Article
Automatic Determination of Cell Division Rate Using Microscope Images
The sixteen-volume set comprising the LNCS volumes 11205-11220 constitutes the refereed proceedings of the 15th European Conference on Computer Vision, ECCV 2018, held in Munich, Germany, in September 2018.
The 776 revised papers presented were carefully reviewed and selected from 2439 submissions. The papers are organized in topical sections on learning for vision; computational photography; human analysis; human sensing; stereo and reconstruction; optimization; matching and recognition; video attention; and poster sessions.
Binary energy optimization is a popular approach for segmenting an image into foreground/background regions. To model region appearance, color, a relatively high dimensional feature, should be handled effectively. A full color histogram is usually too sparse to be reliable. One approach is to reduce dimensionality by color space clustering. Another popular approach is to fit GMMs for soft color space clustering. These approaches work well when the foreground/background are sufficiently distinct. In cases of more subtle difference in appearance, both approaches may reduce or even eliminate foreground/background distinction. This happens because either color clustering is performed completely independently from segmentation, as a preprocessing step (in clustering), or independently for the foreground and independently for the background (in GMM). We propose to make clustering an integral part of segmentation, by including a new clustering term in the energy. Our energy favors clusterings that make foreground/ background appearance more distinct. Exact optimization is not feasible, therefore we develop an approximate algorithm. We show the advantage of including the color clustering term into the energy function on camouflage images, as well as standard segmentation datasets.
The Shape Boltzmann Machine (SBM) and its multilabel version MSBM have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of objects and the seeds which approximately correspond to the locations of objects parts. The latter can be obtained from part-based detectors in an unsupervised manner. We derive a latent variable model and an EM-like training procedure for adjusting the weights of MSBM using a deep learning framework. We show that the model trained by our method outperforms SBM in the tasks related to binary shapes and is very close to the original MSBM in terms of quality of multilabel shapes.
In the paper we address a challenging problem of incorporating preferences on possible shapes of an object in a binary image segmentation framework. We extend the well-known conditional random fields model by adding new variables that are responsible for the shape of an object. We describe the shape via a flexible graph augmented with vertex positions and edge widths. We derive exact and approximate algorithms for MAP estimation of label and shape variables given an image. An original learning procedure for tuning parameters of our model based on unlabeled images with only shape descriptions given is also presented. Experiments confirm that our model improves the segmentation quality in hard-to-segment images by taking into account the knowledge about typical shapes of the object.
Parameters that affect the perception quality of visual data has been investigated. Evaluation of such parameters due to distortion during filtering was determined. Segmentation methods according to colour and brightness similarity were discussed. Perceptive model for contrast sensitivity influence evaluation was discussed. The image region detection method for watermarking is suggested.
The sixteen-volume set comprising the LNCS volumes 11205-11220 constitutes the refereed proceedings of the 15th European Conference on Computer Vision, ECCV 2018, held in Munich, Germany, in September 2018. The 776 revised papers presented were carefully reviewed and selected from 2439 submissions. The papers are organized in topical sections on learning for vision; computational photography; human analysis; human sensing; stereo and reconstruction; optimization; matching and recognition; video attention; and poster sessions.
We discuss a model for image segmentation that is able to overcome the short-boundary bias observed in standard pairwise random field based approaches. To wit, we show that a random field with multi-layered hidden units can encode boundary preserving higher order potentials such as the ones used in the cooperative cuts model of [11] while still allowing for fast and exact MAP inference. Exact inference allows our model to outperform previous image segmentation methods, and to see the true effect of coupling graph edges. Finally, our model can be easily extended to handle segmentation instances with multiple labels, for which it yields promising results.