Shahar Mahpod

Bio: Shahar Mahpod is an academic researcher from Bar-Ilan University. The author has contributed to research in topics: Deep learning & Facial recognition system. The author has an hindex of 4, co-authored 6 publications receiving 150 citations.

The FG 2015 Kinship Verification in the Wild Evaluation

Abstract: The aim of the Kinship Verification in the Wild Evaluation (held in conjunction with the 2015 IEEE International Conference on Automatic Face and Gesture Recognition, Ljubljana, Slovenia) was to evaluate different kinship verification algorithms. For this task, two datasets were made available and three possible experimental protocols (unsupervised, image-restricted, and image-unrestricted) were designed. Five institutions submitted their results to the evaluation: (i) Politecnico di Torino, Italy; (ii) LIRIS-University of Lyon, France; (iii) Universidad de Las Palmas de Gran Canaria, Spain; (iv) Nanjing University of Aeronautics and Astronautics, China; and (v) Bar Ilan University, Israel. Most of the participants tackled the image-restricted challenge and experimental results demonstrated better kinship verification performance than the baseline methods provided by the organizers.

Kin-Verification Model on FIW Dataset Using Multi-Set Learning and Local Features

Abstract: Kinship Verification of two or more people has shown to be a complicated problem, though it is widely used in various practical tasks and applications. The areas of the use-cases vary. Among them are applications for homeland security, automatic family recognition, youth and elder matching or predicting and more. We propose using Deep Learning approach to deal with the problem of Kin Verification, such to provide a logical explanation for solving the problem with a novel mechanism for training on the FIW data-set. Our method obtains state-of-the-art for the FIW challenge for the restricted-image setting11

Visual Kinship Recognition of Families in the Wild

Abstract: We present the largest database for visual kinship recognition, Families In the Wild (FIW), with over 13,000 family photos of 1,000 family trees with 4-to-38 members. It took only a small team to build FIW with efficient labeling tools and work-flow. To extend FIW, we further improved upon this process with a novel semi-automatic labeling scheme that used annotated faces and unlabeled text metadata to discover labels, which were then used, along with existing FIW data, for the proposed clustering algorithm that generated label proposals for all newly added data–both processes are shared and compared in depth, showing great savings in time and human input required. Essentially, the clustering algorithm proposed is semi-supervised and uses labeled data to produce more accurate clusters. We statistically compare FIW to related datasets, which unarguably shows enormous gains in overall size and amount of information encapsulated in the labels. We benchmark two tasks, kinship verification and family classification, at scales incomparably larger than ever before. Pre-trained CNN models fine-tuned on FIW outscores other conventional methods and achieved state-of-the art on the renowned KinWild datasets. We also measure human performance on kinship recognition and compare to a fine-tuned CNN.

Tri-Subject Kinship Verification: Understanding the Core of A Family

Abstract: One major challenge in computer vision is to go beyond the modeling of individual objects and to investigate the bi- (one-versus-one) or tri- (one-versus-two) relationship among multiple visual entities, answering such questions as whether a child in a photo belongs to given parents. The child-parents relationship plays a core role in a family and understanding such kin relationship would have fundamental impact on the behavior of an artificial intelligent agent working in the human world. In this work, we tackle the problem of one-versus-two (tri-subject) kinship verification and our contributions are three folds: 1) a novel relative symmetric bilinear model (RSBM) introduced to model the similarity between the child and the parents, by incorporating the prior knowledge that a child may resemble a particular parent more than the other; 2) a spatially voted method for feature selection, which jointly selects the most discriminative features for the child-parents pair, while taking local spatial information into account; 3) a large scale tri-subject kinship database characterized by over 1,000 child-parents families. Extensive experiments on KinFaceW, Family101 and our newly released kinship database show that the proposed method outperforms several previous state of the art methods, while could also be used to significantly boost the performance of one-versus-one kinship verification when the information about both parents are available.

Tri-Subject Kinship Verification: Understanding the Core of A Family

Abstract: One major challenge in computer vision is to go beyond the modeling of individual objects and to investigate the bi- (one-versus-one) or tri- (one-versus-two) relationship among multiple visual entities, answering such questions as whether a child in a photo belongs to the given parents. The child-parents relationship plays a core role in a family, and understanding such kin relationship would have a fundamental impact on the behavior of an artificial intelligent agent working in the human world. In this work, we tackle the problem of one-versus-two (tri-subject) kinship verification and our contributions are threefold: 1) a novel relative symmetric bilinear model (RSBM) is introduced to model the similarity between the child and the parents, by incorporating the prior knowledge that a child may resemble one particular parent more than the other; 2) a spatially voted method for feature selection, which jointly selects the most discriminative features for the child-parents pair, while taking local spatial information into account; and 3) a large-scale tri-subject kinship database characterized by over 1,000 child-parents families. Extensive experiments on KinFaceW, Family101, and our newly released kinship database show that the proposed method outperforms several previous state of the art methods, while could also be used to significantly boost the performance of one-versus-one kinship verification when the information about both parents are available.

Kinship Verification with Deep Convolutional Neural Networks.

Abstract: Kinship verification from facial images is an interesting and challenging problem. The current algorithms on this topic typically represent faces with multiple low-level features, followed by a shallow learning model. However, these general manual features cannot well discover information implied in facial images for kinship verification, and thus even current best algorithms are not satisfying. In this paper, we propose to extract high-level features for kinship verification based on deep convolutional neural networks. Our method is end-to-end, without complex pre-processing often used in traditional methods. The high-level features are produced from the neuron activations of the last hidden layer, and then fed into a soft-max classifier to verify the kinship of two persons. Considering the importance of facial key-points, we also extract keypoints-based features for kinship verification. Experimental results demonstrate that our proposed approach is very effective even with limited training samples, largely outperforming the state-of-the-art methods. On two most widely used kinship databases, our method achieves 5.2% and 10.1% improvements compared with the previous best one, respectively.

Kinship Verification on Families in the Wild with Marginalized Denoising Metric Learning

Abstract: With our Families In the Wild (FIW) dataset, which consists of labels 1, 000 families in over 12, 000 family photos, we benchmarked the largest kinship verification experiment to date. FIW, with its quality data and labels for full family trees found worldwide, more accurately is the true, global distribution of blood relatives with a total 378, 300 face pairs of 9 different relationship types. This gives support to tackle the problem with modern-day data-driven methods, which are imperative due to the complex nature of tasks involving visual kinship recognition– many hidden factors and less discrimination when considering face pairs of blood relatives. For this, we propose a denoising auto-encoder based robust metric learning (DML) framework and its marginalized version (mDML) to explicitly preserve the intrinsic structure of data and simultaneously endow the discriminative information into the learned features. Large-scale experiments show that our method outperforms other features and metric based approaches on each of the 9 relationship types.