to combine the evidence parameters to generate confidence factor using DSCR to justify the correctness of the estimated horizon. We compute Confidence Interval (CI) based on Gaussian Mixture Model (GMM). We also propose two techniques to provide evidence parameters for the estimated horizon using CI. We demonstrate the effectiveness of the decision framework on clear and noisy data sets of simulated and real images/videos captured by Micro Air Vehicle (MAV).","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122089757","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776186
R. Mukherjee, V. Mahajan, I. Chakrabarti, S. Sengupta
The video coding standard H.264 uses Context-based Adaptive Variable Length Coding (CAVLC) as one of its entropy encoding techniques. This paper proposes VLSI architecture for CAVLC algorithm. The designed hardware meets the required speed of H.264 without compromising the hardware cost. The CAVLC encoder works at a maximum clock frequency of 126 MHz when implemented in Xilinx 10.1i, Virtex-5 technology. The speed is quite appreciable when compared to other existing works. The implemented architecture meets the required rate for processing of HD-1080 format video sequence.
{"title":"High performance VLSI implementation of Context-based Adaptive Variable Length Coding (CAVLC) for H.264 encoder","authors":"R. Mukherjee, V. Mahajan, I. Chakrabarti, S. Sengupta","doi":"10.1109/NCVPRIPG.2013.6776186","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776186","url":null,"abstract":"The video coding standard H.264 uses Context-based Adaptive Variable Length Coding (CAVLC) as one of its entropy encoding techniques. This paper proposes VLSI architecture for CAVLC algorithm. The designed hardware meets the required speed of H.264 without compromising the hardware cost. The CAVLC encoder works at a maximum clock frequency of 126 MHz when implemented in Xilinx 10.1i, Virtex-5 technology. The speed is quite appreciable when compared to other existing works. The implemented architecture meets the required rate for processing of HD-1080 format video sequence.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123578043","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776243
B. H. Shekar, N. Harivinod
A novel method for multispectral palmprint matching based on the joint sparse representation is proposed. We use joint sparse representation to model the identity assurance system that involves identification as well as verification. The method represents the given palmprint as a linear combination of the multispectral palmprints. The information from different spectrum are fused by means of feature level fusion. The nearest neighbour classification based on class wise reconstruction error is used for classification. Experiments are conducted on PolyU multispectral palmprint database. The results show that the proposed method works better in comparison with the existing techniques.
{"title":"Multispectral palmprint matching based on joint sparse representation","authors":"B. H. Shekar, N. Harivinod","doi":"10.1109/NCVPRIPG.2013.6776243","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776243","url":null,"abstract":"A novel method for multispectral palmprint matching based on the joint sparse representation is proposed. We use joint sparse representation to model the identity assurance system that involves identification as well as verification. The method represents the given palmprint as a linear combination of the multispectral palmprints. The information from different spectrum are fused by means of feature level fusion. The nearest neighbour classification based on class wise reconstruction error is used for classification. Experiments are conducted on PolyU multispectral palmprint database. The results show that the proposed method works better in comparison with the existing techniques.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122269456","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776207
Subhaluxmi Sahoo, P. Nanda, Sunita Samant
In this paper, an embedded entropy based image registration scheme has been proposed. Here, Tsallis and Renyi's entropy have been embedded to form a new entropic measure. This parametrized entropy has been used to determine the weighted mutual information (MI) for the CT and MR brain images. The embedded mutual information has been maximized to obtain registration. This notion of embedded mutual information has also been validated in feature space registration. The mutual information with respect to the registration parameter has been found to be a nonlinear curve. It has been found that the feature space registration resulted in higher value mutual information and hence registration process could be smoother. We have used Simulated Annealing algorithm to determine the maximum of this embedded mutual information and hence register the images.
