Holograms are security features applied to security documents like banknotes, passports, and ID cards in order to protect them from counterfeiting. Checking the authenticity of holograms is an important but difficult task, as holograms comprise different appearances for varying observation and/or illumination directions. Multi-view and photometric image acquisition and analysis procedures have been proposed to capture that variable appearance. We have developed a portable ring-light illumination module used to acquire photometric image stacks of holograms with mobile devices. By the application of Convolutional Neural Networks (CNN), we developed a vector representation that captures the essential appearance properties of hologram types in only a few values extracted from the photometric hologram stack. We present results based on Euro banknote holograms of genuine and counterfeited Euro banknotes. When compared to a model-based hologram descriptor, we show that our new learned CNN representation enables hologram authentication on the basis of our mobile acquisition method more reliably.
We investigated optimal implementation strategies for industrial inspection systems aiming to detect cracks on ground steel billets’ surfaces by combining state-of-the-art AI-based methods and classical computational imaging techniques. In 2D texture images, the interesting patterns of surface irregularities are often surrounded by visual clutter, which is to be ignored, e.g., grinding patterns. Even neural networks struggle to reliably distinguish between actual surface disruptions and irrelevant background patterns. Consequently, the image acquisition procedure already has to be optimised to the specific application. In our case, we use photometric stereo (PS) imaging to generate 3D surface models of steel billets using multiple illumination units. However, we demonstrate that the neural networks, especially in high-speed scenarios, still suffer from recognition deficiencies when using raw photometric stereo camera data, and are unable to generalise to new billets and image acquisition conditions. Only the additional application of adequate state-of-the-art image processing algorithms guarantees the best results in both aspects. The neural networks benefit when appropriate image acquisition methods together with image processing algorithms emphasise relevant surface structures and reduce overall pattern variation. Our proposed combined strategy shows a 9.25% better detection rate on validation data and is 14.7% better on test data, displaying the best generalisation.
6 November 2015 in Lecture Notes in Computer Science
The transformation of industrial environments is progressing at a fast pace as more and more autonomous systems are installed and operated. Save and explainable AI algorithms are thus essential, especially for collaborative interactive systems that operate in human spaces. We propose the “Semantic Encoder”, a 2D-vision based CNN model trained on a purely synthetic dataset, to address the explainability aspect by extracting semantic descriptions of real objects based on their visual appearances. We can use the extracted semantic information to simply describe depicted samples or to differentiate between normal and anomalous samples, with the possibility to explain what caused the anomaly detection. The semantic description can be further used to sort samples by classifying them or to find a sample with specific semantic properties. We evaluate the Semantic Encoder with respect to its informative power by comparing the computed semantic features with features extracted by a VGG-16 model and classical image processing methods. The results are quantified based on the Generalized Discriminative Value (GDV). We also investigate how accurately anomalous samples are detected by computing ROC and PR curves. We use the semantic parameters to understand what causes good and inaccurate anomaly detection decisions. In addition, we evaluate the quality of the classification based sorting by examining confusion matrices and classification accuracy.
For calculating 3D information with stereo matching, usually correspondence analysis yields a so-called depth hypotheses cost stack, which contains information about similarities of the visible...
21 July 2026 in European Journal of Wood and Wood Products
Manual grading of round timber is time-consuming and inconsistent, while many automated systems still output opaque quality labels that are difficult to verify against European standards. We present and validate a standards-aligned semantic segmentation dataset of spruce ( Picea abies ) logs designed to support transparent, rule-based grading. Using close-range photogrammetry, we recorded 1,875 logs and rendered three orthorectified images per log (two end faces, one mantle), yielding 5,625 images. Fourteen grading-relevant features, defined from EN 844 terminology and EN 1309-3 measurement rules, were annotated by multiple certified graders in a consensus workflow that produces per-pixel confidence. The dataset comprises 17,584 masks with 96,964 connected components and a mean area-weighted pixel-confidence of 91.4%. Reliability (test–retest and split-half), train–test similarity, and distributional realism were quantified from masks alone. Object counts are well described by zero-truncated Conway–Maxwell–Poisson laws, linear sizes by shifted log-normal distributions and shape as well as fractional-area measures by skew exponential power models. Median Kolmogorov–Smirnov and normalized Earth Mover’s Distance values indicate temporal stability and only modest train–test drift. Because mask geometry follows EN 1309-3 clauses, segmentation outputs map directly to EN 1927-1 decision expressions, enabling transparent acceptance checks. The dataset and analyses support explainable, standards-aligned automation of round timber grading and provide a reproducible basis for benchmarking semantic segmentation models in wood quality inspection.