Chapter 4: Perceiving and Recognizing Objects

StudyBlue printing of Chapter 4: Perceiving and Recognizing Objects html, body, div, span, applet, object, iframe, h1, h2, h3, h4, h5, h6, p, blockquote, pre, a, abbr, acronym, address, big, cite, code, del, dfn, em, font, img, ins, kbd, q, s, samp, small, strike, strong, sub, sup, tt, var, b, u, i, center, fieldset, form, label, legend, table, caption, tbody, tfoot, thead, tr, th, td { margin: 0; padding: 0; border: 0; outline: 0; font-size: 100%; background: transparent; } body { line-height: 1; } blockquote, q { quotes: none; } blockquote:before, blockquote:after, q:before, q:after { content: ''; content: none; } /* remember to define focus styles! */ :focus { outline: 0; } /* remember to highlight inserts somehow! */ ins { text-decoration: none; } del { text-decoration: line-through; } /* tables still need 'cellspacing="0"' in the markup */ table { border-collapse: collapse; border-spacing: 0; } /* end RESET */ .header { min-width:800px; } .logo { padding:6px 20px 2px 20px; margin:0; font-size:25px; font-weight:bold; color:#808285; position:relative; border-bottom: 1px solid #c5c5c5; } .logo-blue { color:#70adc4; } .logo-desc { font-weight:normal; font-size:19px; color:#cccccc; margin-top:50px; position:absolute; display: none; } .back-button { position:absolute; top:20px; right:20px; font-size:13px; line-height:25px; color:rgb(0,175,225); font-weight:normal; } .back-button a { color:rgb(0,175,225); } .instructions { padding:0; margin:0; width:100%; position:relative; color:rgb(100,100,100); } .step-holder { border-left:1px solid #ededed; margin-left:20px; } .steps { padding:15px 0; float:left; width:24%; border-right:1px solid #ededed; text-align:center; } .steps-01 { } .steps-02 { } .steps-03 { } .steps-04 { } .label { padding:5px 10px; } .print-button { } .print-button a { background-color:rgb(0,175,225); color:white; line-height: 19px; padding:9px 8px 5px 30px; font-size:14px; text-decoration:none; background-image: url(images/printer.png); background-repeat: no-repeat; background-position: 7px 50%; -moz-border-radius: 5px; -webkit-border-radius: 5px; } .print-button a:hover { background-color:black; } .theNote .content { width: 8.0in !important; margin: 5px auto; padding:20px; background-color:white; } .theNote .header { border-bottom: 1px dashed #C8C8C8; font-size: 17px; padding: 0 0 10px; line-height: 19px; color: #00ADE1; min-width:500px; } .theNote .body { font-size: 14px; line-height: 19px; padding: 10px 0; } .theNote{ padding:6px 0; clear:both; background-color: rgb(200,200,200); } .theNote h3{ color: rgb(100,100,100); } .theNote h1, .theNote h3{ background-color:white; padding:2px 20px; width:8.0in !important; margin: 0 auto; font-size: 15px; } .theNote h1{ padding-top: 10px; font-size: 15px; } .theNote h1:first-child{ font-size: 20px; } .theNote h3 { font-size: 14px; font-weight: normal; } #options { border: 3px double #ccc; padding: 5px 12px; margin: 10px 50px 10px 20px; float: left; } #info { border-top: 1px solid #ccc; padding-top: 5px; font-style: italic; } li { margin: 5px 10px 5px 25px; } ul li { list-style: disc; } ol li { list-style: decimal; } img { border: 0; } table { clear: both; width: 100%; border: 1px solid #c5c5c5; border-width: 1px 0; margin: 0; page-break-after: always; } table#page { page-break-after: auto; } td { text-align: center; font-size: 12px; border-bottom: 1px dashed #c5c5c5; height: 1.75in; width: 50%; padding-left: 15px; } .leftside { border-right: 1px solid #cccccc; padding: 0 15px 0 0; } .bottom td { border-bottom: none; } .clearfix { clear:both; line-height:1px; height:1px; } img { max-width:80%; max-height:150px; margin:20px; } @media print {.header { display: none; } .content .header{ display:inherit; } table { border: 1px dashed #bbb; border-width: 1px 0; } .theNote{ background-color:white; } } Chapter 4: Perceiving and Recognizing Objects We must have processes that successfully combine features into objects This is one of the tasks that defines middle vision middle vision is a loosely defined stage of visual processing that comes after basic features have been extracted from the image (early vision) and before object recognition and scene understanding (high level vision) Middle Vision the goal of middle vision is to organize the elements of a visual scene into groups that we can then recognize as objects finding the edges of te object is a good starting place an illusory contour is an edge or contour that is perceived, even though nothing changes from one side of the edge to the other in the image this tendency of the visual system to go beyond the information given was problematic for one of the earliest groups of perceptual psychologists, the structuralists structuralism was a school of thought believing that complex objects or perceptions could be understood by analysis of the components in their view, perception is built up of the local sensations the way a crystal might be built up of an array of atoms Gestalt theory held that the perceptual whole was more than the sum of its sensory parts Gestalt Grouping Rules = a set of rules describing which elements in an image will appear to group together; the original list was assembled by members of the Gestalt school of thought good continuation = a Gestalt grouping rule stating that two elements will tend to group together if they seem to lie on the same contour color trumps good continuation as an organizing principle texture