자료유형  

 학위논문

Control Number  

0016932923

International Standard Book Number  

9798379871864

Dewey Decimal Classification Number  

005

Main Entry-Personal Name  

Xiong, Nian.

Publication, Distribution, etc. (Imprint  

[S.l.] : North Carolina State University., 2023

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Physical Description  

1 online resource(321 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 85-01, Section: B.

General Note  

Advisor: Wong, Chau-Wai;Post, Justin;Healey, Christopher;Shamey, Renzo.

Dissertation Note  

Thesis (Ph.D.)--North Carolina State University, 2023.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Color image segmentation is one of the most difficult tasks in both the color image processing area and computer vision area. When it is applied in color quality control, it becomes an essential task since proper pixels are supposed to be clustered together for their colors to be averaged. The avera ged color centroids could be regarded as the colors of the printed fabric examined. A pass/fail judge could be given based on the color difference between the averaged colors and the standard colors. The non -uniformity of a specific color cluster could also be calculated and another evaluation of how homogeneous the colors are printed on the target fabric can also be provided. Compared to the method that evaluates color quality perceptually, this method advantaged at high efficiency, larger field of view enables additional homogeneity evaluation which is difficult to measure accurately by the human visual system. Color gradient region separation, which is a challenging part of segmenting multicolored images, has been explored by different segmentation algorithms. In addition, various evaluation methods are applied to compare segmentation results generated by different algorithms. Since the segmentation ground truth for the images is unknown, two empirical unsupervised methods are used for evaluating the color separation performance. In addition to measuring the colorimetric values of the multicolored samples, the color homogeneity of each color cluster on the fabric samples are also determined and the color gradient regions are separated, which could be useful for future studies. To further investigate the visual perception of the color gradient regions in the assessment of multicolored materials, a psychophysical study was conducted. This study aimed to find the perceived boundaries in different types of color gradients and the perceived smoothness levels of these gradient regions. The results of this study could help separate the color gradient regions based on human perception and color appearance assessment of the color transitional regions that might appear in multicolored fabric samples.

Subject Added Entry-Topical Term  

User interface.

Subject Added Entry-Topical Term  

Cameras.

Subject Added Entry-Topical Term  

Systems stability.

Subject Added Entry-Topical Term  

Systems science.

Added Entry-Corporate Name  

North Carolina State University.

Host Item Entry  

Dissertations Abstracts International. 85-01B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:643860