Papers by Aufaclav Frisky
Data in Brief, Apr 1, 2021
Single-frame depth prediction is an efficient 3D reconstruction method for one-side artifacts. Ho... more Single-frame depth prediction is an efficient 3D reconstruction method for one-side artifacts. However, for this purpose, ground truth images, where the pixels are associated with the actual depth, are needed. The small number of publicly accessible datasets is an issue with the restoration of cultural heritage objects. In addition, relief data with irregular characteristics due to nature and human treatment, such as decolorization caused by moss and chemical reaction is still not available. We therefore created a dataset of Borobudur temple reliefs registered with their depth for data availability to solve these problems. This data collection consists of 4608 × 3456 (4K) resolution and profound RGB frames and we call this dataset the Registered Relief Depth (RRD) Borobudur Dataset. The RGB images have been taken using an Olympus EM10 II Camera with a 14 mm f/3.5 lens and the depth images were obtained directly using an ASUS XTION scanner, acquired on the temple's reliefs at 15000–25000 lux day time. The registration process of RGB data and depth information was manually performed via control points and was directly supervised by the archaeologist. Apart of enriching the data availability, this dataset can become an opportunity for International researchers to understand more about Indonesian Cultural Heritages.
Lecture Notes in Computer Science, 2021
International Journal of Robotics and Control Systems
The application of deep learning technology has increased rapidly in recent years. Technologies i... more The application of deep learning technology has increased rapidly in recent years. Technologies in deep learning increasingly emulate natural human abilities, such as knowledge learning, problem-solving, and decision-making. In general, deep learning can carry out self-training without repetitive programming by humans. Convolutional neural networks (CNNs) are deep learning algorithms commonly used in wide applications. CNN is often used for image classification, segmentation, object detection, video processing, natural language processing, and speech recognition. CNN has four layers: convolution layer, pooling layer, fully connected layer, and non-linear layer. The convolutional layer uses kernel filters to calculate the convolution of the input image by extracting the fundamental features. The pooling layer combines two successive convolutional layers. The third layer is the fully connected layer, commonly called the convolutional output layer. The activation function defines the o...
Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2022
Different color material and extreme lighting change pose a problem for single image depth predic... more Different color material and extreme lighting change pose a problem for single image depth prediction on archeological artifacts. These conditions can lead to misprediction on the surface of the foreground depth reconstruction. We propose a new method, the Color-Light Multi-Cascade Network, to overcome single image depth prediction limitations under these influences. Two feature extractions based on Multi-Cascade Networks (MCNet) are trained to deal with light and color problems individually for this new approach. By concatenating both of the features, we create a new architecture capable of reducing both color and light problems. Three datasets are used to evaluate the method with respect to color and lighting variations. Our experiments show that the individual Color-MCNet can improve the performance in the presence of color variations and fails to handle extreme light changes; the Light-MCNet, on the other hand, shows consistent results under changing lighting conditions but lacks detail. When joining the feature maps of Color-MCNet and Light-MCNet, we obtain a detailed surface both in the presence of different material colors in relief images, and under different lighting conditions. These results prove that our networks outperform state-of-the-art in limited number dataset. Finally, we also evaluate our joined network on the NYU Depth V2 Dataset to compare it with other state-of-the-art methods and obtain comparable performance.
2018 1st International Conference on Bioinformatics, Biotechnology, and Biomedical Engineering - Bioinformatics and Biomedical Engineering, 2018
Along with the development of technology in the field of bioinformatics, the cost of DNA sequenci... more Along with the development of technology in the field of bioinformatics, the cost of DNA sequencing from year to year is getting cheaper. This causes the growth of the genetic database to rise beyond Moore's Law. The rapid growth of genetic databases is one of the main obstacles in conducting sequence alignment. Multiple sequence alignment (MSA) is one important method in analyzing DNA or protein. One of the popular MSA methods among practitioners is Clustal. In sequential programming to process large data, it certainly takes a long time. In addition, sequential programming has limited memory, so it can cause the stack in the program. One way to speed up processing performance is to use parallel programming. MPI is one of the popular parallel computing technologies. In this study, a parallel process was run on a cluster consisting of four Raspberry Pi computers. The experiment used sequence data from BAliBase version 3. From the results of the research, it was shown that at the distance matrix calculation stage it could reach 12.7 times, while at the progressive alignment stage it could reach 5.71 times faster than the sequential process.
