%Aigaion2 BibTeX export from Idiap Publications
%Wednesday 20 November 2024 06:40:59 PM

@ARTICLE{odobez-prl05,
         author = {Chen, Datong and Odobez, Jean-Marc},
       projects = {Idiap},
          month = {7},
          title = {Video {T}ext {R}ecognition using {S}equential {M}onte {C}arlo and Error {V}oting {M}ethods},
        journal = {Pattern Recognition Letters},
         volume = {26},
         number = {9},
           year = {2005},
           note = {A shorter version of the paper appeared in the techreport.},
       crossref = {chen-rr0343},
       abstract = {This paper addresses the issue of segmentation and recognition of text embedded in video sequences from their associated text image sequence extracted by a text detection module. To this end, we propose a probabilistic algorithm based on Bayesian adaptive thresholding and Monte-Carlo sampling. The algorithm approximates the posterior distribution of segmentation thresholds of text pixels in an image 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. One important contribution of the paper is to show that, thanks to the proposed methodology, the likelihood of a segmentation parameter sample can be estimated not using a classification criterion or a visual quality criterion based on the produced segmentation map, but directly from the induced text recognition result, which is directly relevant to our task. Furthermore, as a second contribution of the paper, we propose to align text recognition results from high confidence samples gathered over time, to composite a final result using error voting technique (ROVER) at the character level. Experiments are conducted on a two hour video database. Character recognition rates higher than 93\\%, and word error rates higher than 90\\% are achieved, which are 4 and 3\\% more than state-of-the-art methods applied to the same database.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/odobez-prl.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/odobez-prl.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},
}