Publication Type

Journal Article

Version

acceptedVersion

Publication Date

11-2014

Abstract

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted labels as handles, our system empowers a user to verbally refine the results. This enables hands-free parsing of an image into pixel-wise object/attribute labels that correspond to human semantics. Verbally selecting objects of interest enables a novel and natural interaction modality that can possibly be used to interact with new generation devices (e.g., smartphones, Google Glass, livingroom devices). We demonstrate our system on a large number of real-world images with varying complexity. To help understand the trade-offs compared to traditional mouse-based interactions, results are reported for both a large-scale quantitative evaluation and a user study.

Keywords

Design, Human Factors, Languages, Image parsing, natural language control, speech interface, object class segmentation, image parsing, visual attributes, multilabel CRF

Discipline

Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

ACM Transactions on Graphics

Volume

34

Issue

1

First Page

1

Last Page

10

ISSN

0730-0301

Identifier

10.1145/2682628

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/2682628

Download

Share

COinS