Text extraction from fuzzy inspection image based on adaptive immune factor
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU147419" target="_blank" >RIV/00216305:26220/21:PU147419 - isvavai.cz</a>
Result on the web
<a href="https://gdzjg.org.in/index.html" target="_blank" >https://gdzjg.org.in/index.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.16136/j.joel.2021.12.0290" target="_blank" >10.16136/j.joel.2021.12.0290</a>
Alternative languages
Result language
angličtina
Original language name
Text extraction from fuzzy inspection image based on adaptive immune factor
Original language description
In order to achieve accurate and efficient extraction of text object from fuzzy inspection image. In this paper, aiming at various types of fuzzy inspection images, an adaptive immune algorithm is proposed based on the principle of artificial immune and the concept of immune factors combined with adaptive filtering algorithm. The new algorithm proposed in this paper first realizes adaptive filtering by changing the filter window dynamically, which not only preserves the details of the target text, but also filters out the noise. After that, we design different immune factors according to different types of fuzziness, so as to ensure the integrity and accuracy of the extracted text object to the greatest extent. The experimental results show that the proposed new algorithm is more effective when dealing with the same type of blurred inspection images, the true positive rate (TPR) date of the new algorithm is better than other traditional target extraction algorithms. Moreover, the false positive rate of the new algorithm is better than that of other false positive rate (FPR) data. Through the analysis of each evaluation index, it shows that the algorithm in this paper is feasible and accurate in the text extraction of fuzzy inspection image. © 2021, Science Press in China. All right reserved.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
20201 - Electrical and electronic engineering
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Guangdianzi Jiguang/Journal of Optoelectronics Laser
ISSN
1005-0086
e-ISSN
—
Volume of the periodical
32
Issue of the periodical within the volume
12
Country of publishing house
CN - CHINA
Number of pages
7
Pages from-to
1293-1299
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85125178737