Refine
Document Type
- Conference Proceeding (8)
- Article (1)
- Doctoral Thesis (1)
Language
- English (10)
Keywords
- ADAM (1)
- Damage Detection (1)
- Deep learning (1)
- Defect detection (1)
- Dynamic cluster analysis (1)
- Dynamic time warping (1)
- ECG holter (1)
- ICA (1)
- Image novelty detection (2)
- Independent component analysis (1)
Institute
The detection of anomalous or novel images given a training dataset of only clean reference data (inliers) is an important task in computer vision. We propose a new shallow approach that represents both inlier and outlier images as ensembles of patches, which allows us to effectively detect novelties as mean shifts between reference data and outliers with the Hotelling T2 test. Since mean-shift can only be detected when the outlier ensemble is sufficiently separate from the typical set of the inlier distribution, this typical set acts as a blind spot for novelty detection. We therefore minimize its estimated size as our selection rule for critical hyperparameters, such as, e.g., the size of the patches is crucial. To showcase the capabilities of our approach, we compare results with classical and deep learning methods on the popular datasets MNIST and CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario.
Image novelty detection is a repeating task in computer vision and describes the detection of anomalous images based on a training dataset consisting solely of normal reference data. It has been found that, in particular, neural networks are well-suited for the task. Our approach first transforms the training and test images into ensembles of patches, which enables the assessment of mean-shifts between normal data and outliers. As mean-shifts are only detectable when the outlier ensemble and inlier distribution are spatially separate from each other, a rich feature space, such as a pre-trained neural network, needs to be chosen to represent the extracted patches. For mean-shift estimation, the Hotelling T2 test is used. The size of the patches turned out to be a crucial hyperparameter that needs additional domain knowledge about the spatial size of the expected anomalies (local vs. global). This also affects model selection and the chosen feature space, as commonly used Convolutional Neural Networks or Vision Image Transformers have very different receptive field sizes. To showcase the state-of-the-art capabilities of our approach, we compare results with classical and deep learning methods on the popular dataset CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario using the MVTec dataset. Because of the inexpensive design, our method can be implemented by a single additional 2D-convolution and pooling layer and allows particularly fast prediction times while being very data-efficient.
We are interested in computing a mini-batch-capable end-to-end algorithm to identify statistically independent components (ICA) in large scale and high-dimensional datasets. Current algorithms typically rely on pre-whitened data and do not integrate the two procedures of whitening and ICA estimation. Our online approach estimates a whitening and a rotation matrix with stochastic gradient descent on centered or uncentered data. We show that this can be done efficiently by combining Batch Karhunen-Löwe-Transformation [1] with Lie group techniques. Our algorithm is recursion-free and can be organized as feed-forward neural network which makes the use of GPU acceleration straight-forward. Because of the very fast convergence of Batch KLT, the gradient descent in the Lie group of orthogonal matrices stabilizes quickly. The optimization is further enhanced by integrating ADAM [2], an improved stochastic gradient descent (SGD) technique from the field of deep learning. We test the scaling capabilities by computing the independent components of the well-known ImageNet challenge (144 GB). Due to its robustness with respect to batch and step size, our approach can be used as a drop-in replacement for standard ICA algorithms where memory is a limiting factor.
Optical surface inspection: A novelty detection approach based on CNN-encoded texture features
(2018)
In inspection systems for textured surfaces, a reference texture is typically known before novel examples are inspected. Mostly, the reference is only available in a digital format. As a consequence, there is no dataset of defective examples available that could be used to train a classifier. We propose a texture model approach to novelty detection. The texture model uses features encoded by a convolutional neural network (CNN) trained on natural image data. The CNN activations represent the specific characteristics of the digital reference texture which are learned by a one-class classifier. We evaluate our novelty detector in a digital print inspection scenario. The inspection unit is based on a camera array and a flashing light illumination which allows for inline capturing of multichannel images at a high rate. In order to compare our results to manual inspection, we integrated our inspection unit into an industrial single-pass printing system.
Targetless Lidar-camera registration is a repeating task in many computer vision and robotics applications and requires computing the extrinsic pose of a point cloud with respect to a camera or vice-versa. Existing methods based on learning or optimization lack either generalization capabilities or accuracy. Here, we propose a combination of pre-training and optimization using a neural network-based mutual information estimation technique (MINE [1]). This construction allows back-propagating the gradient to the calibration parameters and enables stochastic gradient descent. To ensure orthogonality constraints with respect to the rotation matrix we incorporate Lie-group techniques. Furthermore, instead of optimizing on entire images, we operate on local patches that are extracted from the temporally synchronized projected Lidar points and camera frames. Our experiments show that this technique not only improves over existing techniques in terms of accuracy, but also shows considerable generalization capabilities towards new Lidar-camera configurations.
