Face recognition and OCR processing of 300 million records from US yearbooks

#artificialintelligence

A yearbook is a type of a book published annually to record, highlight, and commemorate the past year of a school. Our team at MyHeritage took on a complex project: extracting individual pictures, names, and ages from hundreds of thousands of yearbooks, structuring the data, and creating a searchable index that covers the majority of US schools between the years 1890–1979 -- more than 290 million individuals. In this article I'll describe what problems we encountered during this project and how we solved them. First of all, let me explain why we needed to tackle this challenge. MyHeritage is a genealogy platform that provides access to almost 10 billion historical records.


A Computational Model for Cursive Handwriting Based on the Minimization Principle

Neural Information Processing Systems

We propose a trajectory planning and control theory for continuous movements such as connected cursive handwriting and continuous natural speech. Its hardware is based on our previously proposed forward-inverse-relaxation neural network (Wada & Kawato, 1993). Computationally, its optimization principle is the minimum torquechange criterion.Regarding the representation level, hard constraints satisfied by a trajectory are represented as a set of via-points extracted from a handwritten character. Accordingly, we propose a via-point estimation algorithm that estimates via-points by repeating the trajectory formation of a character and the via-point extraction from the character. In experiments, good quantitative agreement is found between human handwriting data and the trajectories generated by the theory. Finally, we propose a recognition schema based on the movement generation. We show a result in which the recognition schema is applied to the handwritten character recognition and can be extended to the phoneme timing estimation of natural speech. 1 INTRODUCTION In reaching movements, trajectory formation is an ill-posed problem because the hand can move along an infinite number of possible trajectories from the starting to the target point.


Like by smiling? Facebook acquires emotion detection startup FacioMetrics

#artificialintelligence

Facebook could one day build facial gesture controls for its app thanks to the acquisition of a Carnegie Mellon University spinoff company called FacioMetrics. The startup made an app called Intraface that could detect seven different emotions in people's faces, but it's been removed from the app stores. The acquisition aligns with a surprising nugget of information Facebook slipped into a 32-bullet point briefing sent to TechCrunch this month. "Future applications of deep learning platform on mobile: Gesture-based controls, recognize facial expressions and perform related actions" It's not hard to imagine Facebook one day employing FacioMetrics' tech and its own AI to let you add a Like or one of its Wow/Haha/Angry/Sad emoji reactions by showing that emotion with your face. "How people share and communicate is changing and things like masks and other effects allow people to express themselves in fun and creative ways.


A polynomial-time relaxation of the Gromov-Hausdorff distance

arXiv.org Machine Learning

The Gromov-Hausdorff distance provides a metric on the set of isometry classes of compact metric spaces. Unfortunately, computing this metric directly is believed to be computationally intractable. Motivated by applications in shape matching and point-cloud comparison, we study a semidefinite programming relaxation of the Gromov-Hausdorff metric. This relaxation can be computed in polynomial time, and somewhat surprisingly is itself a pseudometric. We describe the induced topology on the set of compact metric spaces. Finally, we demonstrate the numerical performance of various algorithms for computing the relaxed distance and apply these algorithms to several relevant data sets. In particular we propose a greedy algorithm for finding the best correspondence between finite metric spaces that can handle hundreds of points.


Euler Sparse Representation for Image Classification

AAAI Conferences

Sparse representation based classification (SRC) has gained great success in image recognition. Motivated by the fact that kernel trick can capture the nonlinear similarity of features, which may help improve the separability and margin between nearby data points, we propose Euler SRC for image classification, which is essentially the SRC with Euler sparse representation. To be specific, it first maps the images into the complex space by Euler representation, which has a negligible effect for outliers and illumination, and then performs complex SRC with Euler representation. The major advantage of our method is that Euler representation is explicit with no increase of the image space dimensionality, thereby enabling this technique to be easily deployed in real applications. To solve Euler SRC, we present an efficient algorithm, which is fast and has good convergence. Extensive experimental results illustrate that Euler SRC outperforms traditional SRC and achieves better performance for image classification.