Articles

Found 15 Documents
Search

Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR) Fachrurrozi, Muhammad; Saparudin, Saparudin; Erwin, Erwin; Mardiana, Mardiana; Badillah, Clara Fin; Erlina, Junia; Lazuardi, Auzan
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 5: October 2018 (Part I)
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Original Source | Check in Google Scholar

Abstract

Face recognition?system in real time is divided into three processes, namely feature extraction, clustering, detection, and recognition. Each of these stages uses different methods, Local Binary Pattern (LBP), Agglomerative Hierarchical Clustering (AHC) and Euclidean Distance. Multi-face image search using Content Based Image Retrieval (CBIR) method. CBIR performs image search by image feature itself. Based on real time trial results, the accuracy value obtained is 61.64%.??
Weighting Facial Features Extraction using Geometric Average Saparudin, Saparudin
Computer Engineering and Applications Journal Vol 6 No 1 (2017)
Publisher : Universitas Sriwijaya

Show Abstract | Original Source | Check in Google Scholar | Full PDF (160.833 KB)

Abstract

Human facial feature extraction is an important process in the face recognition system. The quality of the results from the extraction of human facial features is determined by the degree of accuracy. The weighting of human facial features is used to test the accuracy of the methods used. This research produces the process of weighting the facial features automatically. The results obtained are the same as those seen by the human eyes.  
Feature Extraction for Retina Image Based on Difference Approaches Erwin, Erwin; Saparudin, Saparudin; Putri, Arum Cantika; Hidayat, Hidayat; Hariyani, Fifi
Computer Engineering and Applications Journal Vol 7 No 3 (2018)
Publisher : Universitas Sriwijaya

Show Abstract | Original Source | Check in Google Scholar | Full PDF (1151.994 KB)

Abstract

Automatic disease diagnosis using biometric images is a difficult job due to image distortion, such as the presence of artifacts, less or excessive light, narrow vessel visibility and differences in inter-camera variability that affect the performance of an approaches. Almost all extraction methods in the blood vessels in the retina produce the main part of the vessel with no patalogical environment. However, an important problem for this method is that extraction errors occur if they are too focused on the thin vessels, the wide vessels will be more detectable and also artificial vessels that may appear a lot. In addition, when focusing on a wide vessel, the extraction of thin vessels tends to disappear and is low. Based on our research, different treatments are needed to extract thin vessels and wide vessels both visually and in contrast. This study aims to adopt feature extraction strategies with different techniques. The method proposed in segmentation and extraction with three different approaches, namely the pattern of shape, color, and texture. Testing segmentation and feature extraction using STARE datasets with five classes of diseases namely Choroidal Neovascularization, Branch Retinal Vein Occlusion, Histoplasmosis, Myelinated Nerve Fibers, and Coats. Image enhancement on Myelinated Nerve disease Fiber is the best result from the image of other diseases with the highest value of PSNR of 35.4933 dB and the lowest MSE of 0.0003 means that the technique is able to repair objects well. The main significance of this work is to increase the quality of segmentation results by applying the Otsu method. Testing of segmentation results shows improvements with the proposed method compared to other methods. Furthermore, the application of different feature extraction methods will get information on disease classification features based on patterns of suitable shapes, colors, and textures.
PERENCANAAN BAK PENGENDAPAN DAN PENAMPUNGAN AIR YANG BERASAL DARI MATA AIR DI KECAMATAN LAMALA Sirampun, Maksi; Saparudin, Saparudin; Tunas, I Gede
JOURNAL TEKNIK SIPIL DAN INFRASTRUKTUR Vol 3, No 2 (2013)
Publisher : JOURNAL TEKNIK SIPIL DAN INFRASTRUKTUR

Show Abstract | Original Source | Check in Google Scholar | Full PDF (626.645 KB)

Abstract

District of Lamala Regency of Luwuk is the area in which shortage of  water and difficulty in supplying the water needs of its population. This planning study aims to address the fresh water problem and determine the needs of fresh water , especially three villages in the District of  Lamala namely village of Bonebabakal, Lomba and Poroan.The study was conducted by collecting primary data and secondary data, as well as direct observation in the field. Furthermore, to drain the water from the spring water to the deposition basin of 20m3 and reservoir basin of 50m3 at a service area with a distance of 3 km from the source and height difference of 128 meters can utilize the force of gravity. From the research, the spring discharge data obtained at 20.1 liters / sec and to meet the needs of local water services up to year 2031 the population projection can be calculated using the arithmetic and geometric methods.As a suggestion to optimize the volume of water , it should be made on the fresh water catchers building in the location of  water springs as well as the manufacture of bags to drain the sediment sludge coming from the spring.   Keywords: depositional basin, reservoir, springs
Training Making Materials Video Interactive Learning For Teachers in SMK Negeri 1 Muara Enim Siswanti, Sri Desy; Darmawijoyo, Darmawijoyo; Saparudin, Saparudin; Syamsuryadi, Syamsuryadi; Oklilas, Ahmad Fali; Satria, Hadi Purnawan; Primanita, Anggina
Annual Research Seminar (ARS) Vol 1, No 1 (2015)
Publisher : Annual Research Seminar (ARS)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (841.996 KB)

