Claim Missing Document
Check
Articles

Found 10 Documents
Search
Journal : Jurnal Informatika

PELACAKAN DAN PENGENALAN WAJAH MENGGUNAKAN METODE EMBEDDED HIDDEN MARKOV MODELS Margono, Arie Wirawan; Gunawan, Ibnu; Lim, Resmana
Jurnal Informatika Vol 5, No 1 (2004): MAY 2004
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (221.045 KB) | DOI: 10.9744/informatika.5.1.pp. 22-31

Abstract

Tracking and recognizing human face becomes one of the important research subjects nowadays, where it is applicable in security system like room access, surveillance, as well as searching for person identity in police database. Because of applying in security case, it is necessary to have robust system for certain conditions such as: background influence, non-frontal face pose of male or female in different age and race. The aim of this research is to develop software which combines human face tracking using CamShift algorithm and face recognition system using Embedded Hidden Markov Models. The software uses video camera (webcam) for real-time input, video AVI for dynamic input, and image file for static input. The software uses Object Oriented Programming (OOP) coding style with C++ programming language, Microsoft Visual C++ 6.0® compiler, and assisted by some libraries of Intel Image Processing Library (IPL) and Intel Open Source Computer Vision (OpenCV). System testing shows that object tracking based on skin complexion using CamShift algorithm comes out well, for tracking of single or even two face objects at once. Human face recognition system using Embedded Hidden Markov Models method has reach accuracy percentage of 82.76%, using 341 human faces in database that consists of 31 individuals with 11 poses and 29 human face testers. Abstract in Bahasa Indonesia : Pelacakan dan pengenalan wajah manusia merupakan salah satu bidang yang cukup berkembang dewasa ini, dimana aplikasi dapat diterapkan dalam bidang keamanan (security system) seperti ijin akses masuk ruangan, pengawasan lokasi (surveillance), maupun pencarian identitas individu pada database kepolisian. Karena diterapkan dalam kasus keamanan, dibutuhkan sistem yang handal terhadap beberapa kondisi, seperti: pengaruh latar belakang, pose wajah non-frontal terhadap pria maupun wanita dalam perbedaan usia dan ras. Tujuan penelitiam ini adalah untuk membuat perangkat lunak yang menggabungkan sistem pelacakan wajah manusia dengan menggunakan algoritma CamShift dan sistem pengenalan wajah dengan menggunakan algoritma Embedded Hidden Markov Models. Sebagai input sistem digunakan video kamera (webcam) untuk input bersifat real-time, video AVI untuk input bersifat dinamis, dan file image untuk input statis. Pemrograman perangkat lunak menggunakan prinsip pemrograman berorientasi objek (OOP) dengan menggunakan bahasa pemrograman C++, kompiler Microsoft Visual C++ 6.0®, dan dibantu dengan library dari Intel Image Processing Library (IPL) dan Intel Open Source Computer Vision (OpenCV). Hasil pengujian sistem menunjukkan bahwa pelacakan berdasarkan warna kulit manusia dengan menggunakan algoritma CamShift cukup baik, dalam melakukan pelacakan terhadap satu maupun dua objek wajah sekaligus. Sistem pengenalan wajah manusia menggunakan metode Embedded Hidden Markov Models mencapai tingkat akurasi pengenalan sebesar 82.76%, dengan database citra wajah sebanyak 341 citra yang terdiri dari 31 individu dengan 11 pose, dan jumlah citra penguji sebanyak 29 citra wajah. Kata kunci: Computer Vision, Pelacakan Objek, CamShift, Pengenalan Wajah, Hidden Markov Model.
PREDIKSI KEPADATAN KENDARAAN BERMOTOR BERDASARKAN TINGKAT KEBISINGAN LALU LINTAS DENGAN MENGGUNAKAN LOGIKA FUZZY Lim, Resmana; Thiang, Thiang; Kuntjoro, Jusak Agus
Jurnal Informatika Vol 3, No 2 (2002): NOVEMBER 2002
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (99.521 KB) | DOI: 10.9744/informatika.3.2.pp. 53-58

