Text extraction from fuzzy inspection image based on adaptive immune factor

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Text extraction from fuzzy inspection image based on adaptive immune factor

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Text extraction from fuzzy inspection image based on adaptive immune factor

Popis výsledku anglicky

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.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Guangdianzi Jiguang/Journal of Optoelectronics Laser

ISSN

1005-0086

e-ISSN

—

Svazek periodika

32

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

CN - Čínská lidová republika

Počet stran výsledku

7

Strana od-do

1293-1299

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85125178737