Anomaly detection plays a major role in hyper-spectral remote sensing target detection algorithms. The power of anomaly detection in these algorithms is its independence from prior knowledge about the target’s spectrum and the insensitivity to atmospheric corrections on the hyper-spectral image. This article describes a simulation for anomaly targets in hyper-spectral images. The simulation is based on mathematical concepts of statistical anomaly detection algorithms that model the background and discriminate anomalies from background pixels in the hyper-spectral images. With this simulation, anomaly detection algorithms can be tested and redeveloped to cope with anomaly targets of different strengths in order to improve their performance.
Glaucoma is a chronic and progressive optic neurodegenerative disease leading to vision deterioration. The visual loss caused by glaucoma is irreversible and hence early detection of the disease is essential. A novel glaucoma detection system using digital fundus images is proposed based on hybrid features using a combination of fractal and textural features. Fractal features, namely fractal dimension (FD), lacunarity and correlation coefficient (CC), are used with second-order textural features for the effective detection of glaucoma. The feature set is then optimized by the sequential floating forward selection (SFFS) technique and the extracted features are fed as input to an adaptive neurofuzzy inference system (ANFIS) for classification of images as normal or abnormal. The proposed hybrid features achieved 96.8% specificity and 98% sensitivity with an accuracy of 97.45% and can be used in glaucoma mass screening.
State of the art graph-based 3D simultaneous localization and mapping (SLAM) systems are typically divided into the so-called front- and back end. The front end’s task is to align laser scans locally, constructing a graph of the measurements in the process. The back end’s task is to optimize this graph in order to find a maximally consistent configuration of the nodes. The well-known iterative closest point (ICP) algorithm is often used to align pairs of laser scans. As it only provides local convergence, it generally requires an approximate guess in order to determine the correct relative transformation. In practice, this guess is often obtained from a robot’s odometry. However, in some applications this odometry information is not available and a fast initial guess is needed for real-time operation. Existing feature-based approaches are often unsuitable for real-time operation due to their computational requirements. The authors present a featureless algorithm that is able to compute an approximate transformation between two laser scans quickly, serving as initial guess for ICP. This algorithm is an adaptation to 3D of a 2D correlative scan-matching algorithm by Olson and will be evaluated in the context of 3D SLAM. Comparisons are made to results that use features as they are used in image processing to match images. The authors make some plausible and moderate assumptions on the scan acquisition and experimentally show that these are usually met. The experiments show that the presented algorithm is able to align two 3D laser scans quickly and reliably in the context of mobile robotics and stand-alone laser scanning.
Many research and engineering disciplines require a priori knowledge of the spectral properties of materials. The spectral transmittance and reflectance of these materials are not readily available and require expensive equipment to perform the measurements. To complicate matters further many materials are composed of multiple layers, and are made up of a combination of different materials. It can be very beneficial to be able to predict the spectral transmittance and reflectance of these different combinations without having to repeat the measurements.
An analytical model was developed for calculating the spectral reflectance and transmittance of a given multi-layer material based on the data of a single layer of the material. This model and its simple and fast implementation were validated using commercial simulation software, and by comparison with experimental results. Good agreement was found between the predicted and the measured values.
This article aims to define attributes of image quality that affect the quality of textured UV varnish applied as a pattern effect over offset prints. The most common UV varnishing problems that might influence attributes of print quality are reticulation of the varnish, poor adhesion, spreading of the varnish and shade changes. These problems mostly arise from inability to control the coating, especially if applied on differently generated print surfaces. Benefits of UV coatings in terms of image quality improvements might be greater opacity, color stability, deeper and more vibrant colors, sharper graphics, higher gloss and uniform surface to give labels a more vibrant look. Image quality variation assessment often needs to be carried out since an improvement made to one attribute can result in a deficiency to another attribute or attributes. In order to determine correlations between these attributes, a combination of objective and subjective image quality assessments has been applied.
A visible watermark conveys ownership information, used to identify the originator of an image. The watermark image is preprocessed and visibly embedded with an original image, before posting on the web for free observation and download. Based on the request of the buyer, the watermark can be removed to restore the unmarked image. A user-key-dependent frequency domain removable visible watermark embedding system (RVWES) is proposed. The user key structure decides both the embedded subset of the watermark and the host information adopted for adaptive embedding. With the correct user key, watermark removal can be carried out for information detection, and the high quality unmarked image can be restored. The proposed approach is mainly designed for the watermarking of digital camera images of various sizes. Pipeline and parallelism mechanisms are used to improve the throughput in the RVWES. The hardware implementation algorithm is tested in a Xilinx Virtex V XC5VlX330 technology based field programmable gate array, with which the throughput achieved is 4.3 Gbit/s with a total area utilization of 17448 BELs. To improve the robustness, a chaotic map is used to shuffle the watermark. The experimental results show that the watermarked image quality is good. Furthermore, the proposed approach is able to resist against a variety of general image processing attacks.