Defect Detection in SEM Images of Nanofibrous Materials

Abstract

Nanoproducts represent a potential growing sector and nanofibrous materials are widely requested in industrial, medical, and environmental applications. Unfortunately, the production processes at the nanoscale are difficult to control and nanoproducts often exhibit localized defects that impair their functional properties. Therefore, defect detection is a particularly important feature in smart-manufacturing systems to raise alerts as soon as defects exceed a given tolerance level and to design production processes that both optimize the physical properties and control the defectiveness of the produced materials. Here, we present a novel solution to detect defects in nanofibrous materials by analyzing scanning electron microscope images. We employ an algorithm that learns, during a training phase, a model yielding sparse representations of the structures that characterize correctly produced nanofiborus materials. Defects are then detected by analyzing each patch of an input image and extracting features that quantitatively assess whether the patch conforms or not to the learned model. The proposed solution has been successfully validated over 45 images acquired from samples produced by a prototype electrospinning machine. The low computational times indicate that the proposed solution can be effectively adopted in a monitoring system for industrial productio

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

“…The results achieved with this method are the current stateof-the-art on the NanoTWICE dataset, which we also use in our experiments. They improve upon previous results by Carrera et al (2017), who build a dictionary that yields a sparse representation of the normal data. Similar approaches using sparse representations for novelty detection are (Boracchi et al, 2014;Carrera et al, 2015Carrera et al, , 2016.…”

“…Examples of defective and defect-free textures can be seen in Figure 4. We further evaluate our method on a dataset of nanofibrous materials (Carrera et al, 2017), which contains five defectfree gray-scale images of size 1024 × 700 for training and validation and 40 defective images for evaluation. A sample image of this dataset is shown in Figure 1…”

“…We evaluate the performance gains obtained by employing SSIM as a loss function on two real-world industrial inspection datasets and demonstrate significant performance gains over per-pixel approaches. Figure 1 demonstrates the advantage of perceptual loss functions over a per-pixel 2loss on the NanoTWICE dataset of nanofibrous materials (Carrera et al, 2017). While both autoencoders alter the reconstruction in defective regions, only the residual map of the SSIM autoencoder allows a segmentation of these areas.…”

Image Anomalies: A Review and Synthesis of Detection Methods

“…We singled out two of them as the most recent and powerful ones: the sparsity assumption and the self-similarity assumption. We found that two recent exponents use these assumptions to perform a sort of background subtraction: Carrera et al [21] for sparsity and Davy et al [33] for self-similarity.…”

Defect minimization and feature control in electrospinning through design of experiments

“…As for the defect ratio y 1 , the algorithm proposed in Ref. was adopted. Briefly, the algorithm employs the sparse‐approximation technique for representing an image by using a limited number of significant patches, which are collected during a training phase performed on a set of images with no defects.…”