Object detection and object classification using machine learning Algorithms
Journal Title: International Journal of Information Technology and Applied Sciences (IJITAS) - Year 2020, Vol 2, Issue 3
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
- EP ID EP694266
- DOI https://doi.org/10.52502/ijitas.v2i3.12
- Views 148
- Downloads 0
An algorithm to calculates an allocation maximizing the leximin order on the utility profiles of the agents
Allocating a limited set of resources equitably and efficiently to agents each with their own preferences is a general problem of considerable significance. Many examples of this problem are commonly found, among which w...
Assessment of the Quality of the Training System in Moroccan Higher Education Institutions: Case of the Sciences ans Techniques of Physical and Sports Activities
Purpose: The aim of our study is to assess the overall quality of the university training system in sciences and techniques of physical and sports activities in Moroccan higher education. Method: Our method was based on...
Object detection and object classification using machine learning Algorithms
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 o...
Machine Learning confronted with the operational constraints of detection systems
Intrusion detection systems, traditionally based on signatures, have not escaped the recent appeal of machine learning techniques. While the results presented in academic research articles are often excellent, security e...
Strategic Information Systems and Artificial Intelligence in Business
Information systems are defined as systems that consist of a group of people, data records, and some manual and non-manual operations. These systems generally handle data and information related to each system, and it ca...