Penerapan Convolutional Neural Networks Dalam Proses Quality Control Untuk Deteksi Kerusakan Produk Pakaian

Farid, Jihad Amal (2025) Penerapan Convolutional Neural Networks Dalam Proses Quality Control Untuk Deteksi Kerusakan Produk Pakaian. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5024211072-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (22MB) | Request a copy

Abstract

Penelitian ini bertujuan untuk mengembangkan sistem deteksi kerusakan otomatis pada produk pakaian khususnya dalam proses quality control menggunakan teknologi Convolutional Neural Networks (CNN). Dengan pertumbuhan pesat sektor e-commerce, kualitas produk menjadi faktor penting yang memengaruhi kepuasan pelanggan. Kerusakan pada pakaian, seperti bolong, noda, bahan, dan jahitan yang buruk, dapat merugikan reputasi penjual dan meningkatkan tingkat pengembalian barang. Penelitian ini menganalisis tantangan dalam proses inspeksi manual yang masih banyak diterapkan, yang berpotensi menyebabkan kesalahan akibat factor manusia. Dalam hal ini, CNN menawarkan solusi yang efektif dengan kemampuannya dalam menganalisis gambar dan mendeteksi fitur visual yang kompleks. Penelitian ini mengembangkan model CNN untuk mendeteksi dengan akurasi tinggi yang dapat mendeteksi kerusakan pada pakaian, seperti bolong, noda, bahan, dan jahitan yang buruk. Hasil dari penelitian ini diharapkan dapat memberikan kontribusi signifikan terhadap industri e-commerce dengan meningkatkan kualitas produk dan efisiensi operasional, sekaligus mengurangi tingkat pengembalian barang akibat kerusakan produk.
=======================================================================================================================================
This research aims to develop an automatic damage detection system for clothing products, especially in the process of quality control using Convolutional Neural Networks (CNN)
technology. With the rapid growth of the e-commerce sector, product quality is an important factor that affects customer satisfaction. Damages to clothing, such as tears, stains, and poor stitching, can hurt a seller’s reputation and increase the return rate. This research analyzes the challenges in the still widely applied manual inspection process, which has the potential to cause errors due to human factors. In this case, CNN offers an effective solution with its ability to analyze images and detect complex visual features. This research develops a CNN model for high-accuracy detection that can detect damage to clothing, such as tears, stains, and poor stitching. The results of this research are expected to significantly contribute to the e-commerce industry by improving product quality and operational efficiency, while reducing the rate of returned goods due to product defects.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Convolutional Neural Networks (CNN), You Only Look Once (YOLO), Deteksi, Kerusakan Pakaian. Convolutional Neural Networks (CNN), You Only Look Once (YOLO), Detection, Clothing Defects.
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Information Technology > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Jihad Amal Farid
Date Deposited:	31 Jul 2025 06:56
Last Modified:	31 Jul 2025 06:56
URI:	http://repository.its.ac.id/id/eprint/121034

Actions (login required)

View Item