Scan Gambar Wajah Pada Ktm Menggunakan Model CNN (Convolutional Neural Network)

Tennov, Caesar Alwi (2022) Scan Gambar Wajah Pada Ktm Menggunakan Model CNN (Convolutional Neural Network). Project Report. Institut Telkom Telkom Purwokerto. (Unpublished)

[img] Text
Cover.pdf

Download (523kB)
[img] Text
Abstract.pdf

Download (5kB)
[img] Text
Abstrak.pdf

Download (117kB)
[img] Text
BAB I.pdf

Download (42kB)
[img] Text
BAB II.pdf

Download (281kB)
[img] Text
BAB III.pdf

Download (821kB)
[img] Text
BAB IV.pdf
Restricted to Registered users only

Download (192kB) | Request a copy
[img] Text
BAB V.pdf

Download (118kB)
[img] Text
Daftar Pustaka.pdf

Download (119kB)
[img] Text
Lampiran.pdf
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

In this AI project, we implement one of the fields, namely Computer Vision using the CNN (Convolutional Neural Network) architecture, which is an AI model that can detect an image, examples of its use are object classification in images or object detection in images. The purpose of making the project is to make it easier for students to take attendance during lectures, because it only requires KTM which all students must have. With some of our difficulties in Data Acquisition by collecting student KTM directly so that the dataset we have is limited. From the dataset, a training process is carried out for the CNN model to recognize faces from the dataset. Although there are still errors in the identification, this CNN model can still be developed for accuracy by adding a dataset with a greater number of variations. From this model that has been designed and detrained, which is still in the form of Python Script with Tensorflow, we need to convert the CNN model into TF-Lite for us to deploy in the form of Android Apps using Android Studio.

Item Type: Monograph (Project Report)
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Telecommunication and Electrical Engineering > Telecommunication Engineering
Depositing User: staff repository
Date Deposited: 09 Oct 2022 18:20
Last Modified: 09 Oct 2022 18:20
URI: http://repository.ittelkom-pwt.ac.id/id/eprint/8395

Actions (login required)

View Item View Item