Italy


Deep learning approaches have achieved impressive results in breast ultrasound (BUS) image segmentation. However, these methods did not solve uncertainty and noise in BUS images well. Meanwhile, they did not involve the context information of BUS images, either. To address this issue, we present a novel deep learning structure for BUS image semantic segmentation by analyzing the uncertainty using a pyramid fuzzy block and generating a novel feature based on connectedness. There are three major contributions in this paper: (1) the structure of pyramid fuzzy block; (2) a novel membership function based on multi-convolution layers; and (3) a novel context feature based on connectedness. The proposed methods are applied to two datasets: a BUS image benchmark with two categories (background and tumor) and a five-category BUS image dataset with fat layer, mammary layer, muscle layer, background, and tumor. The proposed method achieves the best results on both datasets compared with eight state-of-the-art deep learning-based approaches.

ICPR 2020

Semantic Segmentation of Breast Ultrasound Image with Pyramid Fuzzy Uncertainty Reduction and Direction Connectedness Feature

direction connectedness

breast ultrasound (bus) image

fuzzy logic

segmentation

[![](https://assets.underline.io/uploads/markdown_image/1/image/261902fdf187a88bfa74da226ff77186.png)](https://drive.google.com/file/d/1gUViQJJHCSgM38OhwpDoTdN89evCsZ-7/view?usp=sharing)
[![](https://assets.underline.io/uploads/markdown_image/1/image/1605292c232e6f185c7f87ee38e8502a.png)](https://drive.google.com/file/d/1kPkznVX_6cx-n846z_pUtyVDZql9KImc/view?usp=sharing)


### **Welcome Message**

Welcome to the inaugural **Dutch Lung Congress.**  We have all missed our opportunities to network and interact with our colleagues in the last twelve months or more.  While our desire was to meet face to face once again, when it became evident that this would not be possible until much later in 2021 (or even into 2022) the hard working committee organizing the Dutch Lung Congress found, what we hope will be, an excellent alternative to facilitate our annual meeting.

The Dutch Lung Congress aims to bring together everyone interested in research related to pulmonary diseases in the Netherlands.  We hope this event will provide opportunities for multidisciplinary interactions to enhance our approaches for addressing these challenging diseases.  Each session will include input from patients, clinical and basic and/or translational scientists discussing the latest information around the central themes chosen by the organizing committee.  One advantage of holding our congress as a virtual event this year is that we will have the opportunity to hear from world leading experts from all over the globe.  We hope you enjoy the programme the organizing committee have put together and will engage in dynamic discussions with all the speakers.

One highlight of our congress will be the Young Investigator Session.  Remember to join us for this exciting session when we will hear from the presenters who submitted the top scoring abstracts.  This promises to be a session full of exciting science that will display the strengths that constitute the future talent in our field.

When we are not listening to these great presentations we can all meet in Gathertown.  Within this interactive platform you will be able to meet colleagues and friends for networking. Enjoy a private chat over a virtual coffee, visit the booths of our sponsors and other parties, chat with the Young Investigator Board members or take some timeout in the relaxation spaces.  While in Gathertown take the opportunity to visit all the diverse posters on display. Chat live with the presenters or leave them a question on the discussion board for them to engage with you.  Make sure you check for any messages each time you enter Gathertown to make the most of your networking opportunities.

We look forward to seeing you during the DLC and the great scientific (and other) discussions we are anticipating during our 2021 meeting.

On behalf of the DLC organizing Committee
<br>**Janette Burgess
<br>Chair, DLC Organizing Committee**
![](https://assets.underline.io/uploads/markdown_image/1/image/f461fb275d9667fb2a76a30813388e90.png)



### Special Session: Publieksmiddag
![](https://assets.underline.io/uploads/markdown_image/1/image/77e768dd500e6205175e5cafba59abdc.png)






