Class-Specific, Top-Down Segmentation
نویسندگان
چکیده
In this paper we present a novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images). The approach is different from bottom-up segmentation methods that primarily use the continuity of grey-level, texture, and bounding contours. We show that the method leads to markedly improved segmentation results and can deal with significant variation in shape and varying backgrounds. We discuss the relative merits of class-specific and general image-based segmentation methods and suggest how they can be usefully combined.
منابع مشابه
Shape Based Detection Using Image Segments
We introduce a segmentation-based detection and top-down figure-ground delineation algorithm. Unlike common methods which use appearance for detection, our method relies primarily on the shape of objects as is reflected by their bottom-up segmentation. Our algorithm receives as input an image, along with its bottom-up hierarchical segmentation. The shape of each segment is then described both b...
متن کاملShape Sharing for Object Segmentation
We introduce a category-independent shape prior for object segmentation. Existing shape priors assume class-specific knowledge, and thus are restricted to cases where the object class is known in advance. The main insight of our approach is that shapes are often shared between objects of different categories. To exploit this “shape sharing” phenomenon, we develop a non-parametric prior that tra...
متن کاملSegmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation (pre-print)
The Segmentation According to Natural Examples (SANE) algorithm learns to segment objects in static images from video training data. SANE uses background subtraction to find the segmentation of moving objects in videos. This provides object segmentation information for each video frame. The collection of frames and segmentations forms a training set that SANE uses to learn the image and shape p...
متن کاملOn distances, paths and connections for hyperspectral image segmentation
The present paper introduces the η and μ connections in order to add regional information on λ-flat zones, which only take into account a local information. A top-down approach is considered. First λ-flat zones are built in a way leading to a sub-segmentation. Then a finer segmentation is obtained by computing η-bounded regions and μ-geodesic balls inside the λ-flat zones. The proposed algorith...
متن کاملAlternating Regular Tree Grammars in the Framework of Lattice-Valued Logic
In this paper, two different ways of introducing alternation for lattice-valued (referred to as {L}valued) regular tree grammars and {L}valued top-down tree automata are compared. One is the way which defines the alternating regular tree grammar, i.e., alternation is governed by the non-terminals of the grammar and the other is the way which combines state with alternation. The first way is ta...
متن کامل