Identifikasi Visual Cacat Produk Menggunakan Neural Network Model Backpropagation (Studi Kasus: PT. Panasonic Gobel Eco Solution)

• DOI: 10.30591/jpit.v4i2-2.1865
• Publication Date: 2023-09-12T08:22:35Z
• Authors: Muhammad Nur; Sjaeful Irwan; Danang Santosa
• Keywords: Backpropagation; Identification; RGB color model

Product defects are common in the production process. Visual identification of product is first carried out when produced. Identification vague very small shapes with different sizes and positions difficult to do ordinary eye sight, so that often results decisions about status not right. visual form can be identified by patterns such as shape, size position on image. In this study, we will apply a neural network backpropagation model classification pattern. images processed using image processing converting RGB pixel value into numeric value. Data numerical input for training values model. Training used identify produce decisions. The show able recognize an accuracy 99.24% based simulation test data final weight bias results, success up 91%.