![](https://assets.underline.io/uploads/markdown_image/1/image/f461fb275d9667fb2a76a30813388e90.png)
**More about the committee team:**:
[Barbro N. Melgert, PhD] (https://drive.google.com/file/d/1q_IIH3JvTivumCUzzsZGX7BgD41HxQmk/view?usp=sharing)
// [Bas Holverda, PhD] (https://drive.google.com/file/d/1QKXHmTTQjgs4OZVuM8doXU055S-fu_uU/view?usp=sharing)
// [Frits Franssen, PhD] (https://drive.google.com/file/d/1d7HRUJaqGuRFzkPN3SVgkbBfqFkDkWq2/view?usp=sharing)
// [Janette Burgess, PhD] (https://drive.google.com/file/d/1VHFlrEN6uCQGeeW3Lj4I8aTw7HsB0GFr/view?usp=sharing)
// [Michel van den Heuvel, PhD] (https://drive.google.com/file/d/1JeOEP8MHxiK_4lONr8UM2HaxdxpkAmA2/view?usp=sharing)
// [Patrick Bhairosing] (https://drive.google.com/file/d/1xI8ORq-g1bbVcrlRDviZ9NhAwanc4dFl/view?usp=sharing)
// [Gimano Amatngalim, PhD] (https://drive.google.com/file/d/1fyVDDKARLNjRk_JZk8_GyhGMjmp6DWHp/view?usp=sharing)
// [Peter Kunst, PhD] (https://drive.google.com/file/d/1QhtB4nQezpAjbfUAcBnINc-Bm3Shy2Lf/view?usp=sharing)
// [Dr. Michel van den Heuvel, Prof., MD, PhD] (https://drive.google.com/file/d/1JBdNEBXZCEikEZhJ6MoD5DhQfXMz3bP6/view?usp=sharing)
![](https://assets.underline.io/uploads/markdown_image/1/image/f461fb275d9667fb2a76a30813388e90.png)

Please register with DLC to be able to enter the conference on Underline.io. If you have already registered, please login to Underline.io to be able to see full conference content. In case you do not have an Underline account, please create one. Thank you 

Please login to your Underline account

Dutch Lung Congress

poster

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


We focus on 1 : N identification tasks with binary features. 
Most multiclass classification methods, including identification and verification methods, use a shared metric space in which distances between samples are measured regardless of their identities. This is because dedicated metric spaces learned for each identity in the training set are of little use for the test set. In 1 : N identification tasks, however, gallery samples contain rich information about the test domain. Given a sample and its neighbors in the gallery set, we propose a method for calculating a discriminative feature selection mask that is used as a sample-dependent distance metric. Experiments on several reidentification datasets show that the proposed method enhances the performance of state-of-the-art feature extractors.

Sample-Dependent Distance for 1 : N Identification via Discriminative Feature Selection

In this presentation, we focus on evaluating the initialization of the Nelder-Mead method for hyperparameter optimization in deep learning. The Nelder-Mead (NM) method is known for superior performance for hyperparameter optimization in deep learning. An initial value, one of the initial NM method’s values, is usually determined randomly while the search performance strongly depends on the initial value. Therefore, we clarified its influence on the search performance to determine the proper initial value.
The result contributes to the determination of the initial value in the Nelder-Mead method.

Evaluating Initialization of Nelder-Mead Method for Hyperparameter Optimization in Deep Learning

With the development of technology, biometrics are used for identification. As a biological behavior feature, lip motion has become a new kind of biometric in speaker recognition. In the literature, lots of works used 2D lip images to recognize speaker in a text-dependent context. However, 2D lip easily suffers from face orientations. To this end, in this work, we present a novel end-to-end 3D lip motion Network (3LMNet) by utilizing the sentence-level 3D lip motion (S3DLM) to recognize speakers in both the text-independent and text-dependent contexts.

Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition


Attention module has achieved great success in numerous vision tasks. However, existing visual attention modules generally consider the features of a single-scale, and cannot make full use of their multi-scale contextual information. Meanwhile, the multi-scale spatial feature representation has demonstrated its outstanding performance in a wide range of applications. However, the multi-scale features are always represented in a layer-wise manner, i.e. it is impossible to know their contextual information at a granular level. Focusing on the above issue, a context-aware residual module for image classification is proposed in this paper. It consists of a novel multi-scale channel attention module MSCAM to learn refined channel weights by considering the visual features of its own scale and its surrounding fields, and a multi-scale spatial aware module MSSAM to further capture more spatial information. Either or both of the two modules can be plugged into any CNN-based backbone image classification architecture with a short residual connection to obtain the context-aware enhanced features. The experiments on public image recognition datasets including CIFAR10, CIFAR100，Tiny-ImageNet and ImageNet consistently demonstrate that our proposed modules significantly outperforms a wide-used state-of-the-art methods, e.g., ResNet and the lightweight networks of MobileNet and SqueezeeNet.