Incremental one-class learning using regularized null-space training for industrial defect detection
(2024)
One-class incremental learning is a special case of class-incremental learning, where only a single novel class is incrementally added to an existing classifier instead of multiple classes. This case is relevant in industrial defect detection scenarios, where novel defects usually appear during operation. Existing rolled-out classifiers must be updated incrementally in this scenario with only a few novel examples. In addition, it is often required that the base classifier must not be altered due to approval and warranty restrictions. While simple finetuning often gives the best performance across old and new classes, it comes with the drawback of potentially losing performance on the base classes (catastrophic forgetting [1]). Simple prototype approaches [2] work without changing existing weights and perform very well when the classes are well separated but fail dramatically when not. In theory, null-space training (NSCL) [3] should retain the basis classifier entirely, as parameter updates are restricted to the null space of the network with respect to existing classes. However, as we show, this technique promotes overfitting in the case of one-class incremental learning. In our experiments, we found that unconstrained weight growth in null space is the underlying issue, leading us to propose a regularization term (R-NSCL) that penalizes the magnitude of amplification. The regularization term is added to the standard classification loss and stabilizes null-space training in the one-class scenario by counteracting overfitting. We test the method’s capabilities on two industrial datasets, namely AITEX and MVTec, and compare the performance to state-of-the-art algorithms for class-incremental learning.
The proposed approach applies current unsupervised clustering approaches in a different dynamic manner. Instead of taking all the data as input and finding clusters among them, the given approach clusters Holter ECG data (long-term electrocardiography data from a holter monitor) on a given interval which enables a dynamic clustering approach (DCA). Therefore advanced clustering techniques based on the well known Dynamic Time Warping algorithm are used. Having clusters e.g. on a daily basis, clusters can be compared by defining cluster shape properties. Doing this gives a measure for variation in unsupervised cluster shapes and may reveal unknown changes in healthiness. Embedding this approach into wearable devices offers advantages over the current techniques. On the one hand users get feedback if their ECG data characteristic changes unforeseeable over time which makes early detection possible. On the other hand cluster properties like biggest or smallest cluster may help a doctor in making diagnoses or observing several patients. Further, on found clusters known processing techniques like stress detection or arrhythmia classification may be applied.
Present demographic change and a growing population of elderly people leads to new medical needs. Meeting these with state of the art technology is as a consequence a rapidly growing market. So this work is aimed at taking modern concepts of mobile and sensor technology and putting them in a medical context. By measuring a user’s vital signs on sensors which are processed on a Android smartphone, the target system is able to determine the current health state of the user and to visualize gathered information. The system also includes a weather forecasting functionality, which alerts the user on possibly dangerous future meteorological events. All information are collected centrally and distributed to users based on their location. Further, the system can correlate the client-side measurement of vital signs with a server-side weather history. This enables personalized forecasting for each user individually. Finally, a portable and affordable application was developed that continuously monitors the health status by many vital sensors, all united on a common smartphone.
The ageing infrastructure in ports requires regular inspection. This inspection is currently carried out manually by divers who sense by hand the entire underwater infrastructure. This process is cost-intensive as it involves a lot of time and human resources. To overcome these difficulties, we propose to scan the above and underwater port structure with a Multi-SensorSystem, and -by a fully automated processto classify the obtained point cloud into damaged and undamaged zones. We make use of simulated training data to test our approach since not enough training data with corresponding class labels are available yet. To that aim, we build a rasterised heightfield of a point cloud of a sheet pile wall by cutting it into verticall slices. The distance from each slice to the corresponding line generates the heightfield. This latter is propagated through a convolutional neural network which detects anomalies. We use the VGG19 Deep Neural Network model pretrained on natural images. This neural network has 19 layers and it is often used for image recognition tasks. We showed that our approach can achieve a fully automated, reproducible, quality-controlled damage detection which is able to analyse the whole structure instead of the sample wise manual method with divers. The mean true positive rate is 0.98 which means that we detected 98 % of the damages in the simulated environment.
Particularly for manufactured products subject to aesthetic evaluation, the industrial manufacturing process must be monitored, and visual defects detected. For this purpose, more and more computer vision-integrated inspection systems are being used. In optical inspection based on cameras or range scanners, only a few examples are typically known before novel examples are inspected. Consequently, no large data set of non-defective and defective examples could be used to train a classifier, and methods that work with limited or weak supervision must be applied. For such scenarios, I propose new data-efficient machine learning approaches based on one-class learning that reduce the need for supervision in industrial computer vision tasks. The developed novelty detection model automatically extracts features from the input images and is trained only on available non-defective reference data. On top of the feature extractor, a one-class classifier based on recent developments in deep learning is placed. I evaluate the novelty detector in an industrial inspection scenario and state-of-the-art benchmarks from the machine learning community. In the second part of this work, the model gets improved by using a small number of novel defective examples, and hence, another source of supervision gets incorporated. The targeted real-world inspection unit is based on a camera array and a flashing light illumination, allowing inline capturing of multichannel images at a high rate. Optionally, the integration of range data, such as laser or Lidar signals, is possible by using the developed targetless data fusion method.
