Study guide 3 Perceiving and Recognizing Objects What is middle vision Loosely defined stage of visual processing After basic features have been extracted from the image early vision up to including striate cortex Before object recognition and scene understanding high level vision Goal to organize elements of a visual scene into groups that we can then recognize as objects Why do you think the Gestalt school of thought was instrumental in identifying how we perceive images To answer this you need to know what Gestalt means Helped us understand how we group together objects Gestalt The whole is greater than the sum of parts Know the gestalt grouping principles good continuation occlusion texture segmentation similarity proximity connectedness common region how do those latter 2 relate to proximity what trumps what parallelism symmetry Also know dynamic occlusion Good continuation Gestalt grouping rule 2 lines will tend to group together if they seem to lie on the same contour Occlusion If an edge seems to stop the visual system guesses that it is stopping b c something else is in the way occluding it The illusory contour in a comes from 2 guesses The notches in the circles represent contours that can be extended and the vertical line stops at the top b c something is occluding it BTW the notches themselves are perceived as a place where 1 object is occluding another In c each black line generates illusory contour at right angles to endpoints d circle Texture segmentation carving an image into regions of common texture properties Texture grouping can be based on similar color size orientation and aspects of form Similarity chunks that are similar to each other are grouped together Here the similarity is based on the form Proximity items near each other are grouped together Figure looks striped Common region if 2 features appear to be part of the same common region they will group together 2 Connectedness if 2 items are connected they probably belong together 3 Connectedness and common region trump proximity Parallelism regions with parallel contours are more likely seen as figure Symmetry symmetrical region more likely the figure or vase in previous slide Dynamic occlusion when visual regions are discontinuous not only in space but over time How does color fit in to the gestalt grouping principles Color trumps good continuation as an organizing principle What is an ambiguous figure When 2 cognitive demons shout equally loudly This is the exception that proves the rule the rule being that usually there is consensus among the committees What is an accidental viewpoint A viewing position that produces some regularity in the visual image that is not present in the world like the sides of 2 independent objects lining up perfectly What is figure and ground and what principles do we use to decide which is which in a visual scene What is evidence that maybe object recognition precedes establishment of figure ground Figure ground assignment is the process of determining that some regions of an image belong to a foreground object figure and others are part of the background ground What is the global superiority effect Properties of the whole object take precedence over the properties of parts of the objects This is what middle vision does the 1st goal is to carve the retinal image into large scale objects Why do we probably not use templates to recognize objects We d need way too many What are geons Geons geometric ions What is recognition by components and what are some criticisms of Model objects are recognized by the identities relationships of component this approach parts Criticism are geons really adequate for object recognition View point invariant so we only need to store 1 template in memory Think cigar box versus book is there a difference in the geons needed Some things like letter recognition are view point dependent What about types of cars What about faces This will be a special case What is the pandemonium model and what concepts of visual processing does it illustrate Concepts of visual processing Modularity Feature demons lower vision primary visual cortex Cognitive demons middle vision Decision demon high level vision object recognition inferior temporal cortex Each only know what the previous one told it Perception by committee Multiple committees groups of neurons each looking for a particular pattern Parallelism committee good continuation committee proximity committee etc Parallel processing Each committee feature demon cognitive demon group of neurons is looking for its preferred stimulus at the same time Understand the different levels of categorization Under what circumstances do they change How does this support the possibility of multiple object recognition committees Superordinate level it s an animal Broader categorization Entry level category it s a bird 1st word that comes to mind Geon is possible Fastest recognition compared to super and subordinate Subordinate level it s cardinal More specific level of identification System needs to identify precise details Different brain activation compared to entry level recognition What is prosopagnosia Is facial recognition 2 steps or 2 committees ok we re not sure of this one So what s an argument for each Damage to the temporal lobe resulting in the inability to identify faces
View Full Document
Unlocking...