Italy


Text line localization in document images is still considered an open research task. The state-of-the-art methods in this regard are only based on the classical image analysis techniques mostly have unsatisfactory performances especially when the document images i) contain significant degradations and different noise types and scanning defects, and ii) have touching and/or multi-skewed text lines or overlapping words/characters and non-uniform inter-line space. Moreover, localizing text in ancient handwritten Arabic document images is even more complex due to the morphological particularities related to the Arabic script. Thus, in this paper, we propose a hybrid method combining a deep network with classical document image analysis techniques for text line localization in ancient handwritten Arabic document images. The proposed method is firstly based on using the U-Net architecture to extract the main area covering the text core. Then, a modified RLSA combined with topological structural analysis is applied to localize whole text lines (including the ascender and descender components). To analyze the performance of the proposed method, a set of experiments has been conducted on many recent public and private datasets, and a thorough experimental evaluation has been carried out.

ICPR 2020

Combining Deep and Ad-hoc Solutions to Localize Text Lines in Ancient Arabic Document Images

ad-hoc post-processing

text line localization

ancient arabic document images

deep architecture

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

Focusing on hyperspectral imaging together with deep learning, Sony Europe B.V and University of Padova are proposing together the paper “Semi-supervised Deep Learning Techniques for Spectrum Reconstruction”. We present a family of novel deep learning schemes for hyperspectral data estimation able to work when the hyperspectral information at our disposal is limited. Firstly, we introduce a learning scheme exploiting a physical model based on the backward mapping to the RGB space and total variation regularization that can be trained with a limited amount of HSI images. Then, we propose a novel semi-supervised learning scheme able to work even with just a few pixels labeled with hyperspectral information. The proposed techniques allow to reach impressive performances with very limited supervision with ground truth data.

Semi-supervised Deep Learning Techniques for Spectrum Reconstruction


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Uniform and Non-uniform Sampling Methods for Sub-linear Time k-means
Clustering

We study the impact of highly correlated image content on the estimated photo response non-uniformity (PRNU) of a sensor unit and its impact on the sensor identification performance. Based on eight publicly available finger vein datasets, we show formally and experimentally that the nature of finger vein imagery can cause the estimated PRNU to be biased by image content and lead to a fairly bad PRNU estimate. Such bias can cause a false increase in sensor identification performance depending on the dataset composition. Our results indicate that independent of the biometric modality, examining the quality of the estimated PRNU is essential before the sensor identification performance can be claimed to be good.

Can you really trust the sensor’s PRNU? How image content might impact the finger vein sensor identification performance

Monocular depth estimation plays a key role in 3D scene understanding, and a number of recent papers have achieved significant improvements using deep learning based algorithms. Most papers among them proposed methods that use a pre-trained network as a deep feature extractor and then decode the obtained features to create a depth map. In this study, we focus on how to use this encoder-decoder structure to deliver meaningful representation throughout the entire network. We propose a new network architecture with our suggested modules to create a more accurate depth map by bridging the context between the encoding and decoding phase. First, we place the pyramid block at the bottleneck of the network to enlarge the view and convey rich information about the global context to the decoder. Second, we suggest a skip connection with the fuse module to aggregate the encoder and decoder feature. Finally, we validate our approach on the NYU Depth V2 and KITTI datasets. The experimental results prove the efficacy of the suggested model and show performance gains over the state-of-the-art model.

Delivering Meaningful Representation for Monocular Depth Estimation


Automatic liver tumor segmentation from 3D Computed Tomography (CT) is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on Fully Convolutional Network (FCN) in liver tumor segmentation draw on success of learning discriminative multi-level features. In this paper, we propose a Deep Attentive Refinement Network (DARN) for improved liver tumor segmentation from CT volumes by fully exploiting both low and high level features embedded in different layers of FCN. Different from existing works, we exploit attention mechanism to leverage the relation of different levels of features encoded in different layers of FCN. Specifically, we introduce a Semantic Attention Refinement (SemRef) module to selectively emphasize global semantic information in low level features with the guidance of high level ones, and a Spatial Attention Refinement (SpaRef) module to adaptively enhance spatial details in high level features with the guidance of low level ones. We evaluate our network on the public MICCAI 2017 Liver Tumor Segmentation Challenge dataset (LiTS dataset) and it achieves state-of-the-art performance. The proposed refinement modules are an effective strategy to exploit multi-level features and has great potential to generalize to other medical image segmentation tasks.

