An Effective Turkey Marble Classification System: Convolutional Neural Network with Genetic Algorithm -Wavelet Kernel - Extreme Learning Machine

Abstract

Marble is one of the most popular decorative elements. Marble quality varies depending on its vein patterns and color, which are the two most important factors affecting marble quality and class. The manual classification of marbles is likely to lead to various mistakes due to different optical illusions. However, computer vision minimizes these mistakes thanks to artificial intelligence and machine learning. The present study proposes the Convolutional Neural Network- (CNN-) with genetic algorithm- (GA) Wavelet Kernel- (WK-) Extreme Learning Machine (ELM) (CNN–GA-WK-ELM) approach. Using CNN architectures such as AlexNet, VGG-19, SqueezeNet, and ResNet-50, the proposed approach obtained 4 different feature vectors from 10 different marble images. Later, Genetic Algorithm (GA) was used to optimize adjustable parameters, i.e. k, 1, and m, and hidden layer neuron number in Wavelet Kernel (WK) – Extreme Learning Machine (ELM) and to increase the performance of ELM. Finally, 4 different feature vector parameters were optimized and classified using the WK-ELM classifier. The proposed CNN–GA-WK-ELM yielded an accuracy rate of 98.20%, 96.40%, 96.20%, and 95.60% using AlexNet, SequeezeNet, VGG-19, and ResNet-50, respectively.

Computer vision application for improved product traceability in the granite manufacturing industry

“…The input parameters for all functions are (1) color name, (2) associated code number, (3) colored area (CA), (4) colored ratio (CR), (5) width/height ratio (WHR), ( 6) maximum vertical distance (MVD), (7) minimum Hue (Hmin), (8) minimum Saturation (Smin), (9) minimum Value (Vmin), (10) maximum Hue (Hmax), (11) maximum Saturation (Smax), and (12) maximum Value (Vmax). Parameters (1) and ( 2) are the decoded and encrypted names of each color respectively, the colored area (3) defines the minimum number of pixels that have to be turned on to be considered a true positive case of color detection, while the color ratio ( 4) is defined by the relation between the number of pixels colored with the target color and the total amount of pixels; it has the same goal as the colored area but implements a second layer of security to avoid false positives.…”

“…Parameters (1) and ( 2) are the decoded and encrypted names of each color respectively, the colored area (3) defines the minimum number of pixels that have to be turned on to be considered a true positive case of color detection, while the color ratio ( 4) is defined by the relation between the number of pixels colored with the target color and the total amount of pixels; it has the same goal as the colored area but implements a second layer of security to avoid false positives. The width/height ratio (5) analyzes the relation between the width and the height of the color areas detected. Given the fact that the color bands have rectangular shapes, this parameter aims to get rid of all detected areas which do not have the minimum width to height ratios, such as shades or color spots that do not belong to the color code system.…”

“…Its applications reach a broad range of fields and the potential benefit of its development can have a major impact in the upcoming years. Computer vision has found its applications in the mining sector, more specifically, in the slate industry for the detection of defects [18], [23] and [22], in the ceramic industry for the same purpose [26], [15], [33], [16] and [30], in the marble industry for pattern detection and classification [5] and [27] as well as in the granite industry for the characterization of granite varieties [4] and [21], but there has not been found any previous research on the applications of computer vision for color detection and analysis in order to improve product traceability in this sector.…”

An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

“…Wavelet Features: The wavelet transform method is used to extract the frequency domain features of the defect images. Wavelet transform is a feature extraction tool that divides data, functions, or operators into different frequency components and then examines each component with a resolution appropriate to its scale [18]. The wavelet transform uses narrower windows as window length at high frequencies, while wider windows are used at low frequencies.…”