A Novel Approach to Recognize the off-line Handwritten Numerals using MLP and SVM Classifiers
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2013, Vol 4, Issue 7
Abstract
This paper presents a new approach to off-line handwritten numeral recognition. Recognition of handwritten numerals has been one of the most challenging task in pattern recognition. Recognition of handwritten numerals poses serious problems because of high variability in numeral shapes written by individuals. This paper concerns with offline handwritten numeral recognition based on MLP and SVM classifiers. The performance of character recognition system depends heavily on what kind of features extraction techniques are being used. In this work, we have collected 1200 samples of isolated numerals, contributed by 24 writers and each one has written it five times. In this paper we propose a modified Hough transformation technique and four view projection Profiles technique to extract the feature of numerals. Using the modified Hough transformation technique, we have achieved maximum accuracy of about 93.12% and 72.5% by SVM and MLP classifiers and with four view projection profiles technique; we obtained the 96.04% and 98.73% recognition accuracy by SVM and MLP classifiers.
Authors and Affiliations
Mamta Garg , Deepika Ahuja
Keywords
Related Articles
- EP ID EP130738
- DOI -
- Views 115
- Downloads 0
Efficient Keyword Search Across Relational Databases
In Traditional Keyword search system over relational data bases, a keyword query is submitted by the user to the system and the relevant results are retrieved, where the user has restricted knowledge about the data. Whil...
Wavelet Based Normal and Abnormal Heart Sound Identification using Spectrogram Analysis
The present work proposes a computer-aided normal and abnormal heart sound identification based on Discrete Wavelet Transform (DWT), it being useful for tele-diagnosis of heart diseases. Due to the presence of Cumulative...
A SURVEY OF TOOLS FOR EXTRACTING AND ALIGNING THE DATA IN WEB
The world-wide web is rapidly growing day by day in all fields, mining the data from multiple websites is necessary to filter the relevant contents. Although many approaches developed for extracting the data, there were...
Dynamic Time Quantum in Shortest Job First Scheduling Algorithm (DTQSJF) for Unpredictable Burst Time of Processes
In multitasking and time sharing operating system the performance of the CPU depends on waiting time, response time, turnaround time, context switches from the process mainly depends on the scheduling algorithm. Shortest...
Mobicast Routing Protocol with Multiple Sink Zone Formation in Underwater Sensor Networks
In this paper, we groping the multiple Sink Zone formation Mobicast routing protocol for 3-D Underwater Sensor Networks (USNs). The 3-D USNs consists a number of sensor nodes which are deployed in 3-D environment and Sen...