Department of Informatics, Modeling, Electronics and Systems Engineering (DIMES), University of Calabria, Via P. Bucci, 87036 Rende, Italy.
Department of Biology, Ecology and Earth Sciences (DiBEST), University of Calabria, Via P. Bucci, 87036 Rende, Italy.
Sensors (Basel). 2022 Aug 21;22(16):6292. doi: 10.3390/s22166292.
This paper presents an automatic recognition system for classifying stones belonging to different Calabrian quarries (Southern Italy). The tool for stone recognition has been developed in the SILPI project (acronym of ""), financed by POR Calabria FESR-FSE 2014-2020. Our study is based on the (CNNs) that is used in literature for many different tasks such as speech recognition, neural language processing, bioinformatics, image classification and much more. In particular, we propose a two-stage hybrid approach based on the use of a model of (DL), in our case the CNN, in the first stage and a model of (ML) in the second one. In this work, we discuss a possible solution to stones classification which uses a CNN for the feature extraction phase and the or (MLR), (SVM), (kNN), (RF) and (GNB) ML techniques in order to perform the classification phase basing our study on the approach called (TL). We show the image acquisition process in order to collect adequate information for creating an opportune database of the stone typologies present in the Calabrian quarries, also performing the identification of quarries in the considered region. Finally, we show a comparison of different DL and ML combinations in our Two-Stage Hybrid Model solution.
本文提出了一种用于对来自不同卡拉布里亚采石场（意大利南部）的石头进行分类的自动识别系统。石头识别工具是在 SILPI 项目（Southern Italy Limestone 项目的缩写）中开发的，该项目由 POR Calabria FESR-FSE 2014-2020 资助。我们的研究基于卷积神经网络（CNN），该网络在文献中被用于许多不同的任务，如语音识别、神经语言处理、生物信息学、图像分类等。特别是，我们提出了一种基于使用深度学习（DL）模型的两阶段混合方法，在我们的案例中是 CNN，在第一阶段和基于 （ML）的模型，在第二阶段。在这项工作中，我们讨论了一种可能的解决方案，该方案使用 CNN 进行特征提取阶段，并使用 （MLR）、 （SVM）、 （kNN）、 （RF）和 （GNB）机器学习技术进行分类阶段，我们的研究基于称为 （TL）的方法。我们展示了图像采集过程，以便为创建卡拉布里亚采石场中存在的石材类型的适当数据库收集足够的信息，同时对所考虑地区的采石场进行识别。最后，我们展示了在我们的两阶段混合模型解决方案中不同 DL 和 ML 组合的比较。
