Set Of Example Images Research Articles

Imaging Features of Calcium Pyrophosphate Deposition Disease: Consensus Definitions From an International Multidisciplinary Working Group.

To develop definitions for imaging features being considered as potential classification criteria for calcium pyrophosphate deposition (CPPD) disease, additional to clinical and laboratory criteria, and to compile example images of CPPD on different imaging modalities. The American College of Rheumatology and European Alliance of Associations for Rheumatology CPPD classification criteria Imaging Advisory Group (IAG) and Steering Committee drafted definitions of imaging features that are characteristic of CPPD on conventional radiography (CR), conventional computed tomography (CT), dual-energy CT (DECT), and magnetic resonance imaging (MRI). An anonymous expert survey was undertaken by a 35-member Combined Expert Committee, including all IAG members. The IAG and 5 external musculoskeletal radiologists with expertise in CPPD convened virtually to further refine item definitions and voted on example images illustrating CR, CT, and DECT item definitions, with ≥90% agreement required to deem them acceptable. The Combined Expert Committee survey indicated consensus on all CR definitions. The IAG and external radiologists reached consensus on CT and DECT item definitions, which specify that calcium pyrophosphate deposits appear less dense than cortical bone. The group developed an MRI definition and acknowledged limitations of this modality for CPPD. Ten example images for CPPD were voted acceptable (4 CR, 4 CT, and 2 DECT), and 3 images of basic calcium phosphate deposition were voted acceptable to serve as contrast against imaging features of CPPD. An international group of rheumatologists and musculoskeletal radiologists defined imaging features characteristic of CPPD on CR, CT, and DECT and assembled a set of example images as a reference for future clinical research studies.

Towards a more reliable manufacturing future – Automatic classification of failure modes during adhesion testing of silicon solar cells

Busbar pull tests are the generally accepted method of measuring metal-silicon adhesion for silicon solar cells. However, this method cannot be used to measure metal finger adhesion and consequently cannot be used for cells being interconnected with new technologies that require no busbars to be formed on the cell or for when finger and busbar adhesion can differ. To address this need, a stylus-based adhesion tester has been developed that enables direct finger adhesion measurements. However, the operation of this tester results in different finger impact failure modes depending on the relative cohesive and adhesive properties of the metal fingers, and these different finger impact modes need to be differentiated before the measured forces can be used for comparative purposes. In this paper, we report on the implementation of an automatic classifier of failure modes for stylus-based adhesion testing. The classifier analyses video frames corresponding to when the stylus laterally impacts fingers on the solar cell surface and classifies them using a support vector machine classifier trained on features extracted from a set of example images. A classification accuracy of 94.4% ± 0.4%abs was achieved on a test set of images comprising finger impacts on both screen-printed and plated silicon solar cells when a “Histogram of Oriented Gradients” (HOG) algorithm was used to generate the image features. Using a Matlab implementation, it took 3.2 s to classify 500 test images using the HOG features. This suggests that only 7–8 s would be required to analyse the finger impacts for a 156 mm industrial silicon solar cell, with even further reduced processing times made possible by software optimisation and reducing the number of scans across the solar cell.

Generalised non‐locally centralised image de‐noising using sparse dictionary

Recently, image de-noising algorithm based on sparse representation has received an increasing amount of attention. Such algorithms proposed a comprehensive sparse representation model, by solving the sparse coding problem and choosing the proper method for dictionary updating to achieve better de-noising results. Therefore, the construction of learning dictionary has become one of the key problems that limit the de-noising effectiveness. The non-locally centralised sparse representation de-noising algorithm uses principal component analysis method to achieve dictionary updating. Nevertheless, the instability of a single complete dictionary in sparse coding leads to erratic result in the process of the original image restoration. In this study, the authors present a new method named generalised non-locally centralised sparse representation algorithm. In the proposed method, the authors cluster the training patches extracted from a set of example images into subspaces, and then train dictionaries for subspaces by sparse analysis k-singular value decomposition dictionary, which is utilised to construct coded sub-block dictionary to avoid the instable results caused by a single dictionary. Experiments show that the improved method has better signal-to-noise ratio and de-noising effect compared with other methods.

Evolutionary Design of Problem-Adapted Image Descriptors for Texture Classification

Effective texture classification requires image descriptors capable of efficiently detecting, extracting, and describing the most relevant information in the images, so that, for instance, different texture classes can be distinguished despite image distortions such as varying illuminations, viewpoints, scales, and rotations. Designing such an image descriptor is a challenging task that typically involves the intervention of human experts. In this paper, a general method to automatically design effective image descriptors is proposed. Our method is based on grammatical evolution and, using a set of example images from a texture classification problem and a classification algorithm as inputs, generates problem-adapted image descriptors that achieve very competitive classification results. Our method is tested on five well-known texture data sets with different number of classes and image distortions to prove its effectiveness and robustness. Our classification results are statistically compared against those obtained by means of six popular hand-crafted texture descriptors in the state of the art. This statistical analysis shows that our evolutionarily designed descriptors outperform most of those designed by human experts.

