Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1
In this paper, we study stochastic models for discrete letter encoding and object classification via ensembles of different modality datasets. For these models, the minimal values of the average mutual information between a given ensemble of datasets and the corresponding set of possible decisions a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2024-06-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480318e.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086505878716416 |
|---|---|
| author | M.M. Lange A.M. Lange |
| author_facet | M.M. Lange A.M. Lange |
| author_sort | M.M. Lange |
| collection | DOAJ |
| description | In this paper, we study stochastic models for discrete letter encoding and object classification via ensembles of different modality datasets. For these models, the minimal values of the average mutual information between a given ensemble of datasets and the corresponding set of possible decisions are constructed as the appropriate monotonic decreasing functions of a given admissible error probability. We present examples of such functions constructed for a scheme of coding independent letters represented by pairs of observation values with possible errors as well as for a scheme of classifying composite objects given by pairs of face and signature images. The inversions of the obtained functions yield the lower bounds for the error probability for any amount of processed information. So, these functions can be considered as the appropriate bifactor fidelity criteria for source coding and object classification decisions. Moreover, the obtained functions are similar to the rate distortion function known in the information theory. |
| format | Article |
| id | doaj-art-60337a83d48e4ec5ae84388abc799891 |
| institution | Kabale University |
| issn | 0134-2452 2412-6179 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj-art-60337a83d48e4ec5ae84388abc7998912025-02-06T12:54:11ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792024-06-0148346047010.18287/2412-6179-CO-1362Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1M.M. Lange0A.M. Lange1Federal Research Center "Computer Science and Control" RASFederal Research Center "Computer Science and Control" RASIn this paper, we study stochastic models for discrete letter encoding and object classification via ensembles of different modality datasets. For these models, the minimal values of the average mutual information between a given ensemble of datasets and the corresponding set of possible decisions are constructed as the appropriate monotonic decreasing functions of a given admissible error probability. We present examples of such functions constructed for a scheme of coding independent letters represented by pairs of observation values with possible errors as well as for a scheme of classifying composite objects given by pairs of face and signature images. The inversions of the obtained functions yield the lower bounds for the error probability for any amount of processed information. So, these functions can be considered as the appropriate bifactor fidelity criteria for source coding and object classification decisions. Moreover, the obtained functions are similar to the rate distortion function known in the information theory.https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480318e.htmlsource codingensemble of datasetsentropyobject classificationerror probabilitymutual informationrate distortion function |
| spellingShingle | M.M. Lange A.M. Lange Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 Компьютерная оптика source coding ensemble of datasets entropy object classification error probability mutual information rate distortion function |
| title | Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 |
| title_full | Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 |
| title_fullStr | Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 |
| title_full_unstemmed | Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 |
| title_short | Information-theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets M.M. Lange 1, A.M. Lange 1 |
| title_sort | information theoretic bounds for accuracy of letter encoding and pattern recognition via ensembles of datasets m m lange 1 a m lange 1 |
| topic | source coding ensemble of datasets entropy object classification error probability mutual information rate distortion function |
| url | https://www.computeroptics.ru/eng/KO/Annot/KO48-3/480318e.html |
| work_keys_str_mv | AT mmlange informationtheoreticboundsforaccuracyofletterencodingandpatternrecognitionviaensemblesofdatasetsmmlange1amlange1 AT amlange informationtheoreticboundsforaccuracyofletterencodingandpatternrecognitionviaensemblesofdatasetsmmlange1amlange1 |