Object detection and object classification using machine learning Algorithms

Abstract

Urban objects are characterized by a very variable representation in terms of shape, texture and color. In addition, they are present multiple times on the images to be analyzed and can be stuck to each other. To carry out the automatic localization and recognition of the different objects we propose to use supervised learning approaches. Due to their characteristics, urban objects are difficult to detect and conventional detection approaches do not offer satisfactory performance. We proposed the use of a wide margin separator network (SVM) in order to better merge the information from the different resolutions and therefore to improve the representativeness of the urban object. The use of an SVM network makes it possible to improve performance but at a significant computational cost. We then proposed to use an activation path making it possible to reduce complexity without losing efficiency. This path will activate the network sequentially and stop the exploration when the probability of detecting an object is high. In the case of a location based on the extraction of characteristics then the classification, the computational reduction is a factor of five. Subsequently, we have shown that we can combine the SVM network with feature maps from convolutional neural networks.

Authors and Affiliations

Dora Racheed Rahmatullah Muin Ahmed Jaylan

Keywords

Related Articles

New Approach Securing the Internet of Things

IOT connected objects are new technologies used to connect objects to the internet and to users. The IOT influences our daily life in several fields such as logistics, health, energy, intelligent vehicles, the smart home...

Development of a franchise and rating in the formation of programs for the development of higher project education

The subject of the article is the development of franchises and ratings as information technologies used in the development of higher project education; the object of the article is higher project education in the condit...

Sport and Physical Education at Abdelmalek Essaâdi University: State of the Art

This research deals with the issue of Physical Education (PE) and Sport at Abdelmalek Essaâdi University, Tetouan, Morrocco. It adopts a problem related to the diagnosis and development of the Physical Education/sport sy...

Effect of service quality on student-inspector satisfaction at the training center for educational inspectors in Rabat, Morocco

In theory, we all know that if students are satisfied, then training centers do provide a better quality of service. But what about in practice? The purpose of this research is twofold. On the one hand, we aim to assess...

A simple formalism Artificial intelligence-based to represent knowledge in a multi-agent planning context

At the start of the simulation, the agent knows nothing about how the dynamics of interaction with the environment unfold, or what causes his sensations. He does not distinguish obstacles from free paths, and he does not...

Download PDF file
  • EP ID EP694266
  • DOI https://doi.org/10.52502/ijitas.v2i3.12
  • Views 180
  • Downloads 0

How To Cite

Dora Racheed Rahmatullah Muin Ahmed Jaylan (2020). Object detection and object classification using machine learning Algorithms. International Journal of Information Technology and Applied Sciences (IJITAS), 2(3), -. https://europub.co.uk./articles/-A-694266