%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:08:59 PM

@ARTICLE{odobez-ijprai05,
         author = {Chen, Datong and Odobez, Jean-Marc and Thiran, Jean-Philippe},
       projects = {Idiap},
          month = {8},
          title = {Monte {C}arlo {V}ideo {T}ext {S}egmentation},
        journal = {International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI)},
         volume = {19},
         number = {5},
           year = {2005},
           note = {IDIAP-RR 03-43},
       crossref = {chen-rr0343},
       abstract = {This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences based on adaptive thresholding using a Bayes filtering method. The algorithm approximates the posterior distribution of segmentation thresholds of video text by a set of weighted samples. The set of samples is initialized by applying a classical segmentation algorithm on the first video frame and further refined by random sampling under a temporal Bayesian framework. This framework allows us to evaluate an text image segmentor on the basis of recognition result instead of visual segmentation result, which is directly relevant to our character recognition task. Results on a database of 6944 images demonstrate the validity of the algorithm.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/odobez_ijprai_2005.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/odobez_ijprai_2005.ps.gz},
ipdmembership={vision},
}



crossreferenced publications: 
@TECHREPORT{chen-rr0343,
         author = {Chen, Datong and Odobez, Jean-Marc},
       projects = {Idiap},
          month = {5},
          title = {Video Text Segmentation Using Particle Filters},
           type = {Idiap-RR},
         number = {Idiap-RR-43-2003},
           year = {2003},
    institution = {IDIAP},
           note = {published in Int. Journal of Pattern Recognition and Artificial Intelligence},
       abstract = {This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences based on adaptive thresholding using a Bayes filtering method. The algorithm approximates the posterior distribution of segmentation thresholds of video text by a set of weighted samples. The set of samples is initialized by applying a classical segmentation algorithm on the first video frame and further refined by random sampling under a temporal Bayesian framework. This framework allows us to evaluate an text image segmentor on the basis of recognition result instead of visual segmentation result, which is directly relevant to our character recognition task. Results on a database of 6944 images demonstrate the validity of the algorithm.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-43.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-43.ps.gz},
ipdmembership={vision},
}