Implementasi Segmentasi Citra Pada Citra Tanaman Pakcoy Menggunakan Framework Tensorflow Lite

Erika, Lety Istikhomah Puspita Sari (2022) Implementasi Segmentasi Citra Pada Citra Tanaman Pakcoy Menggunakan Framework Tensorflow Lite. Diploma thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (473kB)
	Text Abstract.pdf Download (165kB)
	Text Abstrak.pdf Download (286kB)
	Text BAB I.pdf Download (59kB)
	Text BAB II.pdf Download (452kB)
	Text BAB III.pdf Download (357kB)
	Text BAB IV.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB V.pdf Download (171kB)
	Text Daftar Pustaka.pdf Download (122kB)
	Text Lampiran.pdf Restricted to Registered users only Download (651kB) | Request a copy

Abstract

Pakcoy is one type of vegetable that is very difficult to distinguish to determine the level of maturity from the intensity of the green color to determine harvest readiness in pakcoy plants. There needs to be a reliable and intelligent system to help farmers in the harvest process. In this study, a camera was used to take pictures of pakcoy plants. This study aims to test the accuracy of object detection with two categories, namely "Ready to Harvest" and "Not Ready to Harvest" pakcoy plants using the Tensorflow Lite framework with the EfficientDet Lite 2 model architecture. to assess the performance of the detection model. The test results show the average accuracy of detecting pakcoy vegetables that are ready to harvest is 98,02% and 99,00% for detecting pakcoy vegetables that are not ready to harvest, this indicates that the detection model works quite well on android devices and websites. Keywords: Pakcoy plant readiness detector, Tensorflow Lite, EfficientDet Lite 2, Deep Learning

Actions (login required)

View Item