Abstract: This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.
The papers are organized into the following topical sections: historical document analysis, document analysis systems, handwriting recognition, scene text detection and recognition, document image processing, natural language processing (NLP) for document understanding, and graphics, diagram and math recognition.

Abstract: In this PhD we have approached the human color vision from two different points of view: psychophysics and computational modeling. First, we have evaluated 15 different tone-mapping operators (TMOs). We have conducted two experiments that
consider two different criteria: the first one evaluates the local relationships among intensity levels and the second one evaluates the global appearance of the tonemapped imagesw.r.t. the physical one (presented side by side). We conclude that the rankings depend on the criterion and they are not correlated. Considering both criteria, the best TMOs are KimKautz (Kim and Kautz, 2008) and Krawczyk (Krawczyk, Myszkowski, and Seidel, 2005). Another conclusion is that a more standardized evaluation criteria is needed to do a fair comparison among TMOs.
Secondly, we have conducted several psychophysical experiments to study the
color induction. We have studied two different properties of the visual stimuli: temporal frequency and luminance spatial distribution. To study the temporal frequency we defined equiluminant stimuli composed by both uniform and striped surrounds and we flashed them varying the flash duration. For uniform surrounds, the results show that color induction depends on both the flash duration and inducer’s chromaticity. As expected, in all chromatic conditions color contrast was induced. In contrast, for striped surrounds, we expected to induce color assimilation, but we observed color contrast or no induction. Since similar but not equiluminant striped stimuli induce color assimilation, we concluded that luminance differences could be a key factor to induce color assimilation. Thus, in a subsequent study, we have studied the luminance differences’ effect on color assimilation. We varied the luminance difference between the target region and its inducers and we observed that color assimilation depends on both this difference and the inducer’s chromaticity. For red-green condition (where the first inducer is red and the second one is green), color assimilation occurs in almost all luminance conditions.
Instead, for green-red condition, color assimilation never occurs. Purple-lime
and lime-purple chromatic conditions show that luminance difference is a key factor to induce color assimilation. When the target is darker than its surround, color assimilation is stronger in purple-lime, while when the target is brighter, color assimilation is stronger in lime-purple (’mirroring’ effect). Moreover, we evaluated whether color assimilation is due to luminance or brightness differences. Similarly to equiluminance condition, when the stimuli are equibrightness no color assimilation is induced. Our results support the hypothesis that mutual-inhibition plays a major role in color perception, or at least in color induction.
Finally, we have defined a new firing rate model of color processing in the V1
parvocellular pathway. We have modeled two different layers of this cortical area: layers 4Cb and 2/3. Our model is a recurrent dynamic computational model that considers both excitatory and inhibitory cells and their lateral connections. Moreover, it considers the existent laminar differences and the cells’ variety. Thus, we have modeled both single- and double-opponent simple cells and complex cells, which are a pool of double-opponent simple cells. A set of sinusoidal drifting gratings have been used to test the architecture. In these gratings we have varied several spatial properties such as temporal and spatial frequencies, grating’s area and orientation. To reproduce the electrophysiological observations, the architecture has to consider the existence of non-oriented double-opponent cells in layer 4Cb and the lack of lateral connections between single-opponent cells. Moreover, we have tested our lateral connections simulating the center-surround modulation and we have reproduced physiological measurements where for high contrast stimulus, the
result of the lateral connections is inhibitory, while it is facilitatory for low contrast stimulus.

Abstract: 3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV.
Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol.
After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging
virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>.
Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect.

Abstract: Anticipating the intentions of vulnerable road users (VRUs) such as pedestrians
and cyclists can be critical for performing safe and comfortable driving maneuvers. This is the case for human driving and, therefore, should be taken into account by systems providing any level of driving assistance, i.e. from advanced driver assistant systems (ADAS) to fully autonomous vehicles (AVs). In this PhD work, we show how the latest advances on monocular vision-based human pose estimation, i.e. those relying on deep Convolutional Neural Networks (CNNs), enable to recognize the intentions of such VRUs. In the case of cyclists, we assume that they follow the established traffic codes to indicate future left/right turns and stop maneuvers with arm signals. In the case of pedestrians, no indications can be assumed a priori. Instead, we hypothesize that the walking pattern of a pedestrian can allow us to determine if he/she has the intention of crossing the road in the path of the egovehicle, so that the ego-vehicle must maneuver accordingly (e.g. slowing down or stopping). In this PhD work, we show how the same methodology can be used for recognizing pedestrians and cyclists’ intentions. For pedestrians, we perform experiments on the publicly available Daimler and JAAD datasets. For cyclists, we did not found an analogous dataset, therefore, we created our own one by acquiring
and annotating corresponding video-sequences which we aim to share with the
research community. Overall, the proposed pipeline provides new state-of-the-art results on the intention recognition of VRUs.

Abstract: Image registration has been for many years the gold standard method to bring two images into correspondence. It has been used extensively in the eld of medical imaging in order to put images of dierent patients into a common overlapping spatial position. However, medical image registration is a slow, iterative optimization process, where many variables and prone to fall into the pit traps local minima.
A coordinate system parameterizing the interior of organs is a powerful tool for a systematic localization of injured tissue. If the same coordinate values are assigned to specic anatomical sites, parameterizations ensure integration of data across different medical image modalities. Harmonic mappings have been used to produce parametric meshes over the surface of anatomical shapes, given their ability to set values at specic locations through boundary conditions. However, most of the existing implementations in medical imaging restrict to either anatomical surfaces, or the depth coordinate with boundary conditions is given at discrete sites of limited geometric diversity.
The medial surface of the shape can be used to provide a continuous basis for the denition of a depth coordinate. However, given that dierent methods for generation of medial surfaces generate dierent manifolds, not all of them are equally suited to be the basis of radial coordinate for a parameterization. It would be desirable that the medial surface will be smooth, and robust to surface shape noise, with low number of spurious branches or surfaces.
In this thesis we present methods for computation of smooth medial manifolds and apply them to the generation of for anatomical volumetric parameterization that extends current harmonic parameterizations to the interior anatomy using information provided by the volume medial surface. This reference system sets a solid base for creating anatomical models of the anatomical shapes, and allows comparing several patients in a common framework of reference.

Abstract: Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.
Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.
Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.

Abstract: Text is the most common way of information sharing from ages. With recent development of personal images databases and handwritten historic manuscripts the demand for algorithms to make these databases accessible for browsing and indexing are in rise. Enabling search or understanding large collection of manuscripts or image databases needs fast and robust methods. Researchers have found different ways to represent cropped words for understanding and matching, which works well when words are already segmented. However there is no trivial way to extend these for non-segmented documents. In this thesis we explore different methods for text retrieval and recognition from unsegmented document and scene images. Two different ways of representation exist in literature, one uses a fixed length representation learned from cropped words and another a sequence of features of variable length. Throughout this thesis, we have studied both these representation for their suitability in segmentation free understanding of text. In the first part we are focused on segmentation free word spotting using a fixed length representation. We extended the use of the successful PHOC (Pyramidal Histogram of Character) representation to segmentation free retrieval. In the second part of the thesis, we explore sequence based features and finally, we propose a unified solution where the same framework can generate both kind of representations.