SurfNetv2: An Improved Real-Time SurfNet and Its Applications to Defect Recognition of Calcium Silicate Boards

Abstract

This paper presents an improved Convolutional Neural Network (CNN) architecture to recognize surface defects of the Calcium Silicate Board (CSB) using visual image information based on a deep learning approach. The proposed CNN architecture is inspired by the existing SurfNet architecture and is named SurfNetv2, which comprises a feature extraction module and a surface defect recognition module. The output of the system is the recognized defect category on the surface of the CSB. In the collection of the training dataset, we manually captured the defect images presented on the surface of the CSB samples. Then, we divided these defect images into four categories, which are crash, dirty, uneven, and normal. In the training stage, the proposed SurfNetv2 is trained through an end-to-end supervised learning method, so that the CNN model learns how to recognize surface defects of the CSB only through the RGB image information. Experimental results show that the proposed SurfNetv2 outperforms five state-of-the-art methods and achieves a high recognition accuracy of 99.90% and 99.75% in our private CSB dataset and the public Northeastern University (NEU) dataset, respectively. Moreover, the proposed SurfNetv2 model achieves a real-time computing speed of about 199.38 fps when processing images with a resolution of 128 × 128 pixels. Therefore, the proposed CNN model has great potential for real-time automatic surface defect recognition applications.

A Weld Surface Defect Recognition Method Based on Improved MobileNetV2 Algorithm

“…(1) Surface defect detection When detecting surface defects of products in industrial applications, many scholars have proposed research methods based on deep CNN and achieved good experimental results. Tsai et al [19] proposed SurfNetv2 to recognize surface defects of the Calcium Silicate Board (CSB) using visual image information, experimental results show that the proposed SurfNetv2 outperforms five state-of-the-art methods. Wan et al [20] proposed a strip steel defect detection method that achieved surface rapid screening, sample dataset's category balance, defect detection, and classification.…”

Digital Forensics of Scanned QR Code Images for Printer Source Identification Using Bottleneck Residual Block

“…In recent years, deep learning has been widely used, and CNN has also made breakthroughs in image classification, image recognition and other issues [20][21][22][23][24][25][26]. As a new field of machine learning, deep learning uses the structure of a deep neural network with multiple convolution layers, which automatically learns the features of large-scale input data, and forms the bottom features into more abstract high-level features to represent the attribute categories or features of training data, and then represents the attribute categories or features of training data, so as to achieve higher recognition accuracy.…”