Слайд 2
![About recognizing text. Now a text Recognized is a topical](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-1.jpg)
About recognizing text.
Now a text Recognized is a topical theme in
development of information systems. Recognize text by computer is difficult because it can not determinate relativity of all visible objects unlike a human and it doesn’t have all forms of symbol in memory.
Слайд 3
![Neural network](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-2.jpg)
Слайд 4
![Program For the first we must training our network. Read](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-3.jpg)
Program
For the first we must training our network.
Read pictures of all
classes,
Filter each picture,
Build a sign vector for each symbol.
Слайд 5
![Time of training](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-4.jpg)
Слайд 6
![Test pictures](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-5.jpg)
Слайд 7
![Test pictures](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-6.jpg)
Слайд 8
![Test pictures](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-7.jpg)
Слайд 9
![Conclusions 15 pictures is tested. Global percent of recognize≈ 87%.](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/141465/slide-8.jpg)
Conclusions
15 pictures is tested.
Global percent of recognize≈ 87%.
An average time of
recognize a symbol ≈ 0.2 sec.