Abstract

The paper describes a fuzzy logic based system to predict the number of vehicle flow based on its noise. The system equipped by a sensor using a microphone an a 8088 microprocessor. The prediction results are displayed on 7-segment display. The fuzzy inference system used a strategy of MIN-MAX with 3 inputs which are: noise level, the width of road & a correction factor. A Defuzzification method of COG (Center of Gravity) is depployed in the system to produce prediction result in number of vehicle per minnute. The experimental results are presented to figure out the performance of the prediction comparing to the actual number of vehicle. The result shows that the prediction error of the system is about 7-10% comparing to the prediction by using human ear resulting the error of 4-5%. Abstract in Bahasa Indonesia : Paper ini menyajikan pengembangan sebuah sistem prediksi jumlah kendaraan bermotor yang lewat pada suatu jalan berdasarkan tingkat kebisingan lalu lintas dengan menggunakan logika fuzzy. Alat yang dibuat menggunakan sistem mikroprosesor 8088 yang dilengkapi dengan sensor bising berupa mikropon. Hasil prediksi jumlah kendaraan ditampilkan pada display 7-segment led. Sistem inferensia fuzzy yang dipakai di sini menggunakan strategi MIN-MAX dengan tiga crisp input yaitu: level kebisingan, lebar jalan di mana alat ini dipakai dan faktor koreksi. Sedangkan metode defuzifikasi menggunakan COG (Center of Gravity) untuk menghasilkan crisp output berupa prediksi jumlah kendaraan per menit. Pengujian sistem dilakukan dengan 2 cara yaitu membandingkan hasil prediksi alat dengan jumlah kendaraan sebenarnya, dan ke dua adalah membandingkan hasil prediksi dengan hasil perhitungan berdasarkan pendengaran telinga manusia dengan mata tertutup. Hasil percobaan menujukan kesalahan prediksi pada percobaan pertama adalah 7-10% sedangkan kesalahan prediksi alat bila dibandingkan hasil perhitungan telinga manusia adalah sekitar 4-5%. Kata kunci: prediksi jumlah kendaraan berdasarkan kebisingan, sistem prediksi fuzzy logic.
IDENTIFIKASI PERSONAL BERDASARKAN CITRA STRUKTUR TANGAN thiang, Thiang; Lim, Resmana; Sentoso, Budiono
Jurnal Informatika Vol 4, No 2 (2003): NOVEMBER 2003
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (463.426 KB) | DOI: 10.9744/informatika.4.2.pp. 103-108

Abstract

People's hand structure recognition is one of important research area in biometrics. The paper presents a development of hand structure recognition system. The system used color hand images captured from 14 people, with each of 10 images. The images was devided into 2 set which are training set and test set. The color image was converted into greyscale image then folowing a process of thresholding, closing and opening. The feature vector of 14 fiducial lines was extracted from the image of hand structure that represent hand structure. A pattern recognition was deployed on these feature vectors resulting people identity. The experiment results showed that the system has a good prospect to be incorporated into a biometrics system. Abstract in Bahasa Indonesia : Pengenalan struktur tangan manusia merupakan salah satu bidang penelitian yang penting dalam area biometrics. Pada penelitian ini, akan dibuat suatu program pengenalan struktur tangan seseorang. Pada percobaan struktur tangan ini data yang digunakan diperoleh dari 14 orang, tiap orang diambil 10 gambar. Sebagian gambar digunakan sebagai template/ database/training-set dan sebagian digunakan untuk testing-set. Gambar berwarna diubah menjadi grayscale yang kemudian di threshold lalu dilakukan proses Closing dan Opening. Diambil informasi panjang dari 14 garis utama yang mewakili struktur tangan untuk menghasilkan feature vector. Feature vektor ini selanjutnya digunakan untuk pengenalan pola. Hasil pengujian sistem menunjukkan bahwa pengenalan struktur tangan dapat dipertimbangkan untuk keperluan biometrics. Kata kunci: biometrics, pengenalan pola, pengenalan struktur tangan.
APLIKASI SURABAYA HERITAGE BERBASIS WEBSITE Handojo, Andreas; Lim, Resmana; Christian, Robby; Gosal, Robert; Bastion, Yulius
Jurnal Informatika Vol 13, No 1 (2015): MAY 2015
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (200.716 KB) | DOI: 10.9744/informatika.13.1.15-19

