Researching of the deep neural network for amber gemstone classification
This project is based on the researching of the deep neural network for the classification of amber gemstone seen as a great opportunity to expand the range of application of the well known deep learning, which have been used more and more in different fields. First, it is explained the theoretical...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2018 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/171087 |
| Acceso en línea: | https://hdl.handle.net/2117/171087 |
| Access Level: | acceso abierto |
| Palabra clave: | Soft computing Informàtica tova Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica |
| Sumario: | This project is based on the researching of the deep neural network for the classification of amber gemstone seen as a great opportunity to expand the range of application of the well known deep learning, which have been used more and more in different fields. First, it is explained the theoretical concepts about machine learning and deep learning, besides a little comparison between them in order to for the reader to make the thesis more understandable. It is also introduced the different machine learning classifiers and the different methods of deep learning which have been used during the presented work. After having the basic concepts it will be explained the different methods that have been studied throughout the thesis to find the best possible accuracy in the training, validation and testing of the data set. Finally, it will be showcased the different results obtained followed by a short explanation per each of them. In this work the main technique that will be used for the researching is the method of transfer learning. Due to the lack of huge amounts of database regarding the amber stones, this technique can be a lot profitable to achieve the best accuracy. Nevertheless other methods like training from scratch will be tested; in which it will be used YOLO (You Only Looks Once). There is plenty of developed architectures that can be used for transfer learning, but only AlexNet will be used, since is one of the most used. The main tool for performing all the training and testing is MATLAB, which is quite suitable for processing images and with the latest version now it is able to run deep neural network with ease. |
|---|