2014 7th International Conference on Ubi-Media Computing and Workshops, 2014
In this paper, we propose an emotion profile based music recommendation system. In the proposed a... more In this paper, we propose an emotion profile based music recommendation system. In the proposed algorithm, two emotion profiles are constructed using decision value in support vector machine (SVM), and based on short term and long term features respectively. The recognized emotion, emotion profile, and personal historical query results are fed into the recommendation module to generate the recommended music list.
Data in Brief, 2021
Single-frame depth prediction is an efficient 3D reconstruction method for one-side artifacts. Ho... more Single-frame depth prediction is an efficient 3D reconstruction method for one-side artifacts. However, for this purpose, ground truth images, where the pixels are associated with the actual depth, are needed. The small number of publicly accessible datasets is an issue with the restoration of cultural heritage objects. In addition, relief data with irregular characteristics due to nature and human treatment, such as decolorization caused by moss and chemical reaction is still not available. We therefore created a dataset of Borobudur temple reliefs registered with their depth for data availability to solve these problems. This data collection consists of 4608 × 3456 (4K) resolution and profound RGB frames and we call this dataset the Registered Relief Depth (RRD) Borobudur Dataset. The RGB images have been taken using an Olympus EM10 II Camera with a 14 mm f/3.5 lens and the depth images were obtained directly using an ASUS XTION scanner, acquired on the temple's reliefs at 15000–25000 lux day time. The registration process of RGB data and depth information was manually performed via control points and was directly supervised by the archaeologist. Apart of enriching the data availability, this dataset can become an opportunity for International researchers to understand more about Indonesian Cultural Heritages.
Journal on Computing and Cultural Heritage
This article investigates the limitations of single image depth prediction (SIDP) under different... more This article investigates the limitations of single image depth prediction (SIDP) under different lighting conditions. Besides that, it also offers a new approach to obtain the ideal condition for SIDP. To satisfy the data requirement, we exploit a photometric stereo dataset consisting of several images of an object under different light properties. In this work, we used a dataset of ancient Roman coins captured under 54 different lighting conditions to illustrate how the approach is affected by them. This dataset emulates many lighting variances with a different state of shading and reflectance common in the natural environment. The ground truth depth data in the dataset was obtained using the stereo photometric method and used as training data. We investigated the capabilities of three different state-of-the-art methods to reconstruct ancient Roman coins with different lighting scenarios. The first investigation compares the performance of a given network using previously trained ...
Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
2016 2nd International Conference on Science and Technology-Computer (ICST), 2016
2015 International Carnahan Conference on Security Technology (ICCST), 2015
Ijeis Indonesian Journal of Electronics and Instrumentation Systems, Oct 31, 2012
Telah dibuat suatu sistem pendeteksi kulit manusia melalui citra HSV (Hue Saturation Value) mengg... more Telah dibuat suatu sistem pendeteksi kulit manusia melalui citra HSV (Hue Saturation Value) menggunakan program Matlab. Penelitian ini dilakukan karena masih minimnya penelitian untuk citra HSV pada Matlab. Berbedanya nilai Hue dan Saturation pada program matlab maka penelitian ini akan berguna untuk pendeteksian kulit m anusia menggunakan program Matlab. Penelitian ini dimulai dengan mencari nilai Hue dan Saturation pada citra HSV dan menentukan range nilai kulit manusia yang dapat dibedakan juga dengan objek yang memiliki warna mirip dengan kulit manusia. Hasil dari segmentasi kemudian di filter menggunakan low pass filter untuk menghilangkan noise. Hasilnya akan dideteksi untuk membedakan kulit manusia yang berupa muka dan selain muka. Penelitian ini menghasilkan kesimpulan range kulit manusia memiliki nilai Hue sebesar 0.021 sampai 0.080 dan Nilai Saturation sebesar 0.23 sampai 0.68. Metode ini dapat bekerja dengan sangat baik dengan kecepatan rata-rata 1.4 frame per second dengan tingkat akurasi 87.86 %. Akurasi keberhasilan dipengaruhi oleh gerakan objek, posisi dan arah objek wajah terhadap kamera, jumlah objek orang dalam satu frame, jarak objek kulit manusia dengan kamera serta intensitas cahaya pencahayaan.
Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2020
Uploads
Papers by Aufaclav Frisky