Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JOIV : International Journal on Informatics Visualization

Enhanced U-Net Architecture for Glottis Segmentation with VGG-16 Aldi, Febri; Yuhandri, Yuhandri; Tajuddin, Muhammad
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3088

Abstract

Laryngeal endoscopic image analysis with segmentation techniques has great potential in detecting various diseases in the glottic area, which is essential for early diagnosis and proper treatment. This study proposes developing the U-Net architecture by integrating the VGG-16 model, aiming to improve the accuracy in detecting glottic areas. VGG-16 is applied to the encoder and bridge sections so that the model can take advantage of previously learned knowledge. This modification is expected to improve segmentation performance compared to standard U-Net, especially in handling variations in laryngeal image complexity. The dataset used consisted of 1,200 images taken randomly from the BAGLS website, a collection of laryngeal endoscopic image data rich in variation. The training results show that the standard U-Net produces an accuracy of 0.9995, IoU 0.6744, and DSC 0.7814. The improved U-Net showed a significant performance improvement, with an accuracy of 0.9998, an IoU of 0.8223, and a DSC of 0.9153. This improvement confirms that modifying the U-Net architecture using VGG-16 provides superior results in detecting glottic areas precisely. VGG-16 also helps model performance in overcoming the problem of smaller datasets. In addition, both models were tested using relevant evaluation metrics, and the test results showed that the improved U-Net consistently outperformed other CNN-based segmentation methods. These advantages show that the proposed approach improves accuracy and contributes significantly to developing glottic disease detection methods through laryngeal endoscopic image analysis, which can ultimately support clinical practice in detecting abnormalities in glottis more effectively.
The Development of Affine Transformation Method Using Scale Invariant Feature Transform (SIFT) Hartika Zain, Ruri Hartika; Yuhandri, Yuhandri; Sovia, Rini
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.3653

Abstract

Carving is a technique used to create decorative images on wood, stone, and other materials. In Indonesia, wood is a popular choice because of its durability and attractive grain. Examples of wood carvings include floral designs. The carving process can involve changes in color, texture, and scale, which may affect the carving's size and appearance and cause dimensional changes in certain materials. This study addresses the issue of quality control in wood carving on thin veneer layers. Free wood-carving data are provided as 200 flower images that can be used as input images. Affine transformation is used to determine the system behavior and the material transfer function during the production process. Additionally, we propose extending the affine transformation method to use the Scale-Invariant Feature Transform (SIFT). Affine transformations enable correlation analysis, outlier removal, and feature orientation in the affine domain. The SIFT algorithm accounts for scale, rotation, brightness, and perspective. Applications using ASIFT can efficiently process images and handle those with different pixel sizes to create new carvings. Training samples used to update the filter model are changed to the same pose. This enables the flower wood carving filter to represent objects with 98% accuracy. The model is then used to predict the class of the flower-carving data and to compute the distance between the template image's features and those of the input flower-wood-carving image. This research project has successfully developed an Affine Transformation method using SIFT features to create a new engraving application based on the ASIFT approach. 
Co-Authors Afifah Cahayani Adha Agus Perdana Windarto Akbar Iskandar Aldi Muharsyah Aldi, Febri Andrean, Fajri Ilhami Anita Sindar Ardiyan, Destio Arif Budiman Aulia, Allans Prima Aziz, Majid Rahman Budayawan, Khairi Chandra, Mrs Montesna Dahria, Muhammad Devita, Retno Dewi Eka Putri Dikki Handoko Dolly Indra Dwi Narulita Dwika Assrani Effendy, Geraldo Revanska Efori Buulolo Eka Praja Wiyata Mandala Esa Kurniawan Fauzan, Yuniko Febri Hadi Feri Irawan Finny Fitry Yani Firzada, Fahmi Fuad El Khair Gayatri, Satya Gemilang, Fhajri Arye Gunadi Widi Nurcahyo Hartika Zain, Ruri Hartika Hartomi, Zupri Henra Hendrick, H Idun Ariastuti Iftitah, Hasanatul Iskandar Fitri, Iskandar Jaya, Budi Jufriadif Na`am, Jufriadif Juledi, Angga Putra Julius Santony Julius Santony Julius Santony Kadrahman, Kadrahman Kurniawan, Jefdy Lidia K Simanjuntak M Ikhsan Setiawan M, Mutia Maharani Maharani, Maharani Mayola , Liga Mesran, Mesran Musli Yanto Na'am, Jufriadif Natalia Silalahi, Natalia Nelly Astuti Hasibuan Nuning Kurniasih Nurdiyanto, Heri Permana, Randy Petti Indrayati Sijabat Pohan, Yosua Ade Purnomo, Nopi Putra, Heru Rahmat Wibawa Putra, Rafi Septiawan Putri, Stefani Rahayu, Rita Rahmad Dian Rakhmad Kuswandhie Rio Andika Malik Ronda Deli Sianturi S Sumijan Sagala, Gamrina Salmiati, S Sarjon Defit Sarjon Defit Septiana, Vina Tri Setiawan, Adil Sisi Hendriani Siska, Ayu Prima Soraya Rahma Hayati Sovia, Rini Sri Dewi Stephano, Rivo Sugiarti, Sugiarti Suginam Suhaidir, Lc Granadi Sumijan Sumijan Sumijan Sumijan Sumijan, S Surya Darma Nasution Sutiksno, Dian Utami Syafrika Deni Rizki, Syafrika Deni Syafril Syafril Syaiffullah, Afif Tajuddin, Muhammad Takyudin, Takyudin Tessa Y M Sihite Tukino, Tukino Veri, Jhon Virgo, Ismail Vratiwi, Septiana Wanto, Anjar Wendi Boy Winanda, Teddy Yanto, Musli Yasmin, Nabilla Yendi Putra Yeni, Nasma Yenila, Firna Yolla Rahmadi Helmi Yudha Aditya Fiandra Zikir Risky, Muhammad Arif