Article Per Year (5 Year)
p-Index From 2021 - 2026
0.995
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Indonesian Journal of Electrical Engineering and Informatics (IJEEI) JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI
Saparudin, Saparudin
Telkom University
Computer Science & IT Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : TELKOMNIKA (Telecommunication Computing Electronics and Control)

 1 
Network and layer experiment using convolutional neural network for content based image retrieval work Fachruddin Fachruddin; Saparudin Saparudin; Errissya Rasywir; Yovi Pratama
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 20, No 1: February 2022
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v20i1.19759

Abstract

In this study, a test will be conducted to find out how the results of experiments on the network and layer used on the convolutional neural network algorithm. The performance and accuracy of the retrieval process method that was tested using the algorithm approach to do an object image retrieval. The expected results of this study are the techniques offered can provide relatively better results compared to previous studies. The results of the classification of object images with different levels of confusion on the Caltech 101 database resulted an average accuracy value. From the experiments conducted in the study, content based image retrieval work (CBIR) work using convolutional neural network (CNN) algorithm in terms of execution time, loss testing and accuracy testing. From several experiments on layers and networks shows that, the more hidden layers used, then the result is better. The graph of validation loss decreases at fewer epochs, slightly fluctuating at more epochs. Likewise, validation accuracy increases insignificantly on epochs with small amounts, but tends to be stable on more epochs.
Extraction of object image features with gradation contour Fachruddin Fachruddin; Saparudin Saparudin; Errissya Rasywir; Yovi Pratama; Beni Irawan
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 6: December 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i6.19491

Abstract

Image retrieval using features has been used in previous studies including shape, color, texture, but these features are lagging. With the selection of high-level features with contours, this research is done with the hypothesis that images on objects can also be subjected to representations that are commonly used in natural images. Considering the above matters, we need to research the feature extraction of object images using gradation contour. From the results of the gradation contour test results, there is linearity between the results of accuracy with the large number of images tested. Therefore, it can be said that the influence of the number of images will affect the accuracy of classification. The use of contour gradation can be accepted and treated equally in all image types, so there is no more differentiation between image features. The complexity of the image does not affect the method of extracting features that are only used uniquely by an image. From the results of testing the polynomial coefficient savings data as a result of the gradation contour, the highest result is 81.40% with the highest number of categories and the number of images tested in the category is also higher.
Co-Authors Deris Stiawan Errissya Rasywir Fachruddin Fachruddin Fachruddin Fachruddin Irawan, Beni Mohd. Yazid Idris Nurhadi Nurhadi Yovi Pratama