東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

A relationship between human shape c...

Rutgers The State University of New Jersey - New Brunswick., Graduate School - New Brunswick.

Linked to FindBook

Google Book

Amazon

博客來

A relationship between human shape categorization and the statistics of natural shapes.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	A relationship between human shape categorization and the statistics of natural shapes./
Author:	Wilder, John.
Description:	34 p.
Notes:	Adviser: Jacob Feldman.
Contained By:	Masters Abstracts International47-05.
Subject:	Psychology, General. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1462257
ISBN:	9781109068511

A relationship between human shape categorization and the statistics of natural shapes.
Wilder, John.

A relationship between human shape categorization and the statistics of natural shapes. - 34 p.

Adviser: Jacob Feldman.

Thesis (M.S.)--Rutgers The State University of New Jersey - New Brunswick, 2009.

We studied the classification of shapes into broad natural categories, such as"animal" and "leaf", into which many shapes can proceed without overt basic-level recognition. Many shape representation models make implicit assumptions about what shape structures often occur in natural shapes, but such assumptions are not generally closely tied to real-world measurements. In order to tune a model of shape classification to the natural environment we collected statistics from a large database of real animal and leaf shapes; first we calculated the MAP skeletons of these shapes, and then computed several different statistical properties of the skeletons. These statistics allow for the creation of an "ecologically-informed" shape classification model that can generalize of many of the specific structures observed in the two classes. To investigate human shape classification subjects were shown shapes created by taking a weighted average of an animal and a leaf shape, resulting in a novel morphed shape. The task was to classify a shape as animal or leaf. Subjects easily performed this task, and their responses were strongly related to the weight used to averaged the shapes. Next, the classifier was used to obtain the likelihoods that a given morphed shape belonged the each class. These likelihood values are predictive of the subjects' responses, suggesting a relationship between human classification of shapes and the shapes' skeletal structures.

ISBN: 9781109068511Subjects--Topical Terms:

1018034
Psychology, General.

A relationship between human shape categorization and the statistics of natural shapes.
LDR:02337nam 2200265 a 45 001 861443
005 20100719
008 100719s2009 ||||||||||||||||| ||eng d
020 $a 9781109068511
035 $a (UMI)AAI1462257
035 $a AAI1462257
040 $a UMI $c UMI
100 1 $a Wilder, John. $3 1029154
245 1 2 $a A relationship between human shape categorization and the statistics of natural shapes.
300 $a 34 p.
500 $a Adviser: Jacob Feldman.
500 $a Source: Masters Abstracts International, Volume: 47-05, page: 3057.
502 $a Thesis (M.S.)--Rutgers The State University of New Jersey - New Brunswick, 2009.
520 $a We studied the classification of shapes into broad natural categories, such as"animal" and "leaf", into which many shapes can proceed without overt basic-level recognition. Many shape representation models make implicit assumptions about what shape structures often occur in natural shapes, but such assumptions are not generally closely tied to real-world measurements. In order to tune a model of shape classification to the natural environment we collected statistics from a large database of real animal and leaf shapes; first we calculated the MAP skeletons of these shapes, and then computed several different statistical properties of the skeletons. These statistics allow for the creation of an "ecologically-informed" shape classification model that can generalize of many of the specific structures observed in the two classes. To investigate human shape classification subjects were shown shapes created by taking a weighted average of an animal and a leaf shape, resulting in a novel morphed shape. The task was to classify a shape as animal or leaf. Subjects easily performed this task, and their responses were strongly related to the weight used to averaged the shapes. Next, the classifier was used to obtain the likelihoods that a given morphed shape belonged the each class. These likelihood values are predictive of the subjects' responses, suggesting a relationship between human classification of shapes and the shapes' skeletal structures.
590 $a School code: 0190.
650 4 $a Psychology, General. $3 1018034
690 $a 0621
710 2 $a Rutgers The State University of New Jersey - New Brunswick. $b Graduate School - New Brunswick. $3 1019196
773 0 $t Masters Abstracts International $g 47-05.
790 $a 0190
790 1 0 $a Feldman, Jacob, $e advisor
791 $a M.S.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1462257