• Design And Implementation Of Gabor Filter Based Offline YorÙbÁ Handwritten Recognition System.

  • CHAPTER TWO -- [Total Page(s) 7]

    Page 4 of 7

    Previous   1 2 3 4 5 6 7    Next
    • Fundamentals of data processing & how data is processed
      Data processing is undertaken by any activity which requires collection of data. This data collected needs to be stored, sorted, processed and analyzed. This complete process can be divided into 6 basic simple stages which are:
      1.    Data collection
      2.    Storage of data
      3.    Sorting of data
      4.    processing of data
      5.    Data analysis
      6.    Data presentation and conclusions
      Once the data is collected the need for data entry emerges for storage of data. Storage can be done in physical form by use of papers, in notebooks or in any other physical form. But now since the data collection is large and number of operations needs to be performed for meaningful analysis, the data is stored in digital form. Having the data into digital form enables the user to perform large number of operations in small time and allows conversion into different forms. User can thus select the output which best suits the requirement. (Planning Tank, 2017)
      This continuous use and processing of data follows a cycle called as data processing cycle which might provide instantaneous results or take time depending upon the need of processing data. The complexity in the field of data processing is increasing which is creating a need for advanced techniques. (Planning Tank, 2017)
      Storage of data is followed by sorting and filtering. This stage is highly effected by the format in which data is stored and further depends on the software used. General daily day and non complex data can be stored as text files, tables or a combination of both in Microsoft Excel or similar software. As the task becomes complex which requires performing specific and specialized operations they require different software which are meant to cater the peculiar needs. (Planning Tank, 2017)
      Storing, sorting, filtering and processing of data can be done by single software or a combination of software whichever feasible and required. Data processing thus carried out by software is done as per the predefined set of operations. Most of the modern-day software allows users to perform different operations based on the analysis or study to be carried out. Data processing provides the output file in various formats. (Planning Tank, 2017)
      Different types of output files obtained as “processed” data
      Plain text file – These constitute the simplest form or processed data. Most of these files are user readable and easy to comprehend. Very negligible or no further processing is these type of files.
      Table/ spreadsheet – This file format is most suitable for numeric data. Having digits in rows and columns allows user to perform various operations like filtering & sorting in ascending/descending order to make it easy to understand and use. Various mathematical operations can be applied when using this file output.
      Charts & Graphs – Option to get the output in form of charts and graphs is very useful and now forms a standard features in most of the softwares. This option is very useful when dealing with numerical values reflecting trends and growth/decline. Though there are ample of charts and graphs are available to match diverse requirements there exists situation when there is need to have used defined option. In case no inbuilt chart or graph is available then the options to create own charts i.e. custom charts/graphs comes handy.
      Maps/Vector or image file – When dealing with spatial data the option to export the processed data into maps, vector and image files is of great use. Having the information on maps is of particular use for urban planners who work on different types of maps. Image files are obtained when dealing with graphics and does not constitute any human readable input.
      Other formats/ raw files – These are the software specific file formats which can be used and processed by specialized software. These output files may not be a complete product and require further processing. Thus there will be need to perform multiple data processing. (Planning Tank, 2017)
      Types of data processing
      Manual data processing: In this method data is processed manually without use of machine or electronic device. This method might be accompanied with automatic method for completion of the data processing.
      Mechanical data processing – Data processing is done by use of mechanical device or very simple electronic devices like calculator and type writers. When the need for processing is simple this method can be adopted.
      Electronic data processing – This is the fastest and best available method with highest reliability and accuracy. Technology used is latest as this method uses computers and employed in most of the agencies. The use of softwares forms the part of this type of data processing. (Planning Tank, 2017)
  • CHAPTER TWO -- [Total Page(s) 7]

    Page 4 of 7

    Previous   1 2 3 4 5 6 7    Next
    • ABSRACT - [ Total Page(s): 1 ]ABSTRACT COMING SOON , CHECK OTHERS ... Continue reading---

         

      APPENDIX A - [ Total Page(s): 11 ]s=s+n;                e.putString("d"+num,s);                e.commit();                new AlertDialog.Builder(MainActivity.this)                .setMessage(R.string.learn_sample)                .setNeutralButton(R.string.ok,null)                .show();                dv.resetPath();                Paths.reset();                dv.invalidate();            }        }    ... Continue reading---

         

      CHAPTER ONE - [ Total Page(s): 2 ]CHAPTER ONEINTRODUCTION1.1    BACKGROUND OF THE STUDYCharacter is the basic building block of any language which is used to develop different language structures. Characters are alphabets and the structures developed are the words, strings, sentences, paragraphs and so on (Le Cun et al., 1990). Character recognition also known as optical character recognition is the recognition of optically processed characters. The purpose of character recognition is to interpret input as a sequence of chara ... Continue reading---

         

      CHAPTER THREE - [ Total Page(s): 3 ]CHAPTER THREERESEARCH METHODOLOGY3.1    DATA ACQUISTIONThe Yoruba handwriting images used in this project are those were created for the purpose of this project. This database was only recently assembled by the author of this project, and before this there was no standard database for this field. The database consists of a collection of Yoruba characters images, each containing one character. The images come from Ten (10) different writers, mostly students. All the figures in this th ... Continue reading---

         

      CHAPTER FOUR - [ Total Page(s): 4 ]CHAPTER FOURRESULT AND DISCUSSIONS4.1    SYSTEM RESULT ANALYSISBased on the definition given in Handwriting recognition system, 50% of the respondents can be classified as Strong accurate writers, 30% as accurate writers, 15% as Non poor writers and 5% as poor writers. This shows that 95% of handwriting image in the project belong to strong accurate and accurate writers.As far as the gender is concerned, 60% of the respondents were male and 40% were female. This indicates that men are more ap ... Continue reading---

         

      CHAPTER FIVE - [ Total Page(s): 1 ]CHAPTER FIVESUMMARY, CONCLUSION AND RECOMMENDATION5.1    SUMMARYThis project is predicated by the need and necessity to examine the performance evaluation of the Yoruba handwriting image enhancement algorithms. In a bid to achieve this, the Gabor Filter algorithm was used in order to enhance handwriting images so as to test the quality and efficiency recognition.Having implemented this, the levels of performance of the handwriting image enhancement algorithms (Gabor Filter) by comparing the a ... Continue reading---

         

      REFRENCES - [ Total Page(s): 1 ]REFERENCEHuang, B.; Zhang, Y. and Kechadi, M.; Preprocessing Techniques for Online Handwriting Recognition. Intelligent Text Categorization and Clustering, Vol. 164, 2009.J.Pradeep, E.Srinivasanand S.Himavathi, Diagonal based feature extraction for handwritten alphabets recognition System using neural network, Vol 3, No 1, Feb 2011.Jin Chen, Huaigu Cao, Rohit Prasad, Anurag Bhardwaj and Prem Natarajan,Gabor Features for Offline Arabic Handwriting Recognition, 10, June 9-11, 2010.Jumoke F. A ... Continue reading---