Klaus Spinnler

Class of algorithms for real-time subpixel registration

In 1972, Barnea and Silverman presented a new approach to the wide field of template matching, the SSD-algorithm. Further work has been done to adapt the method to gain subpixel accuracy. Intense investigation of the proposed algorithms led to our new approach: by interpolating the template instead of the reference image, and by applying sort of an error- correction to the resulting subpixel-value, both computation time and accuracy can be improved. Exhaustive experiments with a CCD-camera and various kinds of reference images showed that a maximum error of 10% of the pixel period can be expected. Depending on the kind of image, mean square errors range from 0.4% to 4%.

A new type of color-coded light structures for an adapted and rapid determination of point correspondences for 3D reconstruction

This paper proposes a new type of color coded light structures for the inspection of complex moving objects. The novelty of the methods relies on the generation of free-form color patterns permitting the projection of color structures adapted to the geometry of the surfaces to be characterized. The point correspondence determination algorithm consists of a stepwise procedure involving simple and computationally fast methods. The algorithm is therefore robust against varying recording conditions typically arising in real-time quality control environments and can be further integrated for industrial inspection purposes. The proposed approach is validated and compared on the basis of different experimentations concerning the 3D surface reconstruction by projecting adapted spatial color coded patterns. It is demonstrated that in case of certain inspection requirements, the method permits to code more reference points that similar color coded matrix methods.

Multispectral Texture Analysis Using Interplane Sum- and Difference-Histograms

In this paper we present a new approach for color texture classification which extends the gray level sum- and difference histogram features [8]. Intra- and inter-plane second order features capture the spatial correlations between color bands. A powerful set of features is obtained by non-linear color space conversion to HSV and thresholding operation to eliminate the influence of sensor noise on color information. We present an evaluation of classification performance using four different image sets.

Specific features for the analysis of fringe images

In optical nondestructive testing, a novel solution is presented for fault detection based on the interpretation of fringe images. These images can be acquired using different optical methods, such as structured lighting or interferometry. We propose a set of eight special features adapted to the problem of surface inspection using structured illumination. These characteristics are combined with six further features specially developed for the classification of faults using interferometric images. We apply two kinds of decision rules: the Bayesian and the nearest neighbor classifiers. The proposed features are evaluated using a noisy and a noise-free image data set. All patterns were obtained by means of structured lighting. Concerning the noisy data set, we obtain better classification rates when all the 14 features are used in combination with a one-nearest-neighbor classifier. In case of a noise-free data set, we show that similar classification rates are obtained when the 14 features or only the 8 specific features are involved. The methods described are designed to address a broad range of optical nondestructive applications involving the interpretation and classification of fringe patterns.

A Distributed Vision Network for Industrial Packaging Inspection

A distributed vision network is proposed to tackle industrial packaging inspection. The system consists of independent networked inspection stations able to address efficiently parallel inspection tasks such as product identification, character verification, tag inspection and content & packaging quality control at a high production speed. Existing and innovative inspection algorithms such as synergetic classification have been adapted on the smart camera technology of the inspection stations. We present the benefits of the deployment of the system in the production lines of a pharmaceutical packaging facility.

Improvements on the Gray Level Co-occurrence Matrix Technique to Compute Ischemic Stroke Volume

The purpose of this work was to apply and test Haralick’s gray level co-occurrence matrix (GLCM) technique for automatic calculation and segmentation of the ischemic stroke volume from CT images. For this task, the 3-nearest neighbors classifier was trained to perform stroke and non-stroke area classification. The segmentation and classification results were compared versus a manual segmentation. Approximately half of the automatically computed and segmented stroke volumes from CT images differed less than 15 % from the corresponding manually segmented stroke volumes.