Abstract

Report on the implementation of community service describes the learning outcomes of the training video creation intended for Vocational High School (SMK) Negeri 1 Muara Enim. The training was attended by 66 teachers. This training provides a solution to improve the teaching of teachers SMK 1 Muara Enim is by making instructional materials in the form of video lessons. The training is carried out with extension methods and practices, to support the training is complemented every teacher training modules in softcopy. The training was held at the Hall of SMK 1 Muara Enim. To measure the result of performance evaluation activities, where the outcome is a matter of understanding of the material by the participants, the average value reached approximately 80-100 giving the correct answer. For the future need this kind of training activities with the broader material and a longer period  with the aim to improve the quality of teaching and school teachers.
Challenges and Potential Research in Fingerprint Image Recognition Saparudin, Saparudin
Annual Research Seminar (ARS) Vol 1, No 1 (2015)
Publisher : Annual Research Seminar (ARS)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (3374.951 KB)

Abstract

The issues about security of the system and the device are still to be a potential topics in computer technology and networking. The fingerprint image as a kind of human biometric features has been used for over a century and the most widely used for personal recognition in civil, forensic, and commercial areas. In this paper is discussed the latest in trend in fingerprint recognition is viewed from the category of fingerprint images, namely; patent, impressed, and latent. The survey of various research articles indicated that opportunities in the fingerprint identification, particularly the problems in fingerprint image enhancement are topic that potential for researched.
Enhanced Ridge Direction for the Estimation of Fingerprint Orientation Fields Saparudin, Saparudin
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 2: EECSI 2015
Publisher : IAES Indonesia Section

Show Abstract | Original Source | Check in Google Scholar | Full PDF (292.886 KB)

Abstract

An accurate estimation of fingerprint orientation fields is an important step in the fingerprint classification process. Gradient-based approaches are often used  for estimating orientation fields of ridge structures but this method is susceptible to noise. Enhancement of ridge direction improves the structure of orientation fields and increases the number of correct features thereby conducing the overall performance of the classification process. In this paper, we propose an algorithm to improve orientation field structures using variance of gradient. That algorithm have two steps; firstly, estimation of fingerprint orientation fields using gradient-based method, and finally, enhancement of ridge direction using minimum variance of the cross center block direction. We have used standard fingerprint database NIST-DB14 for testing of proposed algorithm to verify the degree of efficiency of algorithm. The experiment results suggest that our enhanced algorithm achieves visibly better noise resistance with other methods.
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segmentation Erwin, Erwin; Saparudin, Saparudin; Saputri, Wulandari
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 6: December 2018 (Part I)
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Original Source | Check in Google Scholar

Abstract

This paper proposes a new method for image segmentation is hybrid multilevel thresholding and improved harmony search algorithm. Improved harmony search algorithm which is a method for finding vector solutions by increasing its accuracy. The proposed method looks for a random candidate solution, then its quality is evaluated through the Otsu objective function. Furthermore, the operator continues to evolve the solution candidate circuit until the optimal solution is found. The dataset used in this study is the retina dataset, tongue, lenna, baboon, and cameraman. The experimental results show that this method produces the high performance as seen from peak signal-to-noise ratio analysis (PNSR). The PNSR result for retinal image averaged 40.342 dB while for the average tongue image 35.340 dB. For lenna, baboon and cameramen produce an average of 33.781 dB, 33.499 dB, and 34.869 dB. Furthermore, the process of object recognition and identification is expected to use this method to produce a high degree of accuracy.
Penentuan Dan Pengembangan Kompetensi Inti Kabupaten Bekasi Nurcahyo, Rahmat; Farizal, Farizal; Stiadi, Edwin; Saparudin, Saparudin
Jurnal Teknik Industri Vol 13, No 1 (2012): Februari
Publisher : Department Industrial Engineering, University of Muhammadiyah Malang

Show Abstract | Original Source | Check in Google Scholar | Full PDF (199.105 KB)

Abstract

Development of a region is a vital issue for the survival of the area. One way for development of a region is based on core competence. This research discusses the core competence of Bekasi region for development. This research methodsare Analytic Hierarchy Process and Interpretive Structural Modeling. Results from this research is a road map model for Bekasi region development, based on small and medium enterprises in food and beverage industry.
Fingerprint Enhancement Algorithm Based-on Gradient Magnitude for the Estimation of Orientation Fields Saparudin, Saparudin; Sulong, Ghazali
Computer Engineering and Applications Journal Vol 4 No 2 (2015)
Publisher : Universitas Sriwijaya

Show Abstract | Original Source | Check in Google Scholar | Full PDF (715.022 KB)

Abstract

An accurate estimation of fingerprint orientation fields is an important step in the fingerprint classification process. Gradient-based approaches are often used for estimating orientation fields of ridge structures but this method is susceptible to noise. Enhancement of fingerprint images improves the ridge-valley structure and increases the number of correct features thereby conducing the overall performance of the classification process. In this paper, we propose an algorithm to improve ridge orientation textures using gradient magnitude. That algorithm has four steps; firstly, normalization of fingerprint image, secondly, foreground extraction, thirdly, noise areas identification and marking using gradient coherence and finally, enhancement of grey level. We have used standard fingerprint database NIST-DB14 for testing of proposed algorithm to verify the degree of efficiency of algorithm. The experiment results suggest that our enhanced algorithm achieves visibly better noise resistance with other methods.