Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.lang.java.programmer > #39290 > unrolled thread
| Started by | chad altenburg <cdalten@gmail.com> |
|---|---|
| First post | 2020-02-12 08:38 -0800 |
| Last post | 2020-02-14 05:54 -0800 |
| Articles | 4 — 2 participants |
Back to article view | Back to comp.lang.java.programmer
Optical Character Recogontion Algorithm question chad altenburg <cdalten@gmail.com> - 2020-02-12 08:38 -0800
Optical Character Recogontion Algorithm question chad altenburg <cdalten@gmail.com> - 2020-02-12 13:23 -0800
Re: Optical Character Recogontion Algorithm question Bheesham Persaud <me@bheesham.com> - 2020-02-14 02:58 -0500
Re: Optical Character Recogontion Algorithm question chad altenburg <cdalten@gmail.com> - 2020-02-14 05:54 -0800
| From | chad altenburg <cdalten@gmail.com> |
|---|---|
| Date | 2020-02-12 08:38 -0800 |
| Subject | Optical Character Recogontion Algorithm question |
| Message-ID | <5c823915-a4fb-49c5-a24f-bb2e741f69eb@googlegroups.com> |
I have a camera that can read in text from an image like 12:05 PM And based on this image, it will convert it to the corresponding text so that the computer can further processes this time. The problem is that the "0" has a line through it. As a result, sometimes the algorithm will interpret the "0" with a line though it as either an "8" or an "e". Should I handle this as special cases in the OCR processing system itself or should I attempt to maybe try to further train the images at the Machine Learning code level?
[toc] | [next] | [standalone]
| From | chad altenburg <cdalten@gmail.com> |
|---|---|
| Date | 2020-02-12 13:23 -0800 |
| Message-ID | <96a3d90b-cdec-415d-8ceb-f5dc2a4b1192@googlegroups.com> |
| In reply to | #39290 |
Never mind. Someone on another site answered it for me.
[toc] | [prev] | [next] | [standalone]
| From | Bheesham Persaud <me@bheesham.com> |
|---|---|
| Date | 2020-02-14 02:58 -0500 |
| Message-ID | <r25jvl$a1d$1@dont-email.me> |
| In reply to | #39291 |
On 2020-02-12 4:23 p.m., chad altenburg wrote: > Never mind. Someone on another site answered it for me. > What did they suggest?
[toc] | [prev] | [next] | [standalone]
| From | chad altenburg <cdalten@gmail.com> |
|---|---|
| Date | 2020-02-14 05:54 -0800 |
| Message-ID | <89ef0285-f7cf-49bf-ad9c-eb7c07a84db1@googlegroups.com> |
| In reply to | #39292 |
On Thursday, February 13, 2020 at 11:58:54 PM UTC-8, Bheesham Persaud wrote: > On 2020-02-12 4:23 p.m., chad altenburg wrote: > > Never mind. Someone on another site answered it for me. > > > > What did they suggest? To do part of the checking at the OCR processing level. And this is kind of Java related because the API that I uses Java which can be found here... https://codelabs.developers.google.com/codelabs/mobile-vision-ocr/#0
[toc] | [prev] | [standalone]
Back to top | Article view | comp.lang.java.programmer
csiph-web