Abstract

Utilization of communication and computer technology has spread into various fields. Begin from the world of entertainment, education, business, health, life-style, and also the tourist field. Nowadays, still lack of the information related to the city of Surabaya as historical information, information about tourist sites, and others. This research conduct to develop an application to explore the history of the city of Surabaya as historic sites, tourist sites, museums, and the event agenda in town. With this application, the user is expected to be able to learn about the history of the city of Surabaya in the interesting form by combining text, picture, sound, and Google map facilities, as well as well as the promotion of tourism and events agenda are hosted in the city of Surabaya. Surabaya Heritage Applications created on a web-based application that is intended for public to know better about the history, tourism objects, as well as the event agenda in the city of Surabaya. Based from the testing results, the application was able to perform functions such as pre-planned. Meanwhile, testing by sampling questionnaires to the user produce that the application is attracting interest from users by 85%. It can be concluded that the applications made quite meet the target research.
GALILEE: AN INTERNET WEB BASED DISTANCE LEARNING SUPPORT SYSTEM Budiman, Arthur; Lim, Resmana
Jurnal Informatika Vol 1, No 1 (1999): MAY 1999
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (204.452 KB) | DOI: 10.9744/informatika.1.1.pp. 23-32

Abstract

This paper presents a project of Web-based Distance Learning support system. The system has been built based on the Internet and World Wide Web facility. The system could be accessed with a web browser which is directed to a certain web server address so that students can do learning process just like in the real situation, such as student admissions, taking course materials, syllabus, assignments, students grades, class discussions through web, and doing online quizzes. Students could also join collaboration works by giving opinions, feedback and student produced paper/web which can be shared to the entire learning community. Therefore, it will build a collaborative learning environment where lectures together with students make constructive knowledge databases for entire learning community. This system has been developed based on Active Server Pages (ASP) technology from Microsoft which is embedded in a web server. Web pages reside in a web server which is connected to an SQL Database Server. Database server is used to store structured data such as lectures/students personal information, course lists, syllabus and its descriptions, announcement texts from lecturers, commentaries for discussion forum, student's study evaluations, scores for each assignment, quizzes for each course, assignments text from lectures, assignments which are collected by students and students contribution/materials. This system has been maintained by an administrator for maintaining and developing web pages using HTML. The administrator also does ASP scripts programming to convert web pages into active server pages. Lectures and students could contribute some course materials and share their ideas through their web browser. This web-based collaborative learning system gives the students more active role in the information gathering and learning process, making the distance students feel part of a learning community, therefore increasing motivation, comprehension and interaction with other students.
PENGGUNAAN METODE FUZZY c-COVERING UNTUK ANALISA MARKET BASKET PADA SUPERMARKET Budhi, Gregorius Satia; Lim, Resmana; Prayitno, Osmand
Jurnal Informatika Vol 6, No 1 (2005): MAY 2005
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (236.901 KB) | DOI: 10.9744/informatika.6.1.pp. 51-58

