scispace - formally typeset
Search or ask a question
Author

Andrew C. Gallagher

Bio: Andrew C. Gallagher is an academic researcher from Google. The author has contributed to research in topics: Digital image & Pixel. The author has an hindex of 51, co-authored 250 publications receiving 8616 citations. Previous affiliations of Andrew C. Gallagher include Eastman Kodak Company & OmniVision Technologies.


Papers
More filters
Book ChapterDOI
07 Oct 2012
TL;DR: A fully automated system that is capable of generating a list of nameable attributes for clothes on human body in unconstrained images is proposed, and a novel application of dressing style analysis is introduced that utilizes the semantic attributes produced by the system.
Abstract: Describing clothing appearance with semantic attributes is an appealing technique for many important applications. In this paper, we propose a fully automated system that is capable of generating a list of nameable attributes for clothes on human body in unconstrained images. We extract low-level features in a pose-adaptive manner, and combine complementary features for learning attribute classifiers. Mutual dependencies between the attributes are then explored by a Conditional Random Field to further improve the predictions from independent classifiers. We validate the performance of our system on a challenging clothing attribute dataset, and introduce a novel application of dressing style analysis that utilizes the semantic attributes produced by our system.

432 citations

Proceedings ArticleDOI
20 Jun 2009
TL;DR: This paper introduced contextual features that encapsulate the group structure locally (for each person in the group), and globally (the overall structure of the group) to accomplish a variety of tasks, such as demographic recognition, calculating scene and camera parameters, and even event recognition.
Abstract: In many social settings, images of groups of people are captured The structure of this group provides meaningful context for reasoning about individuals in the group, and about the structure of the scene as a whole For example, men are more likely to stand on the edge of an image than women Instead of treating each face independently from all others, we introduce contextual features that encapsulate the group structure locally (for each person in the group) and globally (the overall structure of the group) This “social context” allows us to accomplish a variety of tasks, such as such as demographic recognition, calculating scene and camera parameters, and even event recognition We perform human studies to show this context aids recognition of demographic information in images of strangers

339 citations

Proceedings ArticleDOI
23 Jun 2008
TL;DR: This work analyzes the mutual information between pixel locations near the face and the identity of the person to learn a global clothing mask and introduces a publicly available consumer image collection where each individual is identified.
Abstract: Researches have verified that clothing provides information about the identity of the individual. To extract features from the clothing, the clothing region first must be localized or segmented in the image. At the same time, given multiple images of the same person wearing the same clothing, we expect to improve the effectiveness of clothing segmentation. Therefore, the identity recognition and clothing segmentation problems are inter-twined; a good solution for one aides in the solution for the other. We build on this idea by analyzing the mutual information between pixel locations near the face and the identity of the person to learn a global clothing mask. We segment the clothing region in each image using graph cuts based on a clothing model learned from one or multiple images believed to be the same person wearing the same clothing. We use facial features and clothing features to recognize individuals in other images. The results show that clothing segmentation provides a significant improvement in recognition accuracy for large image collections, and useful clothing masks are simultaneously produced. A further significant contribution is that we introduce a publicly available consumer image collection where each individual is identified. We hope this dataset allows the vision community to more easily compare results for tasks related to recognizing people in consumer image collections.

277 citations

Proceedings ArticleDOI
09 May 2005
TL;DR: A novel algorithm is introduced that can detect the presence of interpolation in images prior to compression as well as estimate the interpolation factor, which exploits a periodicity in the second derivative signal of interpolated images.
Abstract: A novel algorithm is introduced that can detect the presence of interpolation in images prior to compression as well as estimate the interpolation factor. The interpolation detection algorithm exploits a periodicity in the second derivative signal of interpolated images. The algorithm performs well for a wide variety of interpolation factors, both integer factors and non-integer factors. The algorithm performance is noted with respect to a digital camera's "digital zoom" feature. Overall the algorithm has demonstrated robust results and might prove to be useful for situations where an original resolution of the image determines the action of an image processing chain.

