Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567494070> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W1567494070 abstract "Efficient coding by scene segmentation Lee & Yuille Efficient coding of visual scenes by grouping and segmentation: theoretical predictions and biological evidence Tai Sing Lee & Alan L. Yuille Introduction The goal of this chapter is to present computational theories of scene coding by image segmentation and to suggest their relevance for understanding visual cortical function and mechanisms. We will first introduce computational theories of image and scene segmentation and show their relationship to efficient encoding. Then we discuss and evaluate the rel- evant physiological data in the context of these computational frameworks. It is hoped that this will stimulate quantitative neurophysiological investigations of scene segmentation guided by computational theories. Our central conjecture is that areas V1 and V2, in addition to encoding fine details of images in terms of filter responses, compute a segmentation of images which allow a more compact and parsimonious encoding of images in terms of the properties of regions and surfaces in the visual scene. This conjecture is based on the observation that neurons and their retinotopic arrangement in these visual areas can represent information precisely, thus furnishing an appropriate computational and representational infrastructure for this task. Segmentation detects and extracts coherent regions in an image and then encode the image in terms of probabilistic models of surfaces and regions in it, in the spirit of Shannon’s theory of information. This representation facilitates visual reasoning at the level of regions and their boundaries, without worrying too much about all the small details in the image. Figure 1 gives three examples which illustrate the meaning of higher level efficient encoding of scenes. Firstly, consider Kanizsa’s (1979) famous illusory triangle (Figure 1a). It is simpler to explain it as a white triangle in front of, and partially occluding, three black circular discs rather than as three pac-mens which are accidentally aligned to each other. Indeed this simple explanation is what human perceive and, in fact, the perception of a triangle is so strong that we hallucinate the surface of the triangle as being brighter than the background and perceive sharp boundaries to the triangle even at places where there is no direct visual cues. Secondly, when confronted with the image shown in Figure 1b (Ramachandran 1988), we perceive it as a group of convex spheres mixed together with a group of concave indentations (e.g. an egg carton partly filled with eggs). This interpretation is more parsimonious than describing every detail of the intensity shading and other image features. Thirdly, at first glance, the image in Figure 1c (Gregory 1970) appears to be a collection of random dots and hence would not have a simple encoding. But the encoding becomes greatly simplified once the viewer perceives the Dalmation dog and can invoke a dog model. The viewer will latch on to this interpretation whenever he sees it again, underscoring the powerful interaction between memory and perception when generating an efficient perceptual description. These three examples suggest that we can achieve a tremendous amount of data compression by interpreting images in terms of the structure of the scene. They suggest a succession of increasingly more compact and semantically more meaningful codes as we move up the visual hierarchy. These codes go beyond efficient coding of images based on Gabor wavelet responses (Daugman 1985, Lee 1996) or independent components (Olshausen and Field 1996, Bell and Sejnowski 1997, Lewicki and Olshausen 1999). In this chapter, we will concentrate on image segmentation which is the process that partitions an image into regions, producing a clear delineation of the boundaries between regions and the labelling of properties of the regions. The definition of “regions” is a flexible one. In this chapter, we focus on early visual processing and so a region is defined to be part of an image that is characterized by a set of (approximately) homogeneous visual cues, such as color, luminance, or texture. These regions can correspond to 3D surfaces in the visual scene, or they can be parts of a 3D surface defined by (approximately) constant texture, albedo, or color (e.g. the red letters “No Parking” on a white stop sign). Based on a single image, however, it is often difficult to distinguish between these two interpretations. At a higher level of vision, the definition of region is more complex and can involve hierarchical structures involving objects and scene structures. The approach we have taken stems from the following computational perspective about the function of the visual system. We hold it to be self-evident that the purpose of the visual system is to interpret input images in terms of objects MIT Press Page" @default.
- W1567494070 created "2016-06-24" @default.
- W1567494070 creator A5007833782 @default.
- W1567494070 creator A5086706224 @default.
- W1567494070 date "2006-09-13" @default.
- W1567494070 modified "2023-09-23" @default.
- W1567494070 title "Efficient Coding of Visual Scenes by Grouping and Segmentation: Theoretical Predictions and Biological Evidence" @default.
- W1567494070 hasPublicationYear "2006" @default.
- W1567494070 type Work @default.
- W1567494070 sameAs 1567494070 @default.
