Neural Network For Unicode Optical Character Recognition (Case Study Of DHL, Enugu)

Project and Seminar Material for Computer Science and Computer Engineering

Neural Network For Unicode Optical Character Recognition (Case Study Of DHL, Enugu)


Optical character Recognition (OCR) refers to the process of converting printed tamil text documents into software translated Unicode tamil text. The printed documents available in the form of books, projects, magazines etc are scanned using standard scanners which produce an image of the scanned documents. As part of the preprocessing phase the image like is checked for skewing. If the image is skewed, it is corrected by a simple rotation technique in the appropriate direction. Then the image is passed through a noise elimination phase and is binarized. The preprocessed image is segmented using an algorithm which decomposes the scanned text into paragraphs using special space detection technique and then the paragraphs into lines using vertical histograms, and lines into words using horizontal histograms, and words into character image glyphs using horizontal histograms.

Each image glyph is comprised of 32 x 32 pixels, thus a data base of character image glyphs is created out of the segmentation phase. Then all the image glyphs are considered for recognition using Unicode mapping. Each image glyph is passed through various routines which extract the features of the glyph. The various features that are considered for classification are the character height, character width, then number of horizontal lines (Long and short), the number of vertical lines (long and short), the horizontally oriented curves, the vertically oriented curves, the number of circles, number of slope lines, image centroid and special dots. The glyphs are now set ready for classification based on these features. The extracted features are passed to a support vector machine (SVM) where the characters are classified by supervised learning algorithm. These classes are mapped into Unicode for recognition. Then the text is reconstructed using Unicode fonts.

Chapter One

1.0 Introduction

Character is the basic building block of any language that is used to build different structures of a language. Characters are the alphabets and the structures are the words, strings and sentences.

Optical character Recognition (OCR) is the process of converting an image of text, such as a scanned project character, document or electronic fax file, into computer-editable text. The text in an image is not editable. The letters/characters are made of tiny dots (pixels) that together form a picture of text. During OCR, the software analyzes an image and converts the pictures of the characters to editable text based on the patterns of the pixels in the image. After OCR, you can expert the converted text and use it with a variety of word-processing, page layout and spreadsheet applications. OCR also enables screen readers and refreshable bralle displays to read the text contained in images.

Optical character Recognition (OCR) deals with machine recognition of characters present in an input image obtained using scanning operation. It refers to the process by which scanned images are electronically processed and converted to an editable text. The need for OCR arises in the context of digitizing tamil documents from the ancient and old era to the latest, which helps in sharing the data through the internet.

A properly printed document is chosen for scanning. It is placed over the scanner, A scanner software is invoked which scans the document. The document is sent to a program that saves it in preferably TIF, JPG or GIF format, so that the image of the document can be obtained when needed. This is the first step in OCR (Vijaya Kumar, 2001), the size of the input image is as specific by the user and can be of any length but is inherently restricted by the scope of the vision and by the scanner software length.

This is the first step in the processing of scanned image. The scanned image is checked for skewing, there are possibilities of image getting skewed with either left or right orientation.

Here, the image is first brightened and binarized the function for skew detection checks for an angle of orientation between +15 degrees and if detected than a simple image rotation is carried out till the lines match with the true horizontal axis, which produce a skew corrected image.

After pre-processing, the noise free image is passed to the segmentation phase, where the image is decomposed into individual characters.

Algorithm for Segmentation:

  1. The binarized image is checked for inter line space
  2. If interline spaces are detected than the image is segmented into sets of paragraphs across the interline gap.
  3. The lines in the paragraphs are scanned for horizontal space interaction with respect to the background.
  4. Histogram of image is used to detect the width of the horizontal lines. Then the lines are scanned vertically for vertical space intersection.

Here, histograms are used to detect the width of the words, then the words are decomposes into characters using character width computation. Fig 3 a shows the original image and Fig 3b shows the decomposition of image into single image character glyphs of size 32 x 32 (LTG, 2003, Vijaya Kumae, 2001).

1.1 Statement of Problems

Owing to:

  1. The security difficulties, people face in transferring information/data.
  2. Security difficulties, people encountered when or ordering for this outside their immediate environment.
  3. Time wasted in manual transferring of information.
  4. Incidence of mail theft, pilfering, tampering and all forms of fraudulent activities.
  5. Important nature of data/information in the growth of any organization.
  6. The need arise for the development of a neural networks for Unicode optical character recognition.

1.2 Purpose of Study

The main purpose of this study is to put to an end the security difficulties, people encountered when sending data/information or ordering for things outside their immediate location. This is actualized by designing neural network for Unicode optical character recognition which is user friendly and interactive. By the time this software is designed and implemented, the security difficulties encountered with manual method of transferring and receiving information with be eliminated.

1.3 Aims and Objectives

The aims and objectives of this project are listed below:

  1. To develop, promote and provide adequate and efficiently co-ordinated posted services at reasonable rates.
  2. To maintain an efficient system of collection, sorting and delivery of mail nationwide.
  3. To demonstrate increased motivation to the DHL workers.
  4. To provide various types of mail services to meet the needs of different categories of mailers.
  5. To eliminate the error involved with the manual method of ordering for data/information or items.
  6. It guarantees prompt mail delivery to the co-operate customers’ door step; thereby prevent delay and avoid congestion
  7. It saves customer’s timer
  8. It is economical and affordable.

