Italy

Semantic segmentation and shape detection of lumbar vertebrae, sacrum, and femoral heads from clinical X-ray images are important and challenging tasks. In this paper, we propose a new multi-path convolutional neural network, BiLuNet, for semantic segmentation on X-ray images. The network is capable of medical image segmentation with very limited training data. With the shape fitting of the bones, we can identify the location of the target regions very accurately for lumbar vertebra inspection. We collected our dataset and annotated by doctors for model training and performance evaluation. Compared to the state-of-the-art methods, the proposed technique provides better mIoUs and higher success rates with the same training data. The experimental results have demonstrated the feasibility of our network to perform semantic segmentation for lumbar vertebrae, sacrum, and femoral heads.

ICPR 2020

BiLuNet: A Multi-path Network for Semantic Segmentation on X-ray Images

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. 


poster

The presentation reviews the work and demonstrates the purposed hybrid machine learning techniques to predict the energy consumption with multi-source data.

A Hybrid Machine Learning Approach for Energy Consumption Prediction in Additive Manufacturing

We present a multiregion image segmentation approach which utilizes multiscale anisotropic diffusion based scale spaces. By combining powerful edge preserving anisotropic diffusion smoothing with isolevel set linking and merging, we obtain coherent segments which are tracked across multiple scales. A hierarchical tree representation of the given input image with progressively simplified regions is used with intra-scale splitting and inter-scale merging for obtaining multiregion segmentations. Experimental results on natural and medical images indicate that multiregion, multiscale image segmentation (MMIS) approach obtains coherent segmentation results.

Multiregion multiscale image segmentation with anisotropic diffusion

Deep-learning-based methods have been used for 3D action recognition in recent years. Methods based on recurrent neural networks (RNNs) have the advantage of modeling long-term context, but they fo- cus mainly on temporal information and ignore the spatial relationships in each skeleton frame. In addition, it is difficult to handle a very long skeleton sequence using an RNN. Compared with an RNN, a convolu- tional neural network (CNN) is better able to extract spatial information. To model the temporal information of skeleton sequences and incorpo- rate the spatial relationship in each frame efficiently using a CNN, this paper proposes a multi-feature skeleton representation for encoding fea- tures from original skeleton sequences. The relative distances between joints in each skeleton frame are computed from the original skeleton sequence, and several relative angles between the skeleton structures are computed. This useful information from the original skeleton sequence is encoded as pixels in grayscale images. To preserve more spatial re- lationships between input skeleton joints in these images, the skeleton joints are divided into five groups: one for the trunk and one for each arm and each leg. Relationships between joints in the same group are more relevant than those between joints in different groups. By rear- ranging pixels in encoded images, the joints that are mutually related in the spatial structure are adjacent in the images. The skeleton repre- sentations, composed of several grayscale images, are input to CNNs for action recognition. Experimental results demonstrate the effectiveness of the proposed method on three public 3D skeleton-based action datasets.

A Novel Multi-Feature Skeleton Representation for 3D Action Recognition

Semantic segmentation is always a key problem in remote sensing image analysis. Especially, it is very useful for city-scale vehicle detection. However, multi-object and imbalanced data classes of remote sensing images bring a huge challenge, which leads that many traditional segmentation approaches were often unsatisfactory. In this paper, we propose a novel Refined Semantic Segmentation Network (R2SN), which apply the classic encoder-to-decoder framework to handle segmentation problem. However, we add the convolution layers in encoder and decoder to make the network can achieve more local information in the training step. The design is more suitable for high-resolution remote sensing image. More specially, the classic Focal loss is introduced in this network, which can guide the model focus on the difficult objects in remote sensing images and effectively handle multi-object segmentation problem. Meanwhile, the classic Hinge loss is also utilized to increase the distinction between classes, which can guarantee the more refined segmentation results. We validate our approach on the International Society for Photogrammetry and Remote Sensing (ISPRS) semantic segmentation benchmark dataset. The evaluation and comparison results show that our method exceeds the state-of-the-art remote sensing image segmentation methods in terms of mean intersection over union (MIoU), pixel accuracy, and F1-score.

Refined Semantic Segmentation Network of City Remote Sensing Image

In our work, we focused on face identification from thermal images. Thermal face identification brings several advantages such as ease of handling with low resolution images, robust to illumination and privacy preserving.
Moreover, we considered scenarios in which face identification from thermal images is performed with low computation and memory resources, making such systems suitable for mobile or embedded applications such as STM32F7 family microcontroller.

