کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
531831 869876 2016 15 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Fine-structured object segmentation via neighborhood propagation
ترجمه فارسی عنوان
تقسیم بندی دقیق ساختار شیء از طریق انتشار محله
کلمات کلیدی
تقسیم بندی دقیق ساختار شی، پخش برچسب، نمودار وابستگی، محله محلی و غیر محلی، هزینه منطقه
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی


• We propose a method for fine-structured object segmentation via label propagation.
• A novel affinity graph combining local and nonlocal connections is constructed.
• We incorporate appearance models as labeling preference for the label propagation.
• The energy minimization is achieved with a globally optimal closed-form solution.
• Extensive experimental results demonstrate the effectiveness of our method.

This paper presents a novel method for the challenging task of fine-structured (FS) object segmentation. The task is formulated as a label propagation problem on an affinity graph. The proposed method has mainly three advantages. First, to enhance the completeness and connectivity of FS objects, we introduce a novel neighborhood system combining both local and nonlocal connections, with a robust scheme for edge weight calculation. Second, appearance models are explicitly incorporated into the energy function as a term of region cost. This helps to further preserve the connectivity of the fine parts for which the label information is hard to propagate correctly via neighboring pixels alone. Third, the resulting energy minimization problem has a closed-form solution with global optimum guaranteed, showing an advantage over the FS object segmentation methods that suffer from NP-hardness. To enrich the evaluation of FS object segmentation methods, we created a new challenging data set. It consists of 100 natural images involving diverse FS objects, with accurately hand-labeled ground truth. Extensive experimental results demonstrate that our method is effective in handling FS objects and achieves the state-of-the-art performance.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 60, December 2016, Pages 130–144
نویسندگان
, , ,