Optical Character Recognition (OCR)

The aim of OCR is to classify optical patterns corresponding to alphanumeric or other characters.

Description

The aim of Optical Character Recognition (OCR) is to classify optical patterns (often contained in a digital image) corresponding to alphanumeric or other characters. The process of OCR involves several steps including segmentation, feature extraction, and classification. This program use Image Processing Toolbox to get it.

For more information, visit: http://www.matpic.com (spanish)
or http://www.eqbyte.com (english)

Acknowledgements

This file inspired Optical Character Recognition(Lower Case And Space Included).

• Required Products: Image Processing Toolbox
• MATLAB release: MATLAB 7.1.0 (R14SP3)

[Wej]

Anyone can help, How to run this code ?

[Chandra Shekhar]

Nice work.

[msp]

sir it is not able to detect the text from video frame. please help

[thebohr]

excuse me for all people,i'm newbie about this..i am a student of computer science departmen and i have an interest of making OCR buat read the character or text from hand writing. for example, i write something on the paper and convert it to digital..is it possible ?
thanks before

[Latte]

 

[samira]

Hola diego, tengo una pregunta estoy tratando de hacer un algoritmo que me reconozca las letras usando redes neuronales con una interfaz grafica, pero el manuscrito de prueba lo tengo que cargar, queria saber si habia alguna manera de crear un recuadro sobre el GUI que sea como "paint" y se pueda dibujar la letra directamente ahi con el mouse

[shweta]

hav used this image and getting errors

http://i275.photobucket.com/albums/jj286/onedrunkirishman/RagTagBanner6.jpg

[tiago]

 

[sriharsha ponnathapura]

Nice code. I used it to generate the templates for 187 fonts in english. I dont know where to upload it for everyone to use..

[OCR_try]

nice code...

[imran]

 

[imran]

Sir its a nice code. i am getting little problem with understanding of this code. can you let me know how did you create the template.mat file from the letters. my is the same i also want to extend this code for lower case letters and local languages. one other thing is that when i replace
sem=corr2(templates{1,n},imagn); in read_letter.m to directly read the letters images and compare or find the correlation. but it does not gives the accurate results. if you read please must reply me.

[Shavi]

Can anybody tell me that how to understand this code for character recognition?
or what is the way
please help.
Its Urgent!!

[Wyfi Mcfly]

maximum rather

[Wyfi Mcfly]

nicely done. for more robust results i found preforming a skeletal reduction of the input image text (when properly prepared), and making a template of skeletal comparisons for the correlation coefficient calculation can get around most font issues.
The next thing is properly aligning the input letter to that of the template. This can be accomplished in many ways, or you can simply preform an image rotation of all 360 degrees at take the minimum confidence coefficient of that process.

[Shavi]

Hello Diego...
Cheers for ur code..
I want to know that how to recognize special characters like +,/,| etc..??
Also your code is not applicable for lowercase letters so please give me some information that how to tackle this.

Thanks!!

[Pon Selvalingam]

Hello sir
It is perfect code, really thanks
Please send this project pdf

[sidharth jhawar]

hello sir,the code works well for majority of the images..perhaps doesnt work for joined text.sir,if u cud plz send a text file describing the objective if all the four .m files??

[pankaj Durve]

i use matlab 6.5,wheh i run oCR project,then templates loading error is come.why error is come?how to error is removed?

[kolayuyelik kolay]

Quite good!

[sanjana]

plz anyone can give me the logic behind this program....on wht basis feature extraction has been done...nd hw Image proceesing tool box is used for simulatin...plz help me out asap....

[Mr Smart]

 

[Fabio Bento]

Quite good!

[Popescu]

Hello! Did any one succeeded to add some new character templates? I am trying to add the OCR-B font templates but I don't know how to do it. I tried in photoshop but it didn't work. Does anyone know if is there a special program to do it?

[Fukuo]

Thx!
It helps me so much!

[Lamis zaki]

Really good job , you helped me out :) thnx

[Sadegh]

It is perfect code, really thanks

[King Lee]

Hi, im planning to improve your code to be able to recognize about the small cases alphabet also,but i cannot access the thumb.db files in the letter number's folder...
Can you tell me it need what to open?

[SURYA]

sir, nice your OCR project...i also using your code for my character recognition for my project...but i code some error because of edge of image...can sir look my project and suggest a solution...i need ur help sir..tq

here is my project

http://www.filehosting.org/file/details/203684/my_project.rar

[vipin vc]

good program
Dear Bogdan

Suppose that we have an image with two lines of text. With "clip", only obtain one line and leave the rest.

[Khaing Thaw]

Hi Hannah,
these images of letters are in the letters_numbers folder. there are 36 image file, if u also want to recognize lower case letters u can add lower letter image files into that folder. and need to edit and add some coding in .m file in OCR folder.
clip is not built-in function, it is a sub function use in line.m function to crop the lines, u can see it lower part of line.m function.
good luck,
thaw

[Claus Becker]

 

[Hannah Whitby]

Hi Diego and everyone,
Good program, but I have a few questions:
Where/how did you make these images of the letters that are in the template? I need to be able to identify lower case letters as well as upper case and have tried just using microsoft paint but although they are .bmp the appear the wrong format. Any ideas anyone?
Also - what is 'clip'? my matlab doesn't seem to support it but when i changed it to imcrop it stalls.
Thanks,
Hannah

[Khaing Thaw]

Hi Diego, Nice ur coding, complete in a few lines, functions, templates ,... except clip function :P

Hi Ashley, to find the spaces calculate the spacing of components in image Labeled,. it is my suggestion, how Diego?

