MARC Record from marc_columbia

LEADER: 03197cam a22003973i 4500
001 12442309
005 20180618183155.0
006 m o d
007 cr |n||||a||||
008 170328s2017 nyu|||| om 00| ||eng d
035 $a(OCoLC)982310694
035 $a(OCoLC)ocn982310694
035 $a(NNC)ACfeed:legacy_id:ac:207316
035 $a(NNC)ACfeed:doi:10.7916/D8CF9VTF
035 $a(NNC)12442309
040 $aNNC$beng$erda$cNNC
100 1 $aBerg, Thomas.
245 10 $aHigh-level, part-based features for fine-grained visual categorization /$cThomas Berg.
264 1 $a[New York, N.Y.?] :$b[publisher not identified],$c2017.
300 $a1 online resource.
336 $atext$btxt$2rdacontent
337 $acomputer$bc$2rdamedia
338 $aonline resource$bcr$2rdacarrier
502 $aThesis (Ph.D.)--Columbia University, 2017.
500 $aDepartment: Computer Science.
500 $aThesis advisor: Peter N. Belhumeur.
520 $aObject recognition--"What is in this image?"--is one of the basic problems of computer vision. Most work in this area has been on finding basic-level object categories such as plant, car, and bird, but recently there has been an increasing amount of work in fine-grained visual categorization, in which the task is to recognize subcategories of a basic-level category, such as blue jay and bluebird. Experimental psychology has found that while basic-level categories are distinguished by the presence or absence of parts (a bird has a beak but car does not), subcategories are more often distinguished by the characteristics of their parts (a starling has a narrow, yellow beak while a cardinal has a wide, red beak). In this thesis we tackle fine-grained visual categorization, guided by this observation. We develop alignment procedures that let us compare corresponding parts, build classifiers tailored to finding the interclass differences at each part, and then combine the per-part classifiers to build subcategory classifiers.
520 $aUsing this approach, we outperform previous work in several fine-grained categorization settings: bird species identification, face recognition, and face attribute classification. In addition, the construction of subcategory classifiers from part classifiers allows us to automatically determine which parts are most relevant when distinguishing between any two subcategories. We can use this to generate illustrations of the differences between subcategories. To demonstrate this, we have built a digital field guide to North American birds which includes automatically generated images highlighting the key differences between visually similar species. This guide, "Birdsnap," also identifies bird species in users' uploaded photos using our subcategory classifiers. We have released Birdsnap as a web site and iPhone application.
653 0 $aOptical pattern recognition
653 0 $aOptical data processing
653 0 $aComputer vision
653 0 $aComputer vision--Computer programs
653 0 $aVisual perception--Data processing
653 0 $aComputer science
856 40 $uhttps://doi.org/10.7916/D8CF9VTF$zClick for full text
852 8 $blweb$hDISSERTATIONS