Improvement of the Recognition Rate by Random Forest

Abstract

In this paper; we introduce a system of automatic recognition of characters based on the Random Forest Method in non-constrictive pictures that are stemmed from the terminals Mobile phone. After doing some pretreatments on the picture, the text is segmented into lines and then into characters. In the stage of characteristics extraction, we are representing the input data into the vector of primitives of the zoning types, of diagonal, horizontal and of the Zernike moment. These characteristics are linked to pixels’ densities and they are extracted on binary pictures. In the classification stage, we examine four classification methods with two different classifiers types namely the multi-layer perceptron (MLP) and the Random Forest method. After some checking tests, the system of learning and recognition which is based on the Random Forest has shown a good performance on a basis of 100 models of pictures.

Authors and Affiliations

Youssef Rachidi, Zouhir Mahani

Keywords

Related Articles

Survey on Different Methods of Digital Audio Watermarking

The significant progress of the technology gives the full access to the digital data for retransmitting and reproduction with comfort. Since the benefits of such progress is easily available, they equally immune to some...

Comparison of Mechanical and Dielectric Properties of Pure and L-Cystein Doped Bis Thiourea Zinc Acetate (L-Btza)

The nonlinear optical single crystal of L-cystein doped bisthiourea zinc acetate (BTZA) was grown successfully by slow evaporation technique using water as solvent at room temperature. Elemental Composition percentages w...

Topology Management for Mobile Ad Hoc Networks Scenario

Cooperative communication is the main accessing point in present days. These results can be accessed through proactive protocol like route request packet sending and route request packet receiving. The main issue is how...

Street Level Modeling of Pollutants for Residential Areas

An effort has been done here to model the pollutants concentration using a software i.e., COPERT STREET LEVEL. This software is a Microsoft windows based software and calculates emission on street basis. Working of this...

A Simple Analytical Model for Estimating Long-term Productivity of Multi-fractured Shale Gas Wells

Shale gas production has been successful developed over the past several years. The horizontal well with multistage hydraulic fracturing has proven to be an effective operation of development these unconventional reservo...

Download PDF file
  • EP ID EP390188
  • DOI 10.9790/9622- 0702043743.
  • Views 138
  • Downloads 0

How To Cite

Youssef Rachidi, Zouhir Mahani (2017). Improvement of the Recognition Rate by Random Forest. International Journal of engineering Research and Applications, 7(2), 37-43. https://europub.co.uk/articles/-A-390188