Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM

  title={Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM},
  author={Reza Ebrahimzadeh and Mahdi Jampour},
  journal={International Journal of Computer Applications},
Automatic Handwritten Digits Recognition (HDR) is the process of interpreting handwritten digits by machines. There are several approaches for handwritten digits recognition. In this paper we have proposed an appearance feature-based approach which process data using Histogram of Oriented Gradients (HOG). HOG is a very efficient feature descriptor for handwritten digits which is stable on illumination variation because it is a gradient-based descriptor. Moreover, linear SVM has been employed as… Expand
Recognition of Handwritten Digits using Histogram of Oriented Gradients
Off-line recognition of text plays a significant role in several applications, such as cheque verification and mail sorting. However, the selection of the technique for feature extraction remains aExpand
Handwritten Digit Recognition based on DWT and DCT
This work has been tested with ADBase database containing 70,000 digits images, and a comparison made against some existing techniques, and promising results have been obtained. Expand
A Novel Handwritten Digits Recognition Method based on Subclass Low Variances Guided Support Vector Machine
A new subclass algorithm based on COSVM, which takes advantage of the target class clusters variance information and is compared with other methods based on other contemporary one-class classifiers, on well-known standard MNIST benchmark datasets and Optical Recognition of Handwritten Digits datasets. Expand
Recognition of Handwritten Indic Script Numerals Using Mojette Transform
An attempt is made to recognize handwritten digits written in four different scripts namely, Bangla, Devanagari, Arabic and Telugu using Mojette transform using Principal Component Analysis (PCA). Expand
Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition
This paper proposes the use of one of the latest swarm intelligence algorithms, the fireworks algorithm, for the support vector machine parameters tuning, and achieves better results compared to other approaches from literature. Expand
Handwritten Digit Recognition and Text Conversion using MNIST Dataset
Abstract The aim of this paper is to implement a better and accurate approach to perceive and foresee manually written digits from 0 to 9 and determine the identity of the digit. It is done byExpand
SVM Kernel Configuration and Optimization for the Handwritten Digit Recognition
The Monte Carlo method was used to optimize kernel parameters and it turned out to be a simple and fast method, compared to other optimization algorithms. Expand
A Novel Method for Persian Handwritten Digit Recognition Using Support Vector Machine
Results revealed that the detection accuracy of such method has 99% accuracy with an adequate rate due to existing unacceptable samples in the database, therefore, the proposed method could improve the outcomes compared to other existing methods. Expand
Metaheuristics for feature selection in handwritten digit recognition
Assessment of three swarm intelligence optimization algorithms for feature selection optimization, called Binary Fish School Search, Advanced Binary Ant Colony Optimization and Binary Particle Swarm Optimization, for the recognition of handwritten digits found a considerable reduction in the number of features used for digit classification on MNIST. Expand
Improved Handwritten Digit Recognition method using Deep Learning Algorithm
This work compared traditional machine learning method versus Deep Learning model, namely Convolutional Neural Network (CNN), on Handwritten Digit Recognition using MNIST dataset and showed that CNN algorithm reaches higher recognition accuracy than Support Vector Machine (SVM). Expand


Handwritten digit recognition using biologically inspired features
This work uses the output of a biologically inspired model for visual recognition as a feature space which is used to train a linear classifier for recognizing handwritten digits using the MNIST and USPS datasets. Expand
A novel hybrid CNN-SVM classifier for recognizing handwritten digits
This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM), which have proven results inExpand
Recognition Method for Handwritten Digits Based on Improved Chain Code Histogram Feature
Improvements based on Chain Code His- togram (CCH) and its first differential characteristics are proposed and the recognition rate is not only higher than CCH and first differential CCH, but also closely to the rec- ognition rate of their combination. Expand
Efficient Pattern Recognition Using a New Transformation Distance
A new distance measure which can be made locally invariant to any set of transformations of the input and can be computed efficiently is proposed. Expand
A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application
A methodology where local regions of varying heights and widths are created dynamically and genetic algorithm (GA) is applied on these local regions to sample the optimal set of local regions from where an optimal feature set can be extracted that has the best discriminating features. Expand
An Application: Handwritten Digit Recognition
In this chapter, this chapter presents an example of how pattern classification can be carried out in a digit recognition problem, with a data set of 6670 training patterns and 3333 test patterns. Expand
Incremental Tensor Principal Component Analysis for Handwritten Digit Recognition
To overcome the shortcomings of traditional dimensionality reduction algorithms, incremental tensor principal component analysis (ITPCA) based on updated-SVD technique algorithm is proposed in thisExpand
Histograms of oriented gradients for human detection
  • N. Dalal, B. Triggs
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied. Expand
Employing Neocognitron Neural Network Base Ensemble Classifiers To Enhance Efficiency Of Classification In Handwritten Digit Datasets
The purpose of this paper is not only to exemplify learning behaviour of neo-cognitron as base classifiers, but also to purport better fashion to combine neural network based ensemble classifiers. Expand
Extracting Support Data for a Given Task
It is observed that three different types of handwritten digit classifiers construct their decision surface from strongly overlapping small subsets of the data base, which opens up the possibility of compressing data bases significantly by disposing of theData which is not important for the solution of a given task. Expand