Search

In this survey, kinship verification is defined as the automatic process of verifying whether two or more persons are blood relatives (kin) by analyzing images of their faces. Kinship verification is an important research field in computer vision with many applications such as finding missing persons, family album organization, and online image search. Although substantial progress has been made in kinship verification in the past decade, there are still challenges such as intrinsic (face i.e., differences in facial appearance) and extrinsic (acquisition i.e., varying imaging conditions) problems. And there is still a demand for more diverse datasets.Therefore, this paper provides a survey on kinship verification methods and datasets. The survey starts with the definition of kinship verification and its corresponding intrinsic and extrinsic challenges. Then, an overview of kinship verification methods and datasets is given. Finally, a new multi-modal dataset (Nemo-Kinship Dataset) is proposed as a benchmark dataset addressing large inter-subject age variations consisting of 4216 videos of 248 persons from 85 families. The newly collected dataset is used to systematically test and analyze state-of-the-art methods.

Introduction: The quality of scars has become an important outcome of burn care. Objective scar assessment through scar surface area measurement enables quantification of scar formation and evaluation of treatment efficacy. 3D technology has proven valid and reliable but often remains cumbersome, expensive, and time-consuming. 3D technology with depth sensors on mobile devices has become available and might surpass these limitations. This study provides a clinimetric assessment of the validity and reliability of a 3D system with a depth sensor for scar surface area measurement. Methods: A technology involving a depth sensor mounted on a mobile device was used. Images and analyses were made with a custom-made software application. A standardized one-keyframe image capturing procedure was followed. To assess validity, stickers with predefined dimensions (8.01 cm2 – 77.70 cm2) were imaged in a single observer setting on various body parts of healthy volunteers. To assess reliability, hypertrophic scars, keloids, and normotrophic scars were imaged and rated by two observers independently. Data are expressed as mean (+/-SD), Coefficient of Variation (CV), Intraclass Correlation Coefficients (ICC), and Limits of Agreements (LoA). Results: Eighty stickers placed on 20 healthy volunteers showed validity with CV between 0.62%− 1.67% for observer A and 0.75%− 1.19% for observer B. For the reliability study, 69 scars on 36 patients were included. Mean scar surface area ranged from 0.83 cm2 to 155.59 cm2. Mean scar surface area measurement was 13.83 cm2 (SD 23.06) for observer A and 13.59 cm2 (SD 23.31) for observer B. Adjusted interobserver CV for trained observers is estimated as 5.59%, with corresponding LoA = 0 ± 0.15 x mean surface area. Interobserver ICCs were 0.99–1.00. Conclusion: This 3D technology with a depth sensor for measuring scar surface area provides valid and reliable data and thereby surpasses expensive and time-consuming 3D cameras.

In this paper, we propose a method which jointly learns the layout prediction and depth estimation from a single indoor panorama image. Previous methods have considered layout prediction and depth estimation from a single panorama image separately. However, these two tasks are tightly intertwined. Leveraging the layout depth map as an intermediate representation, our proposed method outperforms existing methods for both panorama layout prediction and depth estimation. Experiments on the challenging real-world dataset of Stanford 2D–3D demonstrate that our approach obtains superior performance for both the layout prediction tasks (3D IoU: \(85.81\%\) v.s. \(79.79\%\)) and the depth estimation (Abs Rel: 0.068 v.s. 0.079).

Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point clouds into regular 3D voxel grids before they are used as input for ConvNets. Unfortunately, voxel representations are highly insensitive to the geometrical nature of 3D data. More recent methods encode point clouds to higher dimensional features to cover the global 3D space. However, these models are not able to sufficiently capture the local structures of point clouds. Therefore, in this paper, we propose a method that exploits both local and global contextual cues imposed by the k-d tree. The method is designed to learn representation vectors progressively along the tree structure. Experiments on challenging benchmarks show that the proposed model provides discriminative point set features. For the task of 3D scene semantic segmentation, our method significantly outperforms the state-of-the-art on the Stanford Large-Scale 3D Indoor Spaces Dataset (S3DIS).

Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known that albedo (reflectance) is invariant to all kinds of illumination effects. Thus, using reflectance images for semantic segmentation task can be favorable. Additionally, not only segmentation may benefit from reflectance, but also segmentation may be useful for reflectance computation. Therefore, in this paper, the tasks of semantic segmentation and intrinsic image decomposition are considered as a combined process by exploring their mutual relationship in a joint fashion. To that end, we propose a supervised end-to-end CNN architecture to jointly learn intrinsic image decomposition and semantic segmentation. We analyze the gains of addressing those two problems jointly. Moreover, new cascade CNN architectures for intrinsic-for-segmentation and segmentation-for-intrinsic are proposed as single tasks. Furthermore, a dataset of 35K synthetic images of natural environments is created with corresponding albedo and shading (intrinsics), as well as semantic labels (segmentation) assigned to each object/scene. The experiments show that joint learning of intrinsic image decomposition and semantic segmentation is beneficial for both tasks for natural scenes. Dataset and models are available at: https://ivi.fnwi.uva.nl/cv/intrinseg, ECCV 2018

BACKGROUND: Cyst infection may occur in autosomal dominant polycystic kidney disease (ADPKD) and autosomal dominant polycystic liver disease (ADPLD). Antimicrobial agents often fail to control infection, leading to invasive action. We aimed to identify factors predicting escalation of care. METHODS: ADPKD and ADPLD patients were identified from local/national databases (2001-2013). Records were screened for patients meeting criteria for cyst infection (positive cyst aspirate and/or clinical findings). Factors that predict escalated care were identified with multivariate modified Poisson regression. RESULTS: We screened 1773 patients. A total of 77 patients with cyst infection (4.3%) were included for analysis (hepatic 36%; male 49%; age 54 ±; 13 years; ADPKD 95%; dialysis 9%, diabetes 18%, renal transplant 56%, eGFR [IQR 24-78] ml/min/1.73 m2 (excluding patients with a history of renal transplant or receiving dialysis)). A pathogen was identified in 71% of cases. Escherichia coli was the most common pathogen and accounted for 69% of cases. Initial treatment was limited to antibiotics in 87% of patients (n = 67), 40% included a fluoroquinolone. Ultimately, 48% of patients underwent some form of invasive action (escalation of care). Increasing white blood cell count (WBC) (RR 1.04 95%-CI 1.01-1.07, p = 0.008) was associated with escalating care, whereas an increase in time between transplant and infection (RR 0.92 95% CI 0.86-0.97, p = 0.005) and E. coli isolation (RR 0.55 95% CI 0.34-0.89, p = 0.02) were protective. CONCLUSION: High serum WBC, isolation of atypical pathogens and early infection after transplantation are factors that increase the risk of escalation of care in hepatic and renal cyst infection patients.

Robots are increasingly present in modern industry and also in everyday life. Their applications range from health-related situations, for assistance to elderly people or in surgical operations, to automatic and driver-less vehicles (on wheels or flying) or for driving assistance. Recently, an interest towards robotics applied in agriculture and gardening has arisen, with applications to automatic seeding and cropping or to plant disease control, etc. Autonomous lawn mowers are succesful market applications of gardening robotics. In this paper, we present a novel robot that is developed within the TrimBot2020 project, funded by the EU H2020 program. The project aims at prototyping the first outdoor robot for automatic bush trimming and rose pruning., Accepted for publication at International Sympsium on Robotics 2018

Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to keep categorization accuracy intact and give the same numerical results.In the experiments on large scale datasets it is shown that, by using a parallel implementation on the GPU, quantization is 28 times faster and classification is 35 faster than a single-threaded CPU version, while giving the exact same numerical results. The GPU accelerations are applicable to both the learning phase and the testing phase of visual categorization systems. For software visit http://www.colordescriptors.com/ .

In this paper we combine a state of the art eye center locator and a new eye corner locator into a system which estimates the visual gaze of a user in a controlled environment (e.g. sitting in front of a screen). In order to reduce to a minimum the computational costs, the eye corner locator is built upon the same technology of the eye center locator, tweaked for the specific task. If high mapping precision is not a priority of the application, we claim that the system can achieve acceptable accuracy without the requirements of additional dedicated hardware. We believe that this could bring new gaze based methodologies for human-computer interactions into the mainstream.

Color constancy is the ability to measure image features independent of the color of the scene illuminant and is an important topic in color and computer vision. As many color constancy algorithms exist, different distance measures are used to compute their accuracy. In general, these distances measures are based on mathematical principles such as the angular error and Euclidean distance. However, it is unknown to what extent these distance measures correlate to human vision. Therefore, in this paper, a taxonomy of different distance measures for color constancy algorithms is presented. The main goal is to analyze the correlation between the observed quality of the output images and the different distance measures for illuminant estimates. The output images are the resulting color corrected images using the illuminant estimates of the color constancy algorithms, and the quality of these images is determined by human observers. Distance measures are analyzed how they mimic differences in color naturalness of images as obtained by humans. Based on the theoretical and experimental results on spectral and real-world data sets, it can be concluded that the perceptual Euclidean distance (PED) with weight-coefficients (w R = 0.26, w G = 0.70, w B = 0.04) finds its roots in human vision and correlates significantly higher than all other distance measures including the angular error and Euclidean distance.

