This paper proposes a novel approach to real-time automatic rim detection, classification, and inspection by combining traditional computer vision and deep learning techniques. At the end of every automotive assembly line, a quality control process is carried out to identify any potential defects in the produced cars. Common yet hazardous defects are related, for example, to incorrectly mounted rims. Routine inspections are mostly conducted by human workers that are negatively affected by factors such as fatigue or distraction. We have designed a new prototype to validate whether all four wheels on a single car match in size and type. Additionally, we present three comprehensive open-source databases, CWD1500, WHEEL22, and RB600, for wheel, rim, and bolt detection, as well as rim classification, which are free-to-use for scientific purposes.

This paper addresses the monitoring of Varroa destructor infestation in Western honey bee colonies. We propose a simple approach using automatic image-based analysis of the fallout on beehive bottom boards. In contrast to the existing high-tech methods, our solution does not require extensive and expensive hardware components, just a standard smart-phone. The described method has the potential to replace the time-consuming, inaccurate, and most common practice where the infestation level is evaluated manually. The underlining machine learning method combines a thresholding algorithm with a shallow CNN—VarroaNet. It provides a reliable estimate of the infestation level with a mean infestation level accuracy of 96.0% and 93.8% in the autumn and winter, respectively. Furthermore, we introduce the developed end-to-end system and its deployment into the online beekeeper’s diary—ProBee—that allows users to identify and track infestation levels on bee colonies.

Deep learning-based methods for classification and segmentation require large training sets. Generating training data is often a tedious and expensive task. In industrial applications, such as automated visual inspection of products in an assemble line, objects for classification are well defined yet labeled data are difficult to obtain. To alleviate the problem of manual labeling, we propose to train a convolutional neural network with an automatically generated training set using a naive classifier with handcrafted features. We show that when the naive classifier has high precision then the trained network has both high precision and recall despite the low recall of the naive classifier. We demonstrate the proposed methodology on real scenario of detecting a car coolant tank. However, the proposed methodology facilitates collection of train data for a wider type of CNN based methods such as near-duplicate image detection or segmenting tampered areas of images.

In this paper, we propose a new theory of invariants to Gaussian blur. We introduce a notion of a primordial image as a canonical form of all Gaussian blur-equivalent images. The primordial image is defined in spectral domain by means of projection operators. We prove that the moments of the primordial image are invariant to Gaussian blur and we derive recursive formulas for their direct computation without actually constructing the primordial image itself. We show how to extend their invariance also to image rotation. The application of these invariants is in blur-invariant image comparison and recognition. In the experimental part, we perform an exhaustive comparison with two main competitors: 1) the Zhang distance and 2) the local phase quantization.

Given the large amount of blur estimation and blind deconvolution methods just in the last decade, there is an increasing need to compare the performance of a particular method with others. Unlike in other fields in image processing, there are very few well-established benchmark databases of test data and, more importantly, no standard way of performance evaluation. In this paper, we focus on the latter. We propose a new error measure for the blur kernel - a method for comparison of the blur estimate with the ground truth - which correctly reflects how inaccuracies in the blur estimation affect the subsequent image restoration, without the necessity to perform the actual deconvolution.

Videokymography (VKG) is a high-speed medical imaging technique used in laryngology and phoniatrics for examination of vocal fold vibrations, it offers important characteristics for diagnosis and treatment of voice disorders. VKG repeatedly scans only a single line from the scene and captures movements of vocal folds in this region of interest. This paper proposes methods for computer assisted evaluation of diagnostically important vibration features, related to movements of vocal folds and their surroundings. They are derived from existing as well as newly developed methods of digital image processing, mainly based on data segmentation and morphological operations. Performance of the developed methods is compared to expert manual assessments and it proves to be comparable with clinicians conclusions.

In this paper we introduce a new theory of blur invariants. Blur invariants are image features which preserve their values if the image is convolved by a point-spread function (PSF) of a certain class. We present the invariants to convolution with an arbitrary N-fold symmetric PSF, both in Fourier and image domain. We introduce a notion of a primordial image as a canonical form of all blur-equivalent images. It is defined in spectral domain by means of projection operators. We prove that the moments of the primordial image are invariant to blur and we derive recursive formulae for their direct computation without actually constructing the primordial image. We further prove they form a complete set of invariants and show how to extent their invariance also to translation, rotation and scaling. We illustrate by simulated and real-data experiments their invariance and recognition power. Potential applications of this method are wherever one wants to recognize objects on blurred images.