{"title":"Tsallis and Renyi's embedded entropy based mutual information for multimodal image registration","authors":"Subhaluxmi Sahoo, P. Nanda, Sunita Samant","doi":"10.1109/NCVPRIPG.2013.6776207","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776207","url":null,"abstract":"In this paper, an embedded entropy based image registration scheme has been proposed. Here, Tsallis and Renyi's entropy have been embedded to form a new entropic measure. This parametrized entropy has been used to determine the weighted mutual information (MI) for the CT and MR brain images. The embedded mutual information has been maximized to obtain registration. This notion of embedded mutual information has also been validated in feature space registration. The mutual information with respect to the registration parameter has been found to be a nonlinear curve. It has been found that the feature space registration resulted in higher value mutual information and hence registration process could be smoother. We have used Simulated Annealing algorithm to determine the maximum of this embedded mutual information and hence register the images.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129115606","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776230
Krishna P. Miyapuram, W. Schultz, P. Tobler
Mental imagery refers to percept-like experiences in the absence of sensory input. Brain imaging studies suggest common, modality-specific, neural correlates imagery and perception. We associated abstract visual stimuli with either visually presented or imagined monetary rewards and scrambled pictures. Brain images for a group of 12 participants were collected using functional magnetic resonance imaging. Statistical analysis showed that human midbrain regions were activated irrespective of the monetary rewards being imagined or visually present. A support vector machine trained on the midbrain activation patterns to the visually presented rewards predicted with 75% accuracy whether the participants imagined the monetary reward or the scrambled picture during imagination trials. Training samples were drawn from visually presented trials and classification accuracy was assessed for imagination trials. These results suggest the use of machine learning technique for classification of underlying cognitive states from brain imaging data.
{"title":"Predicting the imagined contents using brain activation","authors":"Krishna P. Miyapuram, W. Schultz, P. Tobler","doi":"10.1109/NCVPRIPG.2013.6776230","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776230","url":null,"abstract":"Mental imagery refers to percept-like experiences in the absence of sensory input. Brain imaging studies suggest common, modality-specific, neural correlates imagery and perception. We associated abstract visual stimuli with either visually presented or imagined monetary rewards and scrambled pictures. Brain images for a group of 12 participants were collected using functional magnetic resonance imaging. Statistical analysis showed that human midbrain regions were activated irrespective of the monetary rewards being imagined or visually present. A support vector machine trained on the midbrain activation patterns to the visually presented rewards predicted with 75% accuracy whether the participants imagined the monetary reward or the scrambled picture during imagination trials. Training samples were drawn from visually presented trials and classification accuracy was assessed for imagination trials. These results suggest the use of machine learning technique for classification of underlying cognitive states from brain imaging data.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129527190","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776236
H. Aggarwal, A. Majumdar
A generic-filter array design have been proposed to capture multi-spectral images using hypothetical single-sensor multi-spectral cameras. The design idea is based on uniform sampling of intensity values from each band irrespective of spectral properties of any particular band. A reconstruction technique have also been proposed to linearly interpolate unknown intensity values of other bands at each pixel. Proposed technique was evaluated using two multispectral image datasets where one was of Landsat satellite and another was of cooled CCD camera Apogee Alta U260. Quantitative evaluation of the proposed technique was done using peak signal to noise ratio.
