Fabian Timm

Non-parametric texture defect detection using Weibull features

The detection of abnormalities is a very challenging problem in computer vision, especially if these abnormalities must be detected in images of textured surfaces such as textile, stone, or wood. We propose a novel, non-parametric approach for defect detection in textures that only employs two features. We compute the two parameters of a Weibull fit for the distribution of image gradients in local regions. Then, we perform a simple novelty detection algorithm in order to detect arbitrary deviations of the reference texture. Therefore, we evaluate the Euclidean distances of all local patches to a reference point in the Weibull space, where the reference point is determined for each texture image individually. Thus, our approach becomes independent of the particular texture type and also independent of a certain defect type. For performance evaluation we use the highly challenging database provided by Bosch for a contest on industrial optical inspection with different classes of textures and different defect types. By using the Weibull parameters we can detect local deviations of texture images in an unsupervised manner with high accuracy. Compared to existing approaches such as Gabor filters or grey level statistics, our approach is not only powerful, but also very efficient such that it can also be applied for real-time applications.

Statistical Fourier Descriptors for Defect Image Classification

In many industrial applications, Fourier descriptors are commonly used when the description of the object shape is an important characteristic of the image. However, these descriptors are limited to single objects. We propose a general Fourier-based approach, called statistical Fourier descriptor (SFD), which computes shape statistics in grey level images. The SFD is computationally efficient and can be used for defect image classification. In a first example, we deployed the SFD to the inspection of welding seams with promising results.

Novelty detection for the inspection of light-emitting diodes

We propose novel feature-extraction and classification methods for the automatic visual inspection of manufactured LEDs. The defects are located at the area of the p-electrodes and lead to a malfunction of the LED. Besides the complexity of the defects, low contrast and strong image noise make this problem very challenging.For the extraction of image characteristic we compute radially-encoded features that measure discontinuities along the p-electrode. Therefore, we propose two different methods: the first method divides the object into several radial segments for which mean and standard deviation are computed and the second method computes mean and standard deviation along different orientations. For both methods we combine the features over several segments or orientations by computing simple measures such as the ratio between maximum and mean or standard deviation.Since defect-free LEDs are frequent and defective LEDs are rare, we apply and evaluate different novelty-detection methods for classification. Therefore, we use a kernel density estimator, kernel principal component analysis, and a one-class support vector machine. We further compare our results to Pearsons correlation coefficient, which is evaluated using an artificial reference image.The combination of one-class support vector machine and radially-encoded segment features yields the best overall performance by far, with a false alarm rate of only 0.13% at a 100% defect detection rate, which means that every defect is detected and only very few defect-free p-electrodes are rejected.Our inspection system does not only show superior performance, but is also computationally efficient and can therefore be applied to further real-time applications, for example solder joint inspection. Moreover, we believe that novelty detection as used here can be applied to various expert-system applications.

Simple Incremental One-Class Support Vector Classification

We introduce the OneClassMaxMinOver (OMMO) algorithm for the problem of one-class support vector classification. The algorithm is extremely simple and therefore a convenient choice for practitioners. We prove that in the hard-margin case the algorithm converges with

Fast model selection for MaxMinOver-based training of support vector machines

\mathcal{O} (1/\sqrt{t})

Optical Inspection of Welding Seams

to the maximum margin solution of the support vector approach for one-class classification introduced by Scholkopf et al. Furthermore, we propose a 2-norm soft margin generalisation of the algorithm and apply the algorithm to artificial datasets and to the real world problem of face detection in images. We obtain the same performance as sophisticated SVM software such as libSVM.

Accurate, fast, and robust centre localisation for images of semiconductor components

OneClassMaxMinOver (OMMO) is a simple incremental algorithm for one-class support vector classification. We propose several enhancements and heuristics for improving model selection, including the adaptation of well-known techniques such as kernel caching and the evaluation of the feasibility gap. Furthermore, we provide a framework for optimising grid search based model selection that compromises of preinitialisation, cache reuse, and optimal path selection. Finally, we derive simple heuristics for choosing the optimal grid search path based on common benchmark datasets. In total, the proposed modifications improve the runtime of model selection significantly while they are still simple and adaptable to a wide range of incremental support vector algorithms.

Accurate Eye Centre Localisation by Means of Gradients.

We present a framework for automatic inspection of welding seams based on specular reflections. To this end, we make use of a feature set – called specularity features (SPECs) – that describes statistical properties of specular reflections. For the classification we use a one-class support-vector approach. We show that the SPECs significantly outperform other approaches since they capture more complex characteristics and dependencies of shape and geometry. We obtain an error rate of 3.8%, which corresponds to the level of human performance.

WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM

The problem of circular object detection and localisation arises quite often in machine vision applications, for example in semi-conductor component inspection. We propose two novel approaches for the precise centre localisation of circular objects, e.g. p-electrodes of light-emitting diodes. The first approach is based on image gradients, for which we provide an objective function that is solely based on dot products and can be maximised by gradient ascend. The second approach is inspired by the concept of isophotes, for which we derive an objective function that is based on the definition of radial symmetry. We evaluate our algorithms on synthetic images with several kinds of noise and on images of semiconductor components and we show that they perform better and are faster than state of the art approaches such as the Hough transform. The radial symmetry approach proved to be the most robust one, especially for low contrast images and strong noise with a mean error of 0.86 pixel for synthetic images and 0.98 pixel for real world images. The gradient approach yields more accurate results for almost all images (mean error of 4 pixel) compared to the Hough transform (8 pixel). Concerning runtime, the gradient-based approach significantly outperforms the other approaches being 5 times faster than the Hough transform; the radial symmetry approach is 12% faster.