- W1567494070 citedByCount "0" @default.
- W1567494070 crossrefType "journal-article" @default.
- W1567494070 hasAuthorship W1567494070A5007833782 @default.
- W1567494070 hasAuthorship W1567494070A5086706224 @default.
- W1567494070 hasConcept C104317684 @default.
- W1567494070 hasConcept C105795698 @default.
- W1567494070 hasConcept C124504099 @default.
- W1567494070 hasConcept C125411270 @default.
- W1567494070 hasConcept C153180895 @default.
- W1567494070 hasConcept C154945302 @default.
- W1567494070 hasConcept C166957645 @default.
- W1567494070 hasConcept C179518139 @default.
- W1567494070 hasConcept C185592680 @default.
- W1567494070 hasConcept C205649164 @default.
- W1567494070 hasConcept C25694479 @default.
- W1567494070 hasConcept C2779343474 @default.
- W1567494070 hasConcept C31972630 @default.
- W1567494070 hasConcept C33923547 @default.
- W1567494070 hasConcept C41008148 @default.
- W1567494070 hasConcept C55493867 @default.
- W1567494070 hasConcept C65885262 @default.
- W1567494070 hasConcept C66024118 @default.
- W1567494070 hasConcept C66746571 @default.
- W1567494070 hasConcept C89600930 @default.
- W1567494070 hasConceptScore W1567494070C104317684 @default.
- W1567494070 hasConceptScore W1567494070C105795698 @default.
- W1567494070 hasConceptScore W1567494070C124504099 @default.
- W1567494070 hasConceptScore W1567494070C125411270 @default.
- W1567494070 hasConceptScore W1567494070C153180895 @default.
- W1567494070 hasConceptScore W1567494070C154945302 @default.
- W1567494070 hasConceptScore W1567494070C166957645 @default.
- W1567494070 hasConceptScore W1567494070C179518139 @default.
- W1567494070 hasConceptScore W1567494070C185592680 @default.
- W1567494070 hasConceptScore W1567494070C205649164 @default.
- W1567494070 hasConceptScore W1567494070C25694479 @default.
- W1567494070 hasConceptScore W1567494070C2779343474 @default.
- W1567494070 hasConceptScore W1567494070C31972630 @default.
- W1567494070 hasConceptScore W1567494070C33923547 @default.
- W1567494070 hasConceptScore W1567494070C41008148 @default.
- W1567494070 hasConceptScore W1567494070C55493867 @default.
- W1567494070 hasConceptScore W1567494070C65885262 @default.
- W1567494070 hasConceptScore W1567494070C66024118 @default.
- W1567494070 hasConceptScore W1567494070C66746571 @default.
- W1567494070 hasConceptScore W1567494070C89600930 @default.
- W1567494070 hasLocation W15674940701 @default.
- W1567494070 hasOpenAccess W1567494070 @default.
- W1567494070 hasPrimaryLocation W15674940701 @default.
- W1567494070 hasRelatedWork W1583213685 @default.
- W1567494070 hasRelatedWork W1760883005 @default.
- W1567494070 hasRelatedWork W1915578113 @default.
- W1567494070 hasRelatedWork W2001501551 @default.
- W1567494070 hasRelatedWork W2007015305 @default.
- W1567494070 hasRelatedWork W2015432129 @default.
- W1567494070 hasRelatedWork W2016320043 @default.
- W1567494070 hasRelatedWork W2072151643 @default.
- W1567494070 hasRelatedWork W2075512223 @default.
- W1567494070 hasRelatedWork W2082678547 @default.
- W1567494070 hasRelatedWork W2091554265 @default.
- W1567494070 hasRelatedWork W2151129784 @default.
- W1567494070 hasRelatedWork W2156406284 @default.
- W1567494070 hasRelatedWork W2171408098 @default.
- W1567494070 hasRelatedWork W2467617196 @default.
- W1567494070 hasRelatedWork W24875704 @default.
- W1567494070 hasRelatedWork W2592691755 @default.
- W1567494070 hasRelatedWork W2613176026 @default.
- W1567494070 hasRelatedWork W3001970002 @default.
- W1567494070 hasRelatedWork W2188781866 @default.
- W1567494070 isParatext "false" @default.
- W1567494070 isRetracted "false" @default.
- W1567494070 magId "1567494070" @default.
- W1567494070 workType "article" @default.