208 citations

Patent
15 Nov 2006
TL;DR: In this article, the provided capture records are clustered into groups based on capture locations and a map is segmented into a plurality of regions based on relative positions of the capture locations associated with each group.
Abstract: In methods and systems for classifying capture records, such as images. A collection of capture records is provided. Each capture record has metadata defining a map location. This metadata can be earlier determined from a stream of data transmissions, even if there are gaps in transmission. The provided capture records are clustered into groups based on capture locations. A map, inclusive of the capture locations, is segmented into a plurality of regions based on relative positions of the capture locations associated with each group. The regions are associated with the capture records of respective groups.

204 citations


Cited by
More filters
01 Jan 2006

3,012 citations

Journal ArticleDOI
TL;DR: In this paper, the authors offer a new book that enPDFd the perception of the visual world to read, which they call "Let's Read". But they do not discuss how to read it.
Abstract: Let's read! We will often find out this sentence everywhere. When still being a kid, mom used to order us to always read, so did the teacher. Some books are fully read in a week and we need the obligation to support reading. What about now? Do you still love reading? Is reading only for you who have obligation? Absolutely not! We here offer you a new book enPDFd the perception of the visual world to read.

2,250 citations

Patent
12 Nov 2013
TL;DR: In this paper, a variety of technologies by which existing functionality can be improved, and new functionality can also be provided, including visual search capabilities, and determining appropriate actions responsive to different image inputs.
Abstract: Cell phones and other portable devices are equipped with a variety of technologies by which existing functionality can be improved, and new functionality can be provided. Some relate to visual search capabilities, and determining appropriate actions responsive to different image inputs. Others relate to processing of image data. Still others concern metadata generation, processing, and representation. Yet others relate to coping with fixed focus limitations of cell phone cameras, e.g., in reading digital watermark data. Still others concern user interface improvements. A great number of other features and arrangements are also detailed.

2,033 citations

Proceedings ArticleDOI
27 Jun 2016
TL;DR: This work introduces DeepFashion1, a large-scale clothes dataset with comprehensive annotations, and proposes a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks.
Abstract: Recent advances in clothes recognition have been driven by the construction of clothes datasets. Existing datasets are limited in the amount of annotations and are difficult to cope with the various challenges in real-world applications. In this work, we introduce DeepFashion1, a large-scale clothes dataset with comprehensive annotations. It contains over 800,000 images, which are richly annotated with massive attributes, clothing landmarks, and correspondence of images taken under different scenarios including store, street snapshot, and consumer. Such rich annotations enable the development of powerful algorithms in clothes recognition and facilitating future researches. To demonstrate the advantages of DeepFashion, we propose a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks. The estimated landmarks are then employed to pool or gate the learned features. It is optimized in an iterative manner. Extensive experiments demonstrate the effectiveness of FashionNet and the usefulness of DeepFashion.

1,649 citations

Proceedings ArticleDOI
01 Sep 2009
TL;DR: Two novel methods for face verification using binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance and a new data set of real-world images of public figures acquired from the internet.
Abstract: We present two novel methods for face verification. Our first method - “attribute” classifiers - uses binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance (e.g., gender, race, and age). Our second method - “simile” classifiers - removes the manual labeling required for attribute classification and instead learns the similarity of faces, or regions of faces, to specific reference people. Neither method requires costly, often brittle, alignment between image pairs; yet, both methods produce compact visual descriptions, and work on real-world images. Furthermore, both the attribute and simile classifiers improve on the current state-of-the-art for the LFW data set, reducing the error rates compared to the current best by 23.92% and 26.34%, respectively, and 31.68% when combined. For further testing across pose, illumination, and expression, we introduce a new data set - termed PubFig - of real-world images of public figures (celebrities and politicians) acquired from the internet. This data set is both larger (60,000 images) and deeper (300 images per individual) than existing data sets of its kind. Finally, we present an evaluation of human performance.

1,619 citations