segmentation = carving an image into regions of common texture properties similarity is a gestalt grouping rule stating that the tendency of two features to group together will increase as the similarity between them increases the principle of proximity holds that items near each other are more likely to group together than are items more widely separated parallelism = a rule for figure-ground assignment stating that parallel contours are likely to belong to the same figure symmetry = a rule for figure-ground assignment stating that symmetrical regions are more likely to be seen as figure the principle of common region = gestalt grouping rule, two features will tend to group together if they appear to be part of the same larger region connectedness -- two items will tend to group together if they are connected ambiguous figure = a isual stimulus that gives rise to two or more interpretations of its identity or structure Necker Cube = an outline that is perceptually bi-stable; unlike the situation with most stimuli, two interpretations continually battle for perceptual dominance an accidental viewpoint is a viewing position that produces some regularity in the visual image that is not present in the world a second set of assumptions made by the visual system involves an implicit understanding of some aspects of the physics of the world recall an image has no meaning until middle and high-level visual processing dig into it the figure-ground assignment = the process of determining that some regions of an image belong to a foreground object ( figure) and other regions are part of the background ( ground ) surroundedness = a rule for figure-ground assignment stating that if one region is entirely surrounded by another, it is likely that the surrounded region is the figure some of the principles at work in the assignment of regions to figure or ground: surroundedness size symmetry parallelism extremal edges relative motion relatability = the degree to which two line segments appear to be part of the same contour heuristic = a mental shortcut nonaccidental feature = a feature of an object that is not dependent on the exact (or accidental) viewing position of the observer global superiority effect = the finding in various experiments that the properties of the whole object take precedence over the properties of parts of the object Object Recognition the idea that we recognize objects by matching every pixel or even matching every low-level feature of the input to a representation in memory is what might be called naïve template theory the visual system recognized objects by matching the neural representation of the image with a stored representation of the same "shape" in the brain structural description = a description of an object in terms of the nature of its constituent parts and the relationships between those parts "recognition by components" model proposed by Biederman; it holds that objects are recognized by the identities and relationships of their component parts geons = the "geometric ions" out of which perceptual objects are built because geons and relationships such as "A is beside B" are designed to be equally recognizeable from many different vantage points, structural descriptions composed of these geons and relations should also be view-point-invariant minor shape variations wont alter the structural descriptions of geons viewpoint invariance is a good thing, but object recognition is not completely viewpoint-invariant entry-level category = for an object, the label that comes to mind most quickly when we identify the object the object might be more specifically named--that's the subordinate level the object might be more generally named, that's the superordinate level prosopagnosia = the inability to recognize faces, caused by damage to specific areas in the temporal lobe; a person with this problem will recognize the shape of a face and know it is a face, but will not be able to identify whose face they are looking at a neuropsychological mark of truly separate brain modules is double dissociation this is a phenomena in which one of two functions, such as hearing and sight, can be damaged without harm to the other (and vice versa) the extrastriate cortex = the region of the cortex bordering the primary visual cortex and containing multiple areas involved in visual processing from the extrastriate regions of the occipital lobe, visual info moves out along two main pathways one path heads up into the parietal lobe; visual areas in this pathway seem to be important in processing information relating to the location of objects in space, and the actions required to interact with them -- occasionally called the "where" pathway the other path, heading down into the temporal lobe, is known as the "what" pathway -- this pathway appears to be the locus for the explicit acts of object recognition a lesion is a region of damaged brain, and as a verb, it is to destroy a section of the brain agnosia = the failure to recognize objects in spite of the ability to see them; typically occurs with brain damage inferotemporal cortex = part of the cerebral cortex in the lower portion of the temporal lobe, important in object recognition homologous regions = brain regions that appear to have the same function in different species feed-forward process = a process that carries out a computation one neural step after another, without need for feedback from a later stage to an earlier stage