提出了一种通用滤波阵列设计，用于使用假设的单传感器多光谱相机捕获多光谱图像。设计思想是基于对每个波段的强度值进行均匀采样，而不考虑任何特定波段的光谱特性。本文还提出了一种重建技术，用于在每个像素上线性插值其他波段的未知强度值。利用Landsat卫星和Apogee Alta U260冷却CCD相机的两组多光谱图像数据对该技术进行了评价。利用峰值信噪比对该方法进行了定量评价。
{"title":"Multi-spectral demosaicing technique for single-sensor imaging","authors":"H. Aggarwal, A. Majumdar","doi":"10.1109/NCVPRIPG.2013.6776236","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776236","url":null,"abstract":"A generic-filter array design have been proposed to capture multi-spectral images using hypothetical single-sensor multi-spectral cameras. The design idea is based on uniform sampling of intensity values from each band irrespective of spectral properties of any particular band. A reconstruction technique have also been proposed to linearly interpolate unknown intensity values of other bands at each pixel. Proposed technique was evaluated using two multispectral image datasets where one was of Landsat satellite and another was of cooled CCD camera Apogee Alta U260. Quantitative evaluation of the proposed technique was done using peak signal to noise ratio.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564336","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776170
Jayashri Vajpai, J. B. Arun, Ishani Vajpai
With the growth of web enabled services and e-commerce, tremendous amount of information is now readily available on the Internet. A large proportion of this is classified information, which has to be protected against unauthorized access. Password or PIN can be used in conjunction with digital signature, for verification of the identity of users. This paper proposes a dynamic handwritten signature verification based access control system that can be employed in the legal, banking and commercial domains for designing secure information retrieval systems. The dynamic handwritten signature in this system is captured by using a digital tablet or PDA (Personal Digital Assistant) with contact sensitive acquisition system. After preprocessing, the signature data is compared with the templates of authorized signatures by employing an innovative neuro-fuzzy pattern recognition system based on sensing the pressure variable and total time required for executing the signature for uniquely identifying the potential user. The error in matching is used to arrive at the decision regarding permission or denial of access to the classified document. The neuro-fuzzy technique applied in the dynamic signature system is based on evolving fuzzy neural network. This technique has been tested on signatures drawn from signature verification competition database obtained from the internet. Encouraging results show that this technique is a good candidate for the development of practical applications.
随着网络服务和电子商务的发展，大量的信息现在可以在互联网上随时获得。其中很大一部分是机密信息，必须加以保护，防止未经授权的访问。密码或个人识别码可与数字签名配合使用，以核实用户的身份。本文提出了一种基于动态手写签名验证的访问控制系统，可用于法律、银行和商业领域的安全信息检索系统设计。该系统采用带有触敏采集系统的数字平板电脑或PDA (Personal digital Assistant，个人数字助理)采集动态手写签名。预处理后的签名数据与授权签名模板进行比较，采用一种创新的神经模糊模式识别系统，该系统基于感知压力变量和执行签名所需的总时间，以唯一识别潜在用户。匹配中的错误用于决定是否允许访问机密文档。应用于动态签名系统的神经模糊技术是基于进化模糊神经网络的。该技术在签名验证竞赛数据库中抽取的签名上进行了测试。令人鼓舞的结果表明，该技术具有开发实际应用的良好前景。
{"title":"Dynamic signature verification for secure retrieval of classified information","authors":"Jayashri Vajpai, J. B. Arun, Ishani Vajpai","doi":"10.1109/NCVPRIPG.2013.6776170","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776170","url":null,"abstract":"With the growth of web enabled services and e-commerce, tremendous amount of information is now readily available on the Internet. A large proportion of this is classified information, which has to be protected against unauthorized access. Password or PIN can be used in conjunction with digital signature, for verification of the identity of users. This paper proposes a dynamic handwritten signature verification based access control system that can be employed in the legal, banking and commercial domains for designing secure information retrieval systems. The dynamic handwritten signature in this system is captured by using a digital tablet or PDA (Personal Digital Assistant) with contact sensitive acquisition system. After preprocessing, the signature data is compared with the templates of authorized signatures by employing an innovative neuro-fuzzy pattern recognition system based on sensing the pressure variable and total time required for executing the signature for uniquely identifying the potential user. The error in matching is used to arrive at the decision regarding permission or denial of access to the classified document. The neuro-fuzzy technique applied in the dynamic signature system is based on evolving fuzzy neural network. This technique has been tested on signatures drawn from signature verification competition database obtained from the internet. Encouraging results show that this technique is a good candidate for the development of practical applications.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"537 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127981573","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776179
Sanjoy Pratihar, Partha Bhowmick, S. Sural, J. Mukhopadhyay
Performance of an OCR system is badly affected due to presence of hand-drawn annotation lines in various forms, such as underlines, circular lines, and other text-surrounding curves. Such annotation lines are drawn by a reader usually in free hand in order to summarize some text or to mark the keywords within a document page. In this paper, we propose a generalized scheme for detection and removal of these hand-drawn annotations from a scanned document page. An underline drawn by hand is roughly horizontal or has a tolerable undulation, whereas for a hand-drawn curved line, the slope usually changes at a gradual pace. Based on this observation, we detect the cover of an annotation object-be it straight or curved-as a sequence of straight edge segments. The novelty of the proposed method lies in its ability to compute the exact cover of the annotation object, even when it touches or passes through any text character. After getting the annotation cover, an effective method of inpainting is used to quantify the regions where text reconstruction is needed. We have done our experimentation with various documents written in English, and some results are presented here to show the efficiency and robustness of the proposed method.
