Goto

Collaborating Authors

Discriminative models for robust image classification

arXiv.org Machine Learning

A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant challenge. This dissertation explores the development of discriminative models for robust image classification that exploit underlying signal structure, via probabilistic graphical models and sparse signal representations. Probabilistic graphical models are widely used in many applications to approximate high-dimensional data in a reduced complexity set-up. Learning graphical structures to approximate probability distributions is an area of active research. Recent work has focused on learning graphs in a discriminative manner with the goal of minimizing classification error. In the first part of the dissertation, we develop a discriminative learning framework that exploits the complementary yet correlated information offered by multiple representations (or projections) of a given signal/image. Specifically, we propose a discriminative tree-based scheme for feature fusion by explicitly learning the conditional correlations among such multiple projections in an iterative manner. Experiments reveal the robustness of the resulting graphical model classifier to training insufficiency.


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.


Analysis Dictionary Learning: An Efficient and Discriminative Solution

arXiv.org Machine Learning

Yang et al. [7] used Fisher widely advocated for image classification problems. To further Information criterion in their class-specific reconstruction errors sharpen their discriminative capabilities, most state-ofthe-art to compose their approach. DL methods have additional constraints included in Besides SDL, Analysis Dictionary Learning (ADL) [8, 9] the learning stages. These various constraints, however, lead has recently been of interest on account of its fast encoding to additional computational complexity. We hence propose an and stability attributes. ADL provides a linear transformation efficient Discriminative Convolutional Analysis Dictionary of a signal to a nearly sparse representation. Inspired by Learning (DCADL) method, as a lower cost Discriminative the SDL methodology in image classification, ADL has also DL framework, to both characterize the image structures and been adapted to the supervised learning problems by promoting refine the interclass structure representations. The proposed discriminative sparse representations [10, 11]. In [10], DCADL jointly learns a convolutional analysis dictionary and Guo et al. incorporated both a topological structure and a representation a universal classifier, while greatly reducing the time complexity similarity constraint to encourage a suitable classselective in both training and testing phases, and achieving a representation for a 1-Nearest Neighbor classifier.


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.


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.