Adobe, Inc.

Seiko Epson Corporation

Guang Chen

Elya Shechtman

Hailin Jin

Jianchao Yang

Jonathan Worthen Brandt

Jing Xiao

Aseem Agarwala

Yuanyuan Ding

Example systems and methods for classifying visual patterns into a plurality of classes are presented. Using reference visual patterns of known classification, at least one image or visual pattern classifier is generated, which is then employed to classify a plurality of candidate visual patterns of unknown classification. The classification scheme employed may be hierarchical or nonhierarchical. The types of visual patterns may be fonts, human faces, or any other type of visual patterns or images subject to classification.

Generation of visual pattern classes for visual pattern recognition

A system may be configured as an image recognition machine that utilizes an image feature representation called local feature embedding (LFE). LFE enables generation of a feature vector that captures salient visual properties of an image to address both the fine-grained aspects and the coarse-grained aspects of recognizing a visual pattern depicted in the image. Configured to utilize image feature vectors with LFE, the system may implement a nearest class mean (NCM) classifier, as well as a scalable recognition algorithm with metric learning and max margin template selection. Accordingly, the system may be updated to accommodate new classes with very little added computational cost. This may have the effect of enabling the system to readily handle open-ended image classification problems.

Visual pattern recognition in an image

Aspects of the present invention comprise generating and using Multi-Order Contextual co-Occurrence (MOCO) descriptors to implicitly model the high level context using detection responses from a baseline object detector. In embodiments, a 1-order context feature is computed as a set of randomized binary comparisons on a response map of the baseline object detector. The statistics of the 1-order binary context features are further calculated to construct a higher-order co-occurrence descriptor, which, in embodiments, may be combined with other features such as the 0-order context features and/or the 1-order features to form the MOCO. In embodiments, combining the MOCO feature with the original image feature, the baseline object detector may be evolved to a stronger context aware detector.

Detector evolution with multi-order contextual co-occurrence

A hierarchy machine may be configured as a clustering machine that utilizes local feature embedding to organize visual patterns into nodes that each represent one or more visual patterns. These nodes may be arranged as a hierarchy in which a node may have a parent-child relationship with one or more other nodes. The hierarchy machine may implement a node splitting and tree-learning algorithm that includes hard-splitting of nodes and soft-assignment of nodes to perform error-bounded splitting of nodes into clusters. This may enable the hierarchy machine, which may form all or part of a visual pattern recognition system, to perform large-scale visual pattern recognition, such as font recognition or facial recognition, based on a learned error-bounded tree of visual patterns.

Generating a hierarchy of visual pattern classes

Aspects of the present invention include object detection training systems and methods and using object detection systems and methods that have been trained. Embodiments presented herein include hybrid learning approaches that combine global classification and local adaptations, which automatically adjust model complexity according to data distribution. Embodiments of the present invention automatically determine model complexity of the local learning algorithm according to the distribution of ambiguous samples. And, embodiments of the local adaptation from global classifier avoid the common under-training problem for local classifier.

Growing community of inventors

Columbia, MO, United States of America

Guang Chen