The goal of color constancy is to measure image colors despite differences in the color of the light source. Traditionally, the computational method of obtaining this ability is by using pixel values only. Recently, methods using edges instead of pixel values have been proposed. However, different edge types exist, such as material, shadow and specular edges. Therefore, in this paper, the main goal is to analyze the influence of different edge types on the performance of edge-based color constancy. It is shown that, on generated data without color clipping, specular edges deliver near-perfect color constancy and that shadow edges are more valuable than material edges. However, with color clipping, the performance using the specular edges decreases significantly, while the performance using the material or shadow edges is less affected.

Computational color constancy aims to estimate the color of the light source. The performance of many vision tasks, such as object detection and scene understanding, may benefit from color constancy by estimating the correct object colors. Since traditional color constancy methods are based on specific assumptions, none of those methods can be used as a universal predictor. Further, shallow learning schemes are used for training-based color constancy approaches, suffering from limited learning capacity. In this paper, we propose a framework using Deep Neural Networks (DNNs) to obtain an accurate light source estimator to achieve color constancy. We formulate color constancy as a DNN-based regression approach to estimate the color of the light source. The model is trained using datasets of more than a million images. Experiments show that the proposed algorithm outperforms the state-of-the-art by 9\%. Especially in cross dataset validation, reducing the median angular error by 35\%. Further, in our implementation, the algorithm operates at more than $100$ fps during

In this paper we propose an approach for personalising the space in which a game is played (i.e., levels) dependent on classifications of the user’s facial expression - to the end of tailoring the affective game experience to the individual user. Our approach is aimed at online game personalisation, i.e., the game experience is personalised during actual play of the game. A key insight of this paper is that game personalisation techniques can leverage novel computer vision-based techniques to unobtrusively infer player experiences automatically based on facial expression analysis. Specifically, to the end of tailoring the affective game experience to the individual user, in this paper we (1) leverage the proven INSIGHT facial expression recognition SDK as a model of the user’s affective state (Sightcorp 2014), and (2) employ this model for guiding the online game personalisation process. User studies that validate the game personalisation approach in the actual video game INFINITE MARIO BROS. reveal that it provides an effective basis for converging to an appropriate affective state for the individual human player.

In this paper, we investigate and exploit the influence of facial expressions on automatic age estimation. Different from existing approaches, our method jointly learns the age and expression by introducing a new graphical model with a latent layer between the age/expression labels and the features. This layer aims to learn the relationship between the age and expression and captures the face changes which induce the aging and expression appearance, and thus obtaining expression-invariant age estimation. Conducted on two age-expression datasets (FACES and Lifespan), our experiments illustrate the improvement in performance when the age is jointly learnt with expression in comparison to expression-independent age estimation. The age estimation error is reduced by 14.43% and 37.75% for the FACES and Lifespan datasets respectively. Furthermore, the results obtained by our graphical model, without prior-knowledge of the expressions of the tested faces, are better that the best reported ones for both datasets.

Snakes provide high-level information in the form of continuity constraints and minimum energy constraints related to the contour shape and image features.In this paper, we aim at using color invariant gradient information, as image features, to guide the deformation process. We focus on using color snakes for interactive image segmentation for the purpose of contentbased image retrieval. The key idea is to select appropriate subimages of objects (instead of the entire image) on which the image object search will be conducted. After image segmentation, to achieve accurate image object search, weights are assigned to the image features of the selected subimages in accordance to their importance i.e. having high feature frequencies but low overall collection frequencies.Experiments show that the proposed color invariant snake successfully find object material contours discounting other “accidental” edges types (e.g. shadows, shading and highlight transitions). Furthermore, experiments show that object search using subimages with weighted features yield high retrieval accuracy. The object search scheme is at http://www.wins.uva.nl/research/isis/zomax/.

Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand---designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process. Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state---of---the---art methods using other sources of information such as depth, motion or stereo.

We propose to use text recognition to aid in visual object class recognition. To this end we first propose a new algorithm for text detection in natural images. The proposed text detection is based on saliency cues and a context fusion step. The algorithm does not need any parameter tuning and can deal with varying imaging conditions. We evaluate three different tasks: 1. Scene text recognition, where we increase the state-of-the-art by 0.17 on the ICDAR 2003 dataset. 2. Saliency based object recognition, where we outperform other state-of-the-art saliency methods for object recognition on the PASCAL VOC 2011 dataset. 3. Object recognition with the aid of recognized text, where we are the first to report multi-modal results on the IMET set. Results show that text helps for object class recognition if the text is not uniquely coupled to individual object instances.