Anders Boesen Lindbo Larsen

Assessment of algorithms for mitosis detection in breast cancer histopathology images.

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

HEp-2 Cell Classification Using Shape Index Histograms With Donut-Shaped Spatial Pooling

We present a new method for automatic classification of indirect immunoflourescence images of HEp-2 cells into different staining pattern classes. Our method is based on a new texture measure called shape index histograms that captures second-order image structure at multiple scales. Moreover, we introduce a spatial decomposition scheme which is radially symmetric and suitable for cell images. The spatial decomposition is performed using donut-shaped pooling regions of varying sizes when gathering histogram contributions. We evaluate our method using both the ICIP 2013 and the ICPR 2012 competition datasets. Our results show that shape index histograms are superior to other popular texture descriptors for HEp-2 cell classification. Moreover, when comparing to other automated systems for HEp-2 cell classification we show that shape index histograms are very competitive; especially considering the relatively low complexity of the method.

Vision-based method for tracking meat cuts in slaughterhouses.

Meat traceability is important for linking process and quality parameters from the individual meat cuts back to the production data from the farmer that produced the animal. Current tracking systems rely on physical tagging, which is too intrusive for individual meat cuts in a slaughterhouse environment. In this article, we demonstrate a computer vision system for recognizing meat cuts at different points along a slaughterhouse production line. More specifically, we show that 211 pig loins can be identified correctly between two photo sessions. The pig loins undergo various perturbation scenarios (hanging, rough treatment and incorrect trimming) and our method is able to handle these perturbations gracefully. This study shows that the suggested vision-based approach to tracking is a promising alternative to the more intrusive methods currently available.

Estimating the workpiece-backing plate heat transfer coefficient in friction stirwelding

Purpose – The purpose of this paper is to determine the magnitude and spatial distribution of the heat transfer coefficient between the workpiece and the backing plate in a friction stir welding process using inverse modelling. Design/methodology/approach – The magnitude and distribution of the heat transfer coefficient are the variables in an optimisation problem. The objective is to minimise the difference between experimentally measured temperatures and temperatures obtained using a 3D finite element model. The optimisation problem is solved using a gradient based optimisation method. This approach yields optimal values for the magnitude and distribution of the heat transfer coefficient. Findings – It is found that the heat transfer coefficient between the workpiece and the backing plate is non-uniform and takes its maximum value in a region below the welding tool. Four different parameterisations of the spatial distribution of the heat transfer coefficient are analysed and a simple, two parameter dist...

Oriented Shape Index Histograms for Cell Classification

We propose a novel extension to the shape index histogram feature descriptor where the orientation of the second-order curvature is included in the histograms. The orientation of the shape index is reminiscent but not equal to gradient orientation which is widely used for feature description. We evaluate our new feature descriptor using a public dataset consisting of HEp-2 cell images from indirect immunoflourescence lighting. Our results show that we can improve classification performance significantly when including the shape index orientation. Notably, we show that shape index orientation outperforms the gradient orientation on the dataset.

Pond of illusion: interacting through mixed reality

Pond of Illusion is a mixed reality installation where a virtual space (the pond) is injected between two real spaces. The users are in either of the real spaces, and they can see each other through windows in the virtual space as illustrated in Figure 1(left). The installation attracts people to a large display in either of the real spaces by allowing them to feed virtual fish swimming in the pond. Figure 1(middle) shows how a Microsoft Kinect mounted on top of the display is used for detecting throw motions, which triggers virtual breadcrumbs to be thrown into the pond for feeding the nearby fish. Of course, the fish may not be available because they are busy eating what people have thrown into the pond from the other side.