Abstract
This paper presents a uni?ed framework for object detection,
segmentation,and classi?cation using regions.Region
features are appealing in this context because: (1) theyen-
code shape and scale information of objects naturally; (2)
they are only mildly affected by background clutter.
Regions have not been popular as features due to their
sensitivity to segmentation errors.In this paper,we start by
producing a robust bag of overlaid regions for each image
using Arbelaez et al.,CVPR 2009.Each region is represented
by a rich set of image cues(shape,color and texture).
We then learn region weights using a max-margin
framework.In detection and segmentation,we apply a generalized
Hough voting scheme to generate hypotheses of object locations,
scales and support,followed by a veri?cation
classi?er and a constrained segmenter on each hypothesis.
The proposed approach signi?cantly outperforms the
state of the art on the ETHZ shape database(87:1% av-
erage detection rate compared to Ferrari et al.?s 67:2%),
and achieves competitive performance on the Caltech 101
database.
รบกวนที่นะครับผมแปลแล้วสับสนมากเลยเรียบเรียงไม่ถูก ขอบคุณล่วงหน้าครับ !แงๆ