Multidimensional Signal Processing and Applications

In our daily lives and almost unconsciously, we deal with multidimensional data. From color images converted to the luminance and chrominance format to magnetic resonance images commonly acquired for health purposes, from different fashions to write an alphabet to array processing signals underlying any telecommunication system, we deal with multidimensional data. In this special issue, we tried to show the variety of the topics which are currently investigated with multidimensional signal processing tools. The mathematical tools presented in this issue are as diverse as adaptive detectors, wavelet processing, principal component analysis, and improved classical image processing tools such as histogram equalization. In the array processing paradigm, a two-dimensional matrix containing the data depends on the polarization properties of the sources, their number, and the number of sensors in the receiving antenna. Hence the interest of a multidimensional representation, including a polarization variable with two or three possible values, and a real and a complex part for the source amplitudes. In the image processing paradigm, data are as various as magnetic resonance or color images, whose representation can be transferred from the RGB (red green blue) format to other spaces emphasizing for instance the luminance or the chrominance. It is shown how magnetic resonance brain images are classified with support vector machine. To avoid problems related to high dimensionality, which is current in big data processing, adequate features are extracted from the data by discrete wavelet transform and principal component analysis. Color spaces, which are useful for skin detection, for instance, are also further investigated: whatever the representation space is, a color image is a third order tensor, in other words, a three-dimensional data. It is shown how to detect image splicing with the help of merged features in the chrominance space: the relationships between pixels in a neighborhood are studied with a Markov process and the extraction of DCT features from the chrominance channel. Then, with the help of new color spaces, it is shown how evolved versions of neural networks called extreme learning machines can fuse multiple information such as color and local spatial information from face images. The “multi” aspect can also appear in the image processing paradigm when multiple images are obtained from several parameters. In images provided by synthetic aperture radar exploited for flood detection, contrast enhancement is achieved by an adjustable histogram equalization technique. For such an application where the visual aspect of the results are much important much, a color image, that is, a multidimensional signal, can be built from several two-dimensional result images, to get an informative map, where the color informs on the nature of the imaged scene, flooded or not, for instance. Starting from images, a set of multidimensional data is extracted from Serbian texts: the Serbian alphabet, made of 30 letters, can be expressed in a Latin or in a Cyrillic fashion. All letters can be classified into four sets. By studying the frequencies of occurrence of each type of letter in a text, one can deduce that this text is written in the Latin or the Cyrillic fashion. In this application, matrices describing the cooccurrence in the distribution of the four types of letters are built out of any text, to make use of the classical texture features. Adapting the texture features to such a text recognition application, introducing a parameter which is the writing fashion, is a brand new idea. The “multi” aspect can also relate to multiresolution. Histogram of oriented gradients and hue descriptors can be merged to combine information related to the shape of an object and its color. By computing the merged data at several resolution levels, an innovative multidimensional descriptor is obtained. An application considered in this special issue is aircraft characterization and detection of images. In a nutshell, the “multi” representation attracts the interest of researchers from very diverse application fields. Hopefully, this special issue will contribute in diffusing the models and tools of multidimensional signal processing to various application fields. Salah Bourennane Julien Marot Caroline Fossati Ahmed Bouridane Klaus Spinnler

A Fast Logical-Morphological Method to Segment Scratch - Type Objects

In spite of the fast progress of computer technologies there are many tasks, which need accelerated software methods to obtain the results in real time. We propose one of such accelerated logical-morphological methods to detect scratch-type objects on noisy surfaces. The method is based on the principles of human vision and includes an adaptive multithresholding and logical-morphological operations for the fusion of the objects fragments.

Contour Detection for Industrial Image Processing by Means of Level Set Methods

We consider the problem of the automatic inspection of industrial metal pieces. The purpose of the work presented in this paper is to derive a method for defect detection. For the first time in this context we adapt level set method to distinguish hollow regions in the metal pieces from the grinded surface. We compare this method with Canny edge enhancement and with a thresholding method based on histogram computation. The experiments performed on two industrial images show that the proposed method retrieves correctly fuzzy contours and is robust against noise.

Segmentation and classification of anomalies in periodic structures

An alternative solution for surface inspection is being presented. It is based on a concerted combination of an adapted stripe-illumination principle together with an image processing approach specialized on the analysis of the obtained stripe images. This approach is capable of detecting, segmenting, and classifying nondefective surfaces, as well as three- and two-dimensional defective surfaces from perturbations in the stripe illumination. In contrast to alternative procedures, no calibration of illumination or camera is necessary. The principle of the proposed method using a concrete industrial application for the inspection of cylindrical metallic surfaces under structured lighting is explained. Furthermore, based on several examples involving different surface types, we demonstrate the broad range of applications for the proposed algorithm.