{"title":"Removal of hand-drawn annotation lines from document images by digital-geometric analysis and inpainting","authors":"Sanjoy Pratihar, Partha Bhowmick, S. Sural, J. Mukhopadhyay","doi":"10.1109/NCVPRIPG.2013.6776179","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776179","url":null,"abstract":"Performance of an OCR system is badly affected due to presence of hand-drawn annotation lines in various forms, such as underlines, circular lines, and other text-surrounding curves. Such annotation lines are drawn by a reader usually in free hand in order to summarize some text or to mark the keywords within a document page. In this paper, we propose a generalized scheme for detection and removal of these hand-drawn annotations from a scanned document page. An underline drawn by hand is roughly horizontal or has a tolerable undulation, whereas for a hand-drawn curved line, the slope usually changes at a gradual pace. Based on this observation, we detect the cover of an annotation object-be it straight or curved-as a sequence of straight edge segments. The novelty of the proposed method lies in its ability to compute the exact cover of the annotation object, even when it touches or passes through any text character. After getting the annotation cover, an effective method of inpainting is used to quantify the regions where text reconstruction is needed. We have done our experimentation with various documents written in English, and some results are presented here to show the efficiency and robustness of the proposed method.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171379","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 : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776205
Sujatha C, Ravindra Akshay, Chivate, Sayed Altaf Ganihar, U. Mudenagudi
In this paper, we propose a method to browse the activities present in the longer videos for the user defined time. Browsing of activities is important for variety of applications and consumes large amount of viewing time for longer videos. The aim is to generate a summary of the video by retaining salient activities in a given time. We propose a method for selection of salient activities using motion of feature points as a key parameter, where the saliency of a frame depends on total motion and specified time for summarization. The motion information in a video is modeled as a Gaussian mixture model (GMM), to estimate the key motion frames in the video. The salient frames are detected depending upon the motion strength of the keyframe and user specified time, which contributes for the summarization keeping the chronology of activities. The proposed method finds applications in summarization of surveillance videos, movies, TV serials etc. We demonstrate the proposed method on different types of videos and achieve comparable results with stroboscopic approach and also maintain the chronology with an average retention ratio of 95%.
{"title":"Time driven video summarization using GMM","authors":"Sujatha C, Ravindra Akshay, Chivate, Sayed Altaf Ganihar, U. Mudenagudi","doi":"10.1109/NCVPRIPG.2013.6776205","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776205","url":null,"abstract":"In this paper, we propose a method to browse the activities present in the longer videos for the user defined time. Browsing of activities is important for variety of applications and consumes large amount of viewing time for longer videos. The aim is to generate a summary of the video by retaining salient activities in a given time. We propose a method for selection of salient activities using motion of feature points as a key parameter, where the saliency of a frame depends on total motion and specified time for summarization. The motion information in a video is modeled as a Gaussian mixture model (GMM), to estimate the key motion frames in the video. The salient frames are detected depending upon the motion strength of the keyframe and user specified time, which contributes for the summarization keeping the chronology of activities. The proposed method finds applications in summarization of surveillance videos, movies, TV serials etc. We demonstrate the proposed method on different types of videos and achieve comparable results with stroboscopic approach and also maintain the chronology with an average retention ratio of 95%.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124036677","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：