Incremental object matching and detection with Bayesian methods and particle filters

This study is about object matching, that is, a problem of locating the corresponding points of an object in an image. Conventional approaches to object matching are batch methods, meaning that the methods first learn the object model from a training set of example images that contain instances of the object, and then use the learned object model to match instances of the same object (or object class) in unseen test images. Such batch learning often leads to computationally heavy learning, at least when the images are incorporated sequentially into the system and large memory requirements. In computer vision, little work has been done in developing incremental object learners. Especially, an incremental object-matching method has – to the best knowledge of the authors – never been introduced. In this paper, the authors present such a method. Our technique finds the corresponding points of similar object instances, appearing in natural greyscale images with arbitrary location, scale and orientation, by processing the images sequentially. The approach is Bayesian and combines the shape and appearance of the corresponding points into the posterior distribution for the location of them. The posterior distribution is recursively sampled with particle filters to locate the most probable corresponding point sets in the image being processed. The results indicate that the matched corresponding points can be used in forming a representation of the object with which instances of the object in novel test images are successfully detected.

Integrating semantic annotation and information visualization for the analysis of multichannel fluorescence micrographs from pancreatic tissue

The challenging problem of computational bioimage analysis receives growing attention from life sciences. Fluorescence microscopy is capable of simultaneously visualizing multiple molecules by staining with different fluorescent dyes. In the analysis of the result multichannel images, segmentation of ROIs resembles only a first step which must be followed by a second step towards the analysis of the ROI’s signals in the different channels. In this paper we present a system that combines image segmentation and information visualization principles for an integrated analysis of fluorescence micrographs of tissue samples. The analysis aims at the detection and annotation of cells of the Islets of Langerhans and the whole pancreas, which is of great importance in diabetes studies and in the search for new anti-diabetes treatments. The system operates with two modules. The automatic annotation module applies supervised machine learning for cell detection and segmentation. The second information visualization module can be used for an interactive classification and visualization of cell types following the link-and-brush principle for filtering. We can compare the results obtained with our system with results obtained manually by an expert, who evaluated a set of example images three times to account for his intra-observer variance. The comparison shows that using our system the images can be evaluated with high accuracy which allows a considerable speed up of the time-consuming evaluation process.

Semi-adaptive, convex optimisation methodology for image denoising

An optimisation methodology based on a semi-adaptive, convex (SAC) formulation for the image denoising problem is proposed for recovering both sharp edges and smooth subsurfaces from a given noisy image. Basic steps to realise an image denoising algorithm with proper restoration properties and practical computational efficiency with automatic determination of free parameters are described. A set of example images is used to illustrate the proposed approach.

Modelling grey level surfaces using three-dimensional point distribution models

Point Distribution Models (PDM) allow a compact description of an object's shape to be found from a set of example images. This paper investigates adding a third dimension, intensity, to the PDM. Models are derived which include modes of variation in intensity, and mention is made of more recent work that has extended this work to colour. The inclusion of intensity complicates the task of fitting the model by adding new dimensions to the objective function. A two-stage fitting strategy is used to overcome this problem. Nine images were analysed successfully with this strategy. The resulting improvement in fit enables a clear distinction to be made between objects that are animals and those that are not.

Flexible colour point distribution models

A technique is described which models the way the colour of a set of objects can change. Models are derived from a set of example images. They describe the average appearance of an object and the way in which that appearance can change. Two types of object have been modelled using this method, and the models have been fitted to objects not seen in the training data.

Model based location of pigs in scenes

Abstract Point distribution models (PDMs) allow a compact description of an object's shape to be found from a set of example images. In previous work by the second author a method of incorporating grey level information into a PDM was developed. Further work investigated fitting such a composite model to image data consisting of a set of images of a pig viewed from above. This paper describes work on images containing more than one pig. A technique for initialising the model is used which searches the image for ridges in the grey level landscape. These generally lie along the backbone of the animal and provide a good starting point for automatic fitting. By minimising an objective function which measures the difference in grey level and the error in boundary correspondence, an accurate fit of model to data is obtained. Ridge detection initialises the model to within ±12 pixels of the object. Strict limits on the boundaries of the search space constrain the minimisation process allowing convergence to the true minimum. The resulting fit is good even for objects which are partially obscured. Poor final values of the objective function allow the detection of erroneous results.

Fitting grey level point distribution models to animals in scenes

Point distribution models allow a compact description of an object's shape to be found from a set of example images. In previous work by the first author, a method of incorporating grey level information into a PDM was developed. This paper investigates fitting such a composite model to image data consisting of a set of images of a pig viewed from above. Model fitting is achieved by optimizing an objective function consisting of two components, one that measures the degree of grey level correspondence between the model and the data, and the other that measures how well the boundary of the model fits the data. The shape of the objective function as the model parameters are varied is investigated, and an optimization strategy developed. The strategy is used to find a pig in a number of images with backgrounds of increasing complexity. The strategy performs well with both an uncluttered and a realistic background. The performance with a simulated noisy background is not so good when the boundary component is included in the objective function. This is a result of the boundary component being more sensitive to noise in the image. In this case, it is better to optimize with the grey level component alone. A problem is identified when the grey level distribution changes significantly as the pig moves under the light source. It is suggested that this could be overcome by including variations in grey level distribution as modes in the model