Abstract

Data mining application with fuzzy c-covering method for market basket analysis on supermarket. As one of data mining applications, market basket analysis is generally performed using apriori method. However this method tends to searh the association degree of items by only counting how many times the items appears on the overall transaction without considering the items quantity on each transaction. Therefore, we propose a new method which is based on perception that the more items bought in a transaction, the weaker the relation between items on that transaction. For the experimental purpose of the realization the concept, we collect a month sales transaction data from a supermarket. The data are transformed to another form that can be used by the software. Then, an algorithm is created to process the data in order to generate association rule of items in transaction. The rules can be previewed in a table or graphic. Borland Ceplhi 7 and MS Access 2003 is used to build this experiment software. By using the output of this software, which are the association rules, association degree of items, can be obtained which is useful to help the decision maker to make market policies. Based on the testing result, it can concluded that the smaller minimum support and confidence, the more rule to be generated and the more processing time needed. Also, the higher the combination count to be searched, the less processing time needed. Abstract in Bahasa Indonesia : Sebagai salah satu aplikasi data mining, market basket analysis umumnya dilakukan dengan memakai metode Apriori. Metode ini mencari asosiasi antar item dengan hanya menghitung berapa kali item-item tersebut muncul dalam keseluruhan transaksi tanpa memperhatikan quantitas item dalam transaksi. Oleh karena itu, peneliti mengusulkan metode Fuzzy c-Covering. Metode ini didasarkan pada persepsi bahwa semakin banyak item yang dibeli dalam suatu transaksi, maka hubungan antar item dalam transaksi tersebut semakin lemah. Untuk pengujian realisasi konsep tersebut, peneliti mengumpulkan data-data transaksi penjualan dari sebuah swalayan selama satu bulan. Data yang didapat diubah ke bentuk yang dapat diolah oleh program. Kemudian sebuah algoritma dibuat untuk mengolah data tersebut dengan tujuan menghasilkan association rules dari item-item di dalam transaksi. Rule dapat ditampilkan dalam bentuk tabel ataupun grafik. Dengan menggunakan output dari program ini, yang berupa association rule, dapat diketahui tingkat asosiasi antar item yang berguna untuk membantu pihak pengambil keputusan dalam menentukan kebijakan pemasaran. Dari hasil pengujian, dapat disimpulkan bahwa semakin kecil minimum support dan confidence yang ditentukan, semakin banyak rule yang dapat dihasilkan dan waktu yang diperlukan semakin banyak. Selain itu, semakin tinggi jumlah kombinasi yang dicari, semakin sedikit waktu yang dibutuhkan. Kata kunci: analisis market basket, fuzzy c-covering,program data mining, tingkat asosiasi antar item.
SISTEM PENGEMBANGAN KENDALI FUZZY LOGIC BERBASIS MIKROKONTROLER KELUARGA MCS51 (PETRAFUZ) Thiang, Thiang; Hannawati, Anies; Eng, Ban; Lim, Resmana
Jurnal Informatika Vol 1, No 1 (1999): MAY 1999
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (274.717 KB) | DOI: 10.9744/informatika.1.1.pp. 1-10

Abstract

This paper presents a Fuzzy Logic Development Tool called PetraFuz which has been developed at Control System Laboratory, Electrical Engineering Department, Petra Christian University. The system consists of a hardware target based on MCS51 microcontroller and a software support running under PC Windows. The system is targeted for developing fuzzy logic based systems. It supports fuzzy logic design, evaluation, assembly language generator and downloading process to the target hardware to perform on-line fuzzy process. Process action and fuzzy parameters could be transferred to PC monitor via RS-232 serial communication, this on-line process parameters is used for fuzzy tuning, i.e. fuzzy if-then rules and fuzzy membership functions. The PetraFuz tool helps very much for Fuzzy system developments, it could reduce development time significantly. The tool could spur the development of fuzzy systems based on microcontroller systems such as fuzzy control systems, fuzzy information processing, etc. Abstract in Bahasa Indonesia : Makalah ini menyajikan sebuah sistem pengembangan kendali fuzzy logic (PetraFuz, Petra Fuzzy Development System) yang dikembangkan oleh laboratorium Sistem Kontrol, Jurusan Teknik Elektro, Universitas Kristen Petra Surabaya. Sistem ini terdiri dari perangkat keras sistem mikrokontroler MCS51 dan perangkat lunak pendukung yang berjalan pada PC. Sistem PetraFuz digunakan untuk mengembangkan sistem berbasis fuzzy logic utamanya pada bidang kendali. Kemampuan sistem meliputi pengembangan pada fase perancangan kendali, evaluasi kendali, pembentukan program bahasa assembly MCS51 dan proses downloading program menuju target sistem mikrokontroler MCS51 untuk dieksekusi melakukan kendali pada plant yang nyata. Aksi kendali dapat diakuisi oleh program PC melalui komunikasi serial RS232 sehingga respon kendali dapat digambarkan pada layar monitor untuk dilakukan analisis lebih lanjut yang diperlukan pada proses tuning if-then fuzzy rules. Penggunaan tools PetraFuz, sangat membantu proses rancang bangun sistem kendali fuzzy terutama bagi praktisi/akademisi yang berminat menekuni teknik kendali yang relatif baru ini. Sistem PetraFuz diharapkan dapat memberikan kontribusi positip bagi masyarakat sistem kendali untuk mengembangkan berbagai aplikasi kendali berbasis fuzzy logic. Kata kunci: logika fuzzy, sistem pengembangan kendali fuzzy, mikrokontroler MCS51
PROGRAM PENGHITUNG JUMLAH ORANG LEWAT MENGGUNAKAN WEBCAM Lande, Sudianto; Lim, Resmana; Gunadi, Kartika; Chandra K., Chandra K.
Jurnal Informatika Vol 5, No 2 (2004): NOVEMBER 2004
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/informatika.5.2.pp. 121-126