Real-Time Thermal Face Identification System for Low Memory Vision Applications Using CNN

In this work we use two approaches to prevent double spend-
ing and secure IoT transaction through Blockchain and information fu-
sion techniques: the rst method is based on Smart Contracts; while
the second method is implemented by a novel Blockchain system. Both
methods use a hybrid RSA and biometric codes fusion in order to have
an encrypted, taking account of the privacy, identity of the spender. In
Blockchain a contract between the parties is stipulated and the biomet-
ric fused code are kept. The used coin pack is tagged, so a future double
spending or any illegal action on the IoT network or Smart city becomes
forbidden and prosecutable legally. The second part of the work will
present a novel Blockchain where a transaction can be signed only if the
user is successfully authenticated though his biometric fused key.

Blockchain-based iris authentication in order tosecure IoT access and digital money spending

Media forensics has attracted a lot of attention in the last years in part due to the increasing concerns around DeepFakes. Since the initial DeepFake databases from the 1st generation such as UADFV and FaceForensics++ up to the latest databases of the 2nd generation such as Celeb-DF and DFDC, many visual improvements have been carried out, making fake videos almost indistinguishable to the human eye. This
study provides an exhaustive analysis of both 1st and 2nd DeepFake generations in terms of facial regions and fake detection performance. Two different methods are considered in our experimental framework: i) the traditional one followed in the literature and based on selecting the entire face as input to the fake detection system, and ii) a novel approach based on the selection of specic facial regions as input to the fake detection system.
Among all the findings resulting from our experiments, we highlight the poor fake detection results achieved even by the strongest state-of-the-art fake detectors in the latest DeepFake databases of the 2nd generation, with Equal Error Rate results ranging from 15% to 30%. These results remark the necessity of further research to develop more sophisticated fake detectors.

DeepFakes Evolution: Analysis of Facial Regions and Fake Detection Performance

This paper proposes an ensemble of different state-of-art algorithms for realizing a face search system aimed at achieving higher
accuracies compared to any single algorithm. This is achieved by leveraging the most promising deep networks (Facenet, OpenFace, DeepFace, and
VGGFace – originally trained for face recognition) and different Approximate Nearest Neighbor Search (ANNS) algorithms (Annoy and LSHash).
Face images in the database are subjected to feature extraction (embeddings computed by deep networks) and indexing (in set structure for
faster search) by ANNS algorithms. An input face query image is processed in the following four stages. First, the face region is detected from
the query image and appropriately aligned for further processing. Second,
the facial features are extracted using multiple deep networks. Third, the
ANNS algorithms perform a fast search by efficiently shrinking the gallery
size from millions to a few hundred faces. Fourth, a fine matching is performed using two different methods separately to produce the final search
results. These are (a) cosine similarity and (b) score-based matching and
re-ranking of results. The experimental results demonstrate the diversity in results obtained by the use of multiple feature extractors and ANNS
techniques and the accuracy achieved by using the proposed ensemble
framework.

A Novel Ensemble Framework for Face Search

Food texture is a complex property; various sensory attributes such as perceived crispiness and wetness have been identified as ways to quantify it. Objective and automatic recognition of these attributes has applications in multiple fields, including health sciences and food engineering. In this work we use an in-ear microphone, commonly used for chewing detection, and propose algorithms for recognizing three food-texture attributes, specifically crispiness, wetness (moisture), and chewiness. We use binary SVMs, one for each attribute, and propose two algorithms: one that recognizes each texture attribute at the chew level and one at the chewing-bout level. We evaluate the proposed algorithms using leave-one-subject-out cross-validation on a dataset with 9 subjects. We also evaluate them using leave-one-food-type-out cross-validation, in order to examine the generalization of our approach to new, unknown food types. Our approach performs very well in recognizing crispiness (0.95 weighted accuracy on new subjects and 0.93 on new food types) and demonstrates promising results for objective and automatic recognition of wetness and chewiness.

Recognition of food-texture attributes using an in-ear microphone

A suitable combination of data in a multimodal emotion recognition model allows conveying and combining each channel's information to achieve a better recognition of the encoded emotion than would be possible using only a single modality and channel. In this paper, we focus on combining speech and physiological signals to predict the arousal and valence levels of the emotional states of a person. We designed a neural network that can use the information from raw audio signals, electrocardiograms, heart rate variability, electro-dermal activity, and skin conductance levels, to predict emotional states. The proposed deep neural network architecture works as an end-to-end process, which means, neither any pre-processing of the input data nor post-processing of the prediction of the network was applied. Using the data of the modalities available in the publicly accessible part of the RECOLA database, we achieved results comparable to other state-of-the-art approaches.

Downloads

Next from ICPR 2020

A Hybrid Machine Learning Approach for Energy Consumption Prediction in Additive Manufacturing

Similar lecture

DARN: Deep Attentive Refinement Network for Liver Tumor Segmentation from 3D CT volume