Context-Aware Residual Module for Image Classification

Computational Fluid Dynamics (CFD) simulations are a very important tool for many industrial applications, such as aerodynamic optimization of engineering designs like cars shapes, airplanes parts etc. The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated. Automated data analysis methods are warranted but a non-trivial obstacle is given by the very large dimensionality of the data. A flow field typically consists of six measurement values for each point of the computational grid in 3D space and time (velocity vector values, turbulent kinetic energy, pressure and viscosity). In this paper we address the task of extracting meaningful results in an automated manner from such high dimensional data sets. We propose deep learning methods which are capable of processing such data and which can be trained to solve relevant tasks on simulation data, i.e. predicting drag and lift forces applied on an airfoil. We also propose an adaptation of the classical hand crafted features known from computer vision to address the same problem and compare a large variety of descriptors and detectors. Finally, we compile a large dataset of 2D simulations of the flow field around airfoils which contains 16000 flow fields with which we tested and compared approaches. Our results show that the deep learning-based methods, as well as hand crafted feature based approaches, are well-capable to accurately describe the content of the CFD simulation output on the proposed dataset.

Comparison of deep learning and hand crafted features for mining simulation data

We present a novel adaptive optimization algorithm for black-box multi-objective optimization problems with binary constraints on the foundation of Bayes optimization. Our method is based on probabilistic regression and classification models, which act as a surrogate for the optimization goals and allow us to suggest multiple design points at once in each iteration. The proposed acquisition function is intuitively understandable and can be tuned to the demands of the problems at hand. We also present a novel ellipsoid truncation method to speed up the expected hypervolume calculation in a straightforward way for regression models with a normal probability density. We benchmark our approach with an evolutionary algorithm on multiple test problems.

Adaptive Sampling of Pareto Frontiers with Binary Constraints using Regression and Classification

We investigated the threat level of realistic attacks using latent fingerprints against sensors equipped with state-of-art liveness detectors and fingerprint verification systems which integrate such liveness algorithms. To the best of our knowledge, only a previous investigation was done with spoofs from latent prints. In this paper, we focus on using snapshot pictures of latent fingerprints.

Are Spoofs From Latent Fingerprints a Real Threat for
The Best State-of-art Liveness Detectors?

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures.

A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition

Facial cosmetics have the ability to substantially alter the facial appearance, which can negatively affect the decisions of a face recognition. In addition, it was recently shown that the application of makeup can be abused to launch so-called makeup presentation attacks. In such attacks, the attacker might apply heavy makeup in order to achieve the facial appearance of a target subject for the purpose of impersonation. 
In this work, we assess the vulnerability of a COTS face recognition system to makeup presentation attacks employing the publicly available Makeup Induced Face Spoofing (MIFS) database. It is shown that makeup presentation attacks might seriously impact the security of the face recognition system. Further, we propose an attack detection scheme which distinguishes makeup presentation attacks from genuine authentication attempts by analysing differences in deep face representations obtained from potential makeup presentation attacks and corresponding target face images. The proposed detection system employs a machine learning-based classifier, which is trained with synthetically generated makeup presentation attacks utilizing a generative adversarial network for facial makeup transfer in conjunction with image warping. Experimental evaluations conducted using the MIFS database reveal a detection equal error rate of 0.7% for the task of separating genuine authentication attempts from makeup presentation attacks.

Detection of Makeup Presentation Attacks based on Deep Face Representations

In this paper we study the poorly investigated problem of learning Random Forests for distance-based Random Forest clustering. We studied both classic schemes as well as alternative approaches, novel in this context. In particular, we investigated the suitability of Gaussian Density Forests, Random Forests specifically designed for density estimation. Further, we introduce a novel variant of Random Forest, based on an effective non parametric by-pass estimator of the Renyi entropy, which can be useful when the parametric assumption is too strict. An empirical evaluation involving different datasets and different RF-clustering strategies confirms that the learning step is crucial for RF-clustering. We also present a set of practical guidelines useful to determine the most suitable variant of RF-clustering according to the problem under examination.

Premium content

Downloads

Next from ICPR 2020

Sample-Dependent Distance for 1 : N Identification via Discriminative Feature Selection

Similar lecture

Work-related meets environmental asthma in a bus driver