Granite classification using machine learning and edge computing

Abstract

Background: The outlook and the aura of any place are highly dependent on how a place is decorated and what materials are used in designing it. Granite is such a kind of rock which is vastly used for this purpose. Granite flooring and counters have a major influence on the interior d ́ecor which is essential to set the mood and ambience of a house. A system is needed to help the end users differentiate between granites, which enhance the grandeur of their house and also check the frauds of different color granite being sent by the merchant as compared to what was selected by the end user. Several models have been developed for this cause using CNN and other image processing techniques. However, a solution for this purpose must be precise and computationally efficient. Methods: For this purpose,researchers in this work developed a machine learning based granite classifier using Edge Computing and a website to help users in choosing which granite would go well with their d ́ecor is also built. The developed system consists of a color sensor [TCS3200] integrated with an ESP8266 board. The data pertaining to RGB contrasts of different rocks is acquired by using the color sensor from a dealership.This data is used to train a Machine Learning algorithm to classify the rock into different granite types from a granite dealer and yield the category prediction. Results: The proposed system yields a result of 94% accuracy when classified using Random Forest Algorithm. Conclusion: Thus, this system provides an upper hand for the end users in differentiating between different types of granites.

Investigating Artificial Intelligence and Modern Technologies Enhancement in Stone and Marble Cutting in Palestine

“…The technique combines various visual recognition tools including Gobar feature, Grey-level Co-occurrence Matrices, and human visual color features. In addition, it uses non-overlapping images for the training samples.Karanam et al 2022 [11] developed granite classification process based on edge computing and machine learning, such that end users could distinguish different type of granites for their decoration purposes. Different machine learning algorithms were examined, they found that Random Forest classifier yields best accuracy followed by Support Vector Machine SVM then K-Nearest Neighbor KNN classifier.Employing deep learning models such as KNN and DenseNet Murat et al 2023 [12] built on Matlab environment; they were able to classify marbles with efficiency of 99.7%.…”