Hi Priyanka, add some coding in create_templates.m and image files (BMP, 42x24) for lower characters,.

Thanks Diego,.

[Ashley Figer]

Dear sir,
how do we detect blank spaces between the characters?
and print them in the output

[Theodoros Giannakopoulos]

 

[pupu QQ]

not very good for car plate in China.

[mrudula sekhar]

hi sir, ur work is really good.
i am too trying to implement the same as a part of my academics, so like to know more about the subject. can u please help me ?
i did like to know about the different steps involved in character recognition. can u provide me with some pdf documents which i can depend to complete my project.

[Alexandru]

Problem solved. The problem was the performance of my PC.

Thanks again for the program

[Alexandru]

hello,

i use Matlab 7.9.0 (R2009b) and i received an error "Segmentation violation detected" while i tried to run the OCR program. i'm beginner in matlab so can anyone help me please?

PS: thank you Diego for the OCR program

[uet taxila]

 

[Eurico]

Hi Mr. Diego,
at the moment i'm developing a computer vision system to detect and recognize license plates.I experienced your project and works very well but i have a question. What method are you using to do the recognition? SVM's? Neural Networks?

kind regards

[Priyanka M]

Hi Diego..
dis is priyanka,from India
It was a very nice job.Can u plz help me with dis project..???
Plz tell me how to recognize lower case letters..?? and also plz help me with how to obtain the bitmap images of the letters u place in letters_numbers folder so dat I can try for the regional languages...
Plz plz plz do reply me....

[Diego Orlando]

Dear Bogdan

Suppose that we have an image with two lines of text. With "clip", only obtain one line and leave the rest.

Kind regards.

[blue]

Thank you for answare, but I have a nother question : in lines.m file exist next line:
im_texto=clip(im_texto);
What exactly make cilp in this expresion?

[Diego Orlando]

Hello Bogdan

I use IMCROP instead CLIP.

Kind regards.

[blue]

I hava a question for Mr Diego Barragán.
In the Zip file I cannt find the function clip, but On this page link http://www.matpic.com/MATLAB/MATLAB_OPTICAL_CHARACTER_RECOGNITION.html, exist!!!! Where is integrate this function?

[vaibhav sharma]

Please can anyone tell me how to implement this code on fpga??
Its urgent....mail me at [e-mail]

thank you very much

[nurul]

dear sir,
it was a very nice job. however for certain pics it cant read the image correctly. do u have any idea on how to add the image filtering codes to make this program read the image more accurate?
i really need ur help on this matter.

[nurul]

 

[Thabit]

Sid H, come on!

If you can do better, we are waiting!

[Sid H]

Amateur work, both code and concepts. Not robust. Cant support fonts, noise or files different from what the up-loader provides. But great as a concepts demo for undergrad-and-below classes.

[chaogui xia]

thank you

[Hooman]

Very nice job, I have 2 questions the code ignores white space which should not and also it does not detect lowercase letters.
how should we detect white spaces between words?

[Cong Zhou]

good job!

[Cong Zhou]

 

[karthik sarma]

this program is not working for other image files. i created some image files using paint in ariel and times new roman font. the program failed to give correct result

[yusor]

Anybody can help me? My FYP is about converting an image to text. Image may be frim newpaper (anywhere) and should be converted into text and saved into Doc. or pdf but it must retain the oiginal format.

Thank u,
Yusser

[Rushmi]

It works great.But for images with dots or small patches the result is ambiguous.If the code can eliminate this problem,(not recognizing non characters) it will be a good algorithm for character recognition.

[athi rayan]

hello sir please give me as a compltet report in ocr

[ved vrath]

cz

[firas aakroum]

?????

[manish arora]

these files really works..
result not being 100%..

[minnal sagi]

fine

[Bilal KONUK]

hi author
i am using matlab 6.5 version. Can i work your project my matlab?

[eklil alwrd]

 

[Paul Paul]

 

[raghav khanna]

can u tell me wat feature algorithm r u using??

[Tran Dinh Vuong]

Dear Sir, I'm doing handwritten english character recognition.Please guide me to progress this project. thanks lot.

[Pradeep Mapitigama]

Dear Sir,
I'm doing handwritten english character recognition.Please guide me to progress this project.I'm doing this for fullfill the MSc.in computer science.
thanks lot.

[Vihang Patil]

Nice work. Tried creating my own images of numbers and names alike and found sometimes some letters being wrongly identified, especially I, 1, O,0,Q
Other than that nice work!

[John Smith]

Good application

[Diego Barragán]

Hi, this is Diego Barragán, from Ecuador.

I appreciate your comments about OCR.

The error perhaps is due the version of MATLAB. I use version 7.1.0.246 (R14) Service Pack 3.

And other restriction of OCR is the size of letter. The size must be bigger or equal to 42 x 24 pixels.

Regards.

[Austin K]

this is a very good work.
a very good logic and simple to understand .
yet there are lot of sectors which can improve.
and i dont know why it happens is that there is a error while loading the templates.
always shows that the file was corrupted.
any way best wishes and once again good work.