1.4 Scope of Study

The scope of this project is to build a system, that automatically recognize the characters of English language input to the system, and later on they may be used for different purposes.

1.5 Limitation of Study

Owing to the scope of this project work as stated above, this project work is limited to a neural networks for Unicode optical character recognition DHL Enugu.

It is important to mention here that time was a major constraint in the course of fact finding. It is also wise to mention here that some information we need to work with was not collected because of the unwillingness of the staff to review such information.

1.6 Definition of Terms

Mail Business:

The commercial transaction of customer with suppliers.


This is the collection of hardware, software, data information, procedures and people.


This is data that have been processed interpreted and understood by the recipient of the message or report.


It is the collection of information that is related to a particular subject or purpose.


This is the electromechanical part of computer system.


This is the process through which data/information is stored for future use.


This is a person working in an office or establishment/organization.


This is an electronic machine that can accept, handle and manipulate data by performing arithmetic and logic operations with out human intervention usually under the control of programmes.


It is the basic building block of any language that is used to build different structure of a language.

Optical Character recognition (ORC):

IT is the process of converting an image of text such as a scanned project character, document or electronic fax file, into computer editable text.

Chapter Five

5.0 Summary, Recommendation and Conclusion

5.1 Summary

Optical Character Recognition (OCR) is aimed at recognizing printed Tamil document, the input document is read preprocessed, feature extracted and recognized and the recognized text is displayed in a picture box. Thus the Tamil OCR is implemented using a C- Neural Network library. A compete tool bar is also provided for training, recognizing and editing options.

Tamil is an ancient language, there are millions and billions of books which are written by numerous well known authors. Maintaining and getting the contents from and to the books is very difficult.

OCR eliminates the difficulty by making the data available in printed format. In a way OCR provides a paperless environment, OCR provides knowledge exchange by easier means. If the knowledge base of rich Tamil contents is created, it can be accessed by people of varying category with ease and comfort. Still there are scholars who are interested in accessing the contents to look for knowledge.

OCR is currently used to maintain the history of students in universities. If OCR is available then processing and maintaining the students records becomes easier. The student’s forms can be directly scanned, extracted for details and directly transformed into a student Database.

5.2 Recommendation

Recognition of Latin-scrip, typewritten text is still not 100% accurate even where clear imaging is available. One study based on recognition of 19th and early 20th century newspaper pages concluded that character-by-character OCR accuracy for commercial OCR software varied from 71% to 90%, total accuracy can only be achieved by human review.

Other areas including recognition of head printing, cursive handwriting, and printed text in other scripts (especially those East Asian language characters which have many strakes for a single character) are still the subject of active research.

Accuracy rates can be measured in several ways, and how they are measured can greatly affect the reported accuracy rate. For example; if word context (basically a lexicon of words) is not used to correct software finding non-existent words, a character error rate of 1% (99% accuracy) may result in an error rate of 5% (95% accuracy) or worse if the measurement is based on whether each whole word was recognized with no incorrect letters.

On-lined character recognition is sometimes confused with optical character recognition (see handwriting recognition). OCR is an instance of off-line character recognition, where the system recognizes the fixed static shaped of the character, while on-line character recognition instead recognize the dynamic motion during handwriting. For example; on-line recognition, such as that used for gestures in the pinpoint OS or the tablet PC can tell whether a horizontal mark was drawn right-to-left, or left-to-right, on-line character recognition is also referred to other terms such as dynamic character recognition, real time character recognition,, and intelligent character recognition or ICR.

5.3 Conclusion

OCR can also play, a major role in the business environment, OCR reduces cost and effort by eliminating manual data entry, etc if OCR is available, it becomes easier to extract and transform the data into business BASE and promote business without the need for large mobility (data people). The increasing number of faxes and paper documents received by businesses often originate from the same suppliers or customers and have a format and layout that have not changed for some time. The data within these documents have to be manually interpreted and re-keyed into business applications as part of key business processes (e.g purchase, orders and invoices into accounting systems for Account Receivables and payable, students data etc). the larger the volume of documents received, the greater he manual resources requires entering the data into business applications.

The scope for errors and delay to critical business processes also increases as volume increases, if it is handled manually. By scanning the documents to create TIFF image files and automatically routing electronic fax images to OCR, the errors, cost and delay of manual data entry can be avoided, as OCR can automatically extract data form the documents and for format the data for on-ward delivery to other applications.

Get Complete Project Material

5,000 5000

The Complete Material Will Be Sent to You in Just 2 Steps

Quick & Simple…

Step One Purchase

Make Payment (Through Transfer) of ₦5,000 to the Account Below

Zenith BankAcc No: 1225513212
Samphina Academy
Current Account

Or CLICK HERE To Pay With Debit Card

CLICK HERE To Purchase Material ($15)

Step Two Purchase

Send the Following Details on WhatsApp ( 08143831497) After Payment

  1. Payment Details

  2. TOPIC: Neural Network For Unicode Optical Character Recognition (Case Study Of DHL, Enugu)

The Complete Material Will Be Sent To You On WhatsApp After Receiving Your Details
T & C Apply

  Contact Our Help Desk

Need a Different Topic? Perform a Quick Search

List of Related Works

Click on Any Topic to Preview the Content

Samphina Academy

Samphina Academy is an Online Educational Resource Center that is aimed at providing students with quality information and materials to aid them in succeeding in their academic pursuit.