A Compact Convolutional Neural Network for Textured Surface Anomaly Detection

  title={A Compact Convolutional Neural Network for Textured Surface Anomaly Detection},
  author={Domen Ra{\vc}ki and Dejan Tomazevic and Danijel Sko{\vc}aj},
  journal={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. [] Key Result The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.

Figures and Tables from this paper

An Attention-Based Network for Textured Surface Anomaly Detection

This work proposes a novel two-stage approach with an attention mechanism for textured surface anomaly detection that can achieve 100% detection rates in terms of TPR (True Positive Rate) and TNR (True Negative Rate).

A new multiscale texture surface defect detection method based on convolutional neural network

The proposed approach of texture surface defect detection based on convolution neural network (CNN) and wavelet analysis is proposed, which can detect and locate many kinds of defects in complex texture background, especially tiny defects in large-scale images.

A Compact Convolutional Neural Network for Surface Defect Inspection

A compact CNN-based model that not only achieves high performance on tiny defect inspection but can be run on low-frequency CPUs (central processing units) and can be compact and hardware-friendly for future applications in the automated surface inspection (ASI).

Anomaly Detection in Textured Surfaces

AnoNet is a novel and compact fully convolutional network architecture capable of learning to detect the actual shape of anomalies not only from weakly labelled data but also from a limited number of examples, which generalises to similar anomaly detection tasks.

Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks

A deep residual-based triplet network model is utilized, and defective training samples are synthesized exclusively from non-defective samples via random erasing techniques to directly learn a similarity metric between the same-class samples and out-of- class samples.

AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces

This work tackles the problem of teaching a network with a low number of training samples with a system called AnoNet, which learns to detect the underlying shape of the anomalies despite the weak annotation as well as preserves the spatial localization of the anomaly.

PM-AE: Pyramid Memory Autoencoder for Unsupervised Textured Surface Defect Detection

Experimental results demonstrated not only the superiority on efficiency and accuracy, but also the great potential in industrial applications of an efficient pyramid memory autoencoder.

Segmentation-based deep-learning approach for surface-defect detection

A segmentation-based deep-learning architecture that is designed for the detection and segmentation of surface anomalies and is demonstrated on a specific domain of surface-crack detection.

Segmentation-based deep-learning approach for surface-defect detection

A segmentation-based deep-learning architecture that is designed for the detection and segmentation of surface anomalies and is demonstrated on a specific domain of surface-crack detection.

Reliable and Robust Weakly Supervised Attention Networks for Surface Defect Detection

A weakly supervised attention network designed for surface defect detection that can simultaneously predict both the location and probability of defects only by using image-level labels is proposed.

Deep convolutional neural networks for detection of rail surface defects

This paper proposes a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects, and compares the results of different network architectures characterized by different sizes and activation functions.

Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo Images

This work trained CNNs on a database of photometric stereo images of metal surface defects, i.e. rail defects, and explored the impact of regularization methods such as unsupervised layer-wise pre-training and training data-set augmentation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

Steel defect classification with Max-Pooling Convolutional Neural Networks

Not only does the proposed Max-Pooling Convolutional Neural Network approach obtain much better results, but the proposed method also works directly on raw pixel intensities of detected and segmented steel defects, avoiding further time consuming and hard to optimize ad-hoc preprocessing.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Automatic visual inspection: An approach with multi-instance learning

A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques

In this paper, we systematically review recent advances in surface inspection using computer vision and image processing techniques, particularly those based on texture analysis methods. The aim is