ANALISIS STUDI KASUS MULTIVARIAN INTENSITAS DENGAN PERBANDINGAN METODE SEGMENTASI COLOR HISTOGRAM HSV, YCBCR, L*A*B (CIELAB) DAN K-MEANS CLUSTERING WARNA PADA FINGERSPELLING AMERICAN SIGN LANGUAGE (ASL)

PURNAMASARI, DIAH and Erwin, Erwin (2019) ANALISIS STUDI KASUS MULTIVARIAN INTENSITAS DENGAN PERBANDINGAN METODE SEGMENTASI COLOR HISTOGRAM HSV, YCBCR, L*A*B (CIELAB) DAN K-MEANS CLUSTERING WARNA PADA FINGERSPELLING AMERICAN SIGN LANGUAGE (ASL). Undergraduate thesis, Sriwijaya University.

[img] Text
RAMA_56201_09011281320029.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[img] Text
RAMA_56201_09011281320029_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (13MB) | Request a copy
[img]
Preview
Text
RAMA_56201_09011281320029_0029017101_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[img] Text
RAMA_56201_09011281320029_0029017101_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (907kB) | Request a copy
[img] Text
RAMA_56201_09011281320029_0029017101_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (470kB) | Request a copy
[img] Text
RAMA_56201_09011281320029_0029017101_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[img] Text
RAMA_56201_09011281320029_0029017101_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (24kB) | Request a copy
[img] Text
RAMA_56201_09011281320029_0029017101_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (99kB) | Request a copy

Abstract

Sign Language is the only means of communication for the hearing and speech impaired people. Meanwhile, they could not participate in the normal communication as general people do. It makes such a gap in terms of social, economic and education. Finding an interpreter experienced or qualified every time is an intricate and expensive task, in that there are a few normal people who have or want to try to learn sign language so they may have interaction with the population of impaired people. Hence, it becomes the reason for the research. The system built is a system that can identify fingerspelling or gestures of the user, but in practice there are many interruptions or noise either in gesture (video processing) or in image processing. In this study, the proposed method of image processing, focusing on segmentation, where the input images have a variety range of intensity and type of background. This challenge based on the fact that people not always in good lighting conditions, differences in light and background cause skin tone was changed (it can be darker or lighter). The proposed method is set up the histogram in the HSV color space, YCbCr, L * a * b * (CIELAB) and will be tested also the color clustering methods K-Means as a contribution towards the experimental study of effective segmentation improvement. This research resulted in SSIM which the highest is HSV ±0.5742 then following by YCbCr ±0.5676, K-Means (k = 2) ±0.5588, CIELAB (L * a * b) ±0.5515, and the last K-Means (k = 3) ±0.3811. Then, the highest in Dice metric is K-Means ±0.6121, following by YCbCr ±0.6096, HSV ±0.6068, CIELAB (L * a * b) ±0.5982, and K-Means (k = 3) ±0.4411. Both of quality metrics stated that value 1 is best result.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: ASL, Histogram Warna, HSV, Intensitas, K-Means Clustering, L*a*b (CIELAB), Segmentasi, Sørensen–Dice Coefficient, SSIM, YCbCr
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Q Science > Q Science (General) > Q350-390 Information theory
T Technology > TR Photography > TR287-500 Photographic processing. Darkroom technique
Divisions: Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Diah Purnamasari
Date Deposited: 20 Nov 2019 03:49
Last Modified: 20 Nov 2019 03:49
URI: http://repository.unsri.ac.id/id/eprint/17127

Actions (login required)

View Item View Item