In this paper we describe a method for detection and measurement of elliptical particles in atomic force microscopy (AFM) images. AFM imaging is used in physics to scan surfaces; the measured heights are represented by pixel values. Each sample in our project consisted of elliptical particles of principally the same size; the size could be characterized by the average length and width of a number of salient particles. The method we proposed is based on segmentation of undamaged particles and their approximation by ellipses; the major and minor axes provide robust estimates of the lengths and widths of the particles, respectively. The method is robust to distortions typical of AFM images. Its performance was demonstrated on images of pyrroles and compared with manual detection. Results show that the automatic method could be used in place of the time-consuming manual detection.

In this paper we propose a method for automatic removal of artifacts from artwork cross-section images. Cross-section images of minute samples are acquired during the painting material research of an artwork before actual conservation is performed. Such images are unfortunately damaged by the artifacts from grinding of the resin in which the sample is embedded. Removing those artifacts can improve the outcome of image segmentation and other image processing methods. The proposed algorithm can also simplify an analysis of un-derdrawings by reducing the canvas structure after infrared acquisition. Despite the idea is not entirely original, the application to cultural heritage data is novel and the implementation does not require user interaction.

Materials research of microscopic cross-sections of paintings color layers is a very useful tool. It gives the restorers better insight into the technique, reveals how the artwork was created and what kind of materials was used. The proposed approach solves the problem of the proper spatial alignment of visible light and ultraviolet light images of cross-sections for further analysis by means of multimodal geometrical image registration. Then, the application offers primary segmentation of color layers. Second part of our work deals with automatic image retrieval, as a part of designing a database of laboratory research reports for restoration purposes. The aim is to facilitate search for reports about artworks with similar characteristic, based on the cross-section images.

We present the construction of combined blur and rotation moment invariants in arbitrary number of dimensions. Moment invariants to convolution with an arbitrary centrosymmetric filter are derived first, and then their rotationally invariant forms are found by means of group representation theory to achieve the desired combined invariance. Several examples of the invariants are calculated explicitly to illustrate the proposed procedure. Their invariance, robustness, and capability of using in template matching and in image registration are demonstrated on 3D MRI data and 2D indoor images.

The topic of the paper is to estimate parameters of the camera motion using images taken at initial and current positions of the camera. An original method handling defocused images or images blurred in other ways is proposed. The method is based on registering the images by means of detected control points (CP) and so-called combined invariants. These features are invariant both to rigid-body transform and to blurring caused by convolution with an arbitrary centrosymmetric point-spread function (PSF). Thanks to this, the camera position can be estimated directly from defocused images without any deblurring.

We present an application of digital image processing to the analysis of the conservation of a medieval mosaic. The art piece is the "The Last Judgement" mosaic, situated on the wall of St Vitus Cathedral in Prague, Czech Republic. A 19/sup th/ century historical photograph of the mosaic was compared with a photograph of its current reconstructed state. The images were first preprocessed to increase their quality (noise reduction, deblurring). In the second stage, geometrical differences between images were removed by means of image registration techniques. Finally, differences between the current and historical photographs were identified.

The viewing hemisphere of a 3-dimensional object can be partitioned into areas of similar views, termed view bubbles. We compare two procedures of generating view bubbles: tracking of object features, i.e., Gabor wavelet responses, by utilizing the continuity of successive views and matching of features in different views, which are assumed to be independent. Both pro-cedures proved to be appropriate to detect canonical views. We found no difference concerning the size of the view bubbles, but tracking provides more precise correspondences than matching. Tracking is more appropri-ate for recognizing changes of features, whereas matching is more suitable if features of the same appearance are to be found. 1 Subject of Investigation For pose-invariant object recognition and pose estimation of objects it is necessary to uti-lize an appropriate object representation. A naive representation might consist of densly spaced views of an object’s viewing sphere. Our aim is to reduce such a “full ” represen-

A new class of moment-based features invariant to image rotation, translation, scaling, contrast changes and also to convolution with an unknown PSF are introduced in this paper. These features can be used for the recognition of objects captured by a nonideal imaging system of unknown position and blurring parameters.