Naura Muthia Alwanadi, . (2026) PENGEMBANGAN APLIKASI WEB KLASIFIKASI JENIS DAN KUALITAS KAIN BERBASIS DEEP LEARNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (150kB) |
|
Text
AWAL.pdf Download (821kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (223kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (823kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (410kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
BAB 5.pdf Download (188kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (198kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (97kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (35MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (331kB) |
Abstract
The identification of fabric types and quality remains a challenge for both general users and textile practitioners due to texture similarities, quality variations, and the limitations of direct visual assessment. This study aims to develop PATTERNA, a web-based application for classifying fabric types and quality using Deep Learning. The research method follows a gradual Agile approach, including primary data collection, image preprocessing, augmentation, model training and evaluation, website implementation, deployment, and system testing. The dataset consists of 1,000 close-up fabric images divided into 10 classes, covering cotton, polyester, linen, polycotton, and rayon, each categorized into good and poor quality. The models compared in this study include Custom CNN, MobileNetV2, ResNet50, and EfficientNetB0. The results show that ResNet50 H1 P1 achieved the highest accuracy of 85% with a Macro F1-score of 0.85, while EfficientNetB0 H3 P2 was selected as the final model because it provided a more balanced performance in the web implementation, particularly in rejecting non-fabric images. Black-Box Testing showed that all main features worked properly, User Acceptance Testing achieved an index of 89.18% categorized as Strongly Agree, while non-functional testing confirmed that the system met the established performance, compatibility, responsiveness, and security standards.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2210511033] [Pembimbing 1: Ridwan Raafi'udin] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Noor Falih] [Penguji 2: Kharisma Wiati Gusti] |
| Uncontrolled Keywords: | Fabric Classification, Textile Quality, Deep Learning, Web Application, User Acceptance Testing (UAT) |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | NAURA MUTHIA ALWANADI |
| Date Deposited: | 31 Aug 2026 04:11 |
| Last Modified: | 31 Aug 2026 04:11 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51029 |
Actions (login required)
 |
View Item |