Literatur Reviu Sistematis: Identifikasi Jenis Ular Berbasis Computer Vision

  • Eva Putriany
  • Dhani Ariatmanto
N/ACitations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

Systematic Literature Review ini bertujuan untuk mengidentifikasi algoritma-algoritma yang digunakan dalam identifikasi spesies ular yang menggunakan computer vision, mengevaluasi dataset, tingkat akurasi, faktor-faktor yang memengaruhi akurasi, dan keterbatasan yang dihadapi. Melalui tinjauan literatur sistematis, 20 paper terpilih dari tahun 2019-2023, yang didapat dari berbagai sumber literatur. Penelitian-penelitian tersebut mengeksplorasi berbagai strategi untuk mengatasi tantangan pengenalan objek ular secara otomatis, termasuk peningkatan kinerja model, eksplorasi pendekatan baru, dan penerapan solusi efektif. Hasil dari studi literatur menyoroti pentingnya pemrosesan data yang cermat, pemilihan arsitektur model yang tepat, serta penyesuaian parameter algoritma yang optimal dalam mencapai kinerja maksimal pada model-model yang dikembangkan. Beberapa peneliti juga mengemukakan keterbatasan dalam penelitiannya, seperti kualitas dan jumlah dataset, kompleksitas morfologi ular, dan variasi pose ular. Diperlukan kerja sama lintas disiplin dan berbagi pengetahuan untuk mengatasi tantangan ini dan memajukan bidang identifikasi spesies ular melalui computer vision.This Systematic Literature Review aims to identify algorithms used in identifying snake species using computer vision, evaluate datasets, level of accuracy, factors that influence accuracy, and limitations faced. Through a systematic literature review, 20 papers were selected from 2019-2023, obtained from various literature sources. These studies explore various strategies to overcome the challenges of automatic snake object recognition, including improving model performance, exploring new approaches, and implementing effective solutions. The results of the literature study highlight the importance of careful data processing, selecting the right model architecture, and optimal adjustment of algorithm parameters in achieving maximum performance in the models being developed. Several researchers also pointed out limitations in their research, such as the quality and number of datasets, the complexity of snake morphology, and variations in snake poses. Interdisciplinary collaboration and knowledge sharing are needed to overcome these challenges and advance the field of snake species identification through computer vision.

Cite

CITATION STYLE

APA

Eva Putriany, & Dhani Ariatmanto. (2024). Literatur Reviu Sistematis: Identifikasi Jenis Ular Berbasis Computer Vision. JNANALOKA, 43. https://doi.org/10.36802/jnanaloka.2024.v5-no01-43-50

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free