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

Anthropometric body measurements are importantfor industrial design, garment fitting, medical diagnosis andergonomics. A number of methods have been proposed toestimate the body measurements from images, but progress hasbeen slow due to the lack of realistic and publicly availabledatasets. The existing works train and test on silhouettes of 3D body meshes obtained by fitting a human body model to the commercial CAESAR scans. In this work, we introduce theBODY-fit dataset that contains fitted meshes of 2,675 female and1,474 male 3D body scans. We unify evaluation on the CAESAR-fit and BODY-fit datasets by computing body measurements fromgeodesic surface paths as the ground truth and by generating two-view silhouette images. We also introduce BODY-rgb - a realisticdataset of 86 male and 108 female subjects captured with an RGBcamera and manually tape measured ground truth. We propose a simple yet effective deep CNN architecture as a baseline method which obtains competitive accuracy on the three datasets.

Silhouette Body Measurement Benchmarks

Reinforcement learning is an area of machine learning which recently has been applied in a variety of domains. A lot of challenging problems such as playing Atari video games, controlling robotics and many other fields have been solved in past few years. But when it comes to multi-agent environment, there remains much more complex challenges due to the some multiagent pathologies such as the environment non-stationary problem, curse of dimensionality, credit assignment problem and relative overgeneralization. Inspired by the application of attention mechanism in machine translation and other related domains, we propose an attention based approach called attention value decomposition network (AVD-Net), which capitalizes on the coordination relations between agents.

AVD-Net: Attention Value Decomposition Network For Deep Multi-Agent Reinforcement Learning


Degraded document image binarization is one of the most challenging tasks in the domain of document image analysis. In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game. We train the network in an unsupervised setup by assuming that we do not have any paired-training data. In our approach, an Adversarial Texture Augmentation Network (ATANet) first superimposes the texture of a degraded reference image over a clean image. Later, the clean image along with its generated degraded version constitute the pseudo paired-data which is used to train the Unsupervised Document Binarization Network (UDBNet). Following this approach, we have enlarged the document binarization datasets as it generates multiple images having same content feature but different textual feature. These generated noisy images are then fed into the UDBNet to get back the clean version. The joint discriminator which is the third-player of our three-player min-max adversarial game tries to couple both the ATANet and UDBNet. The three-player min-max adversarial game stops, when the distributions modelled by the ATANet and the UDBNet align to the same joint distribution over time. Thus, the joint discriminator enforces the UDBNet to perform better on real degraded image. The experimental results indicate the superior performance of the proposed model over existing state-of-the-art algorithm on widely used DIBCO datasets.

UDBNET: Unsupervised Document Binarization Network via Adversarial Game

In this work, we propose a long-term RGBD trackerthat achieves state-of-the-art performance on the PrincetonRGBD, STC and CDTB datasets and runs nearly real-time(20fps). The tracker is based on non-stationary formulation of the deep Discriminative Correlation Filter (DCF). The DCFfeature channels are modulated by the depth context in eachlocation which makes the tracker robust against occlusion andbackground clutter. Moreover, the non-stationary DCF also performs well in target re-detection enabling long-term tracking.

DAL: A Deep Depth-Aware Long-term Tracker


We present FourierNet, a single shot, anchor-free, fully convolutional instance segmentation method that predicts a shape vector. Consequently, this shape vector is converted into the masks’ contour points using a fast numerical transform. Compared to previous methods, we introduce a new training technique, where we utilize a differentiable shape decoder, which manages the automatic weight balancing of the shape vector’s coefficients. We used the Fourier series as a shape encoder because of its coefficient interpretability and fast implementation.
FourierNet shows promising results compared to polygon representation methods, achieving 30.6 mAP on the MS COCO 2017 benchmark. At lower image resolutions, it runs at 26.6 FPS with 24.3 mAP. It reaches 23.3 mAP using just eight parameters to represent the mask (note that at least four parameters are needed
for bounding box prediction only). Qualitative analysis shows that suppressing a reasonable proportion of higher frequencies of Fourier series, still generates meaningful masks. These results validate our understanding that lower frequency components hold higher information for the segmentation task, and therefore, we can achieve a compressed representation. Code is available at github.com/cogsys-tuebingen/FourierNet.

Premium content

Combining Deep and Ad-hoc Solutions to Localize Text Lines in Ancient Arabic Document Images

Downloads

Next from ICPR 2020

Semi-supervised Deep Learning Techniques for Spectrum Reconstruction

Similar lecture

CardioGAN: An Attention-based Generative Adversarial Network for Generation of Electrocardiograms