کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
527341 869315 2015 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Optimizing the decomposition for multiple foreground cosegmentation
ترجمه فارسی عنوان
بهینه سازی تجزیه برای تقسیم چند پیش زمینه
کلمات کلیدی
تقسیم بندی پیش زمینه چندگانه، تقسیم تصویر چند طبقه، تقسیم شکل زمین، کشف شیء
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی


• We approach unsupervised MFC by decomposing it into three simple tasks.
• The decomposed tasks for MFC are segmentation, segment matching, and F/G assignment.
• Alternative optimization can be easily applied for solving the proposed framework.
• We obtain satisfactory performance for single and multiple foreground cosegmentation.

The goal of multiple foreground cosegmentation (MFC) is to extract a finite number of foreground objects from an input image collection, while only an unknown subset of such objects is presented in each image. In this paper, we propose a novel unsupervised framework for decomposing MFC into three distinct yet mutually related tasks: image segmentation, segment matching, and figure/ground (F/G) assignment. By our decomposition, image segments sharing similar visual appearances will be identified as foreground objects (or their parts), and these segments will be also separated from background regions. To relate the decomposed outputs for discovering high-level object information, we construct foreground object hypotheses, which allows us to determine the foreground objects in each individual image without any user interaction, the use of pre-trained classifiers, or the prior knowledge of foreground object numbers. In our experiments, we first evaluate our proposed decomposition approach on the iCoseg dataset for single foreground cosegmentation. Empirical results on the FlickrMFC dataset will further verify the effectiveness of our approach for MFC problems.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computer Vision and Image Understanding - Volume 141, December 2015, Pages 18–27
نویسندگان
, ,