Abstract

The amount of public places's visitor data is very important. Usually we get it manually. AT the moment, video camera has been used for security. Therefor, the people counter software has been made using Normalized Sum-squared difference (NSSD) method that take differences the sum of frame fixel and background, squared it then normalized by detection window area. The NSSD values that have been count then thresholded to detect the people occurance in detection window. This project is made using Borland Delphi 5.0 with Tvideo component. Corect people counting percentation of more than 90% was obtained. The succesness of this program depends on the right thresholding values. Abstract in Bahasa Indonesia : Data jumlah pengunjung suatu tempat umum sangat penting. Data jumlah pengunjung biasanya didapat secara manual. Saat ini kamera video telah diterapkan untuk kepentingan keamanan. Karena itu dibuatlah program penghitung jumlah pengunjung dengan metode Normalized Sum-Squared Differences (NSSD) yang mengambil selisih jumlah pixel frame dan background dan dikuadratkan, dinormalisasi dengan luasan detection window. Nilai NSSD yang didapat diseleksi dengan proses thresholding untuk mendeteksi keberadaan orang pada detection window. Penelitian ini dibuat dengan menggunakan Borland Delphi 5.0, dengan tambahan komponen TVideo. Program ini secara keseluruhan menunjukkan keberhasilan lebih dari 90%. Keberhasilan dari program ini sangat dipengaruhi oleh penentuan nilai threshold yang tepat. Kata kunci: penghitungan orang, sensor kamera, NSSD, Image processing.
DETEKSI LANDMARK CITRA WAJAH DENGAN EXTRAKSI FITUR GABOR ANALISA FUZZY Lim, Resmana
Jurnal Informatika Vol 4, No 1 (2003): MAY 2003
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/informatika.4.1.pp. 1-7

Abstract

This paper proposes a method that automatically finds human faces as well as its landmark points in color images based on a fuzzy analysis. The proposed approach first uses color information to detect face candidate regions and then uses a fuzzy analysis of the color, shape, symmetry and interior facial features. A deformable Gabor wavelet graph matching is used to locate the facial landmark points describing the face. The latter allows for size and orientation variation since the search for landmark points allows for affine transformations as well as local deformations of the Gabor wavelet graph. The search is performed using a genetic algorithm that is essential because it effectively searches the solution space. Results based on the proposed method are included to verify the effectiveness of the proposed approach. Abstract in Bahasa Indonesia : Paper ini mengusulkan sebuah metode deteksi wajah beserta dengan titik landmarknya pada citra berwarna menggunakan analisa fuzzy. Proses awal menggunakan informasi warna kulit untuk menseleksi calon-calon obyek lantas dilanjukan dengan analisa fuzzy terhadap warna, bentuk, simetri dan fitur/landmark wajah. Proses lokalisasi landmark wajah menggunakan Gabor wavelet graph matching dengan memaksimalkan kemiripan antara landmark wajah model dengan obyek inputan. Proses maksimalisasi kemiripan ini menggunakan algoritma genetika. Hasil-hasil percobaan ditampilkan untuk memberikan gambaran keberhasilan dari metode yang diusulkan. Kata kunci: lokalisasi landmark wajah, analisa fuzzy, graph matching, algoritma genetika, Gabor wavelet.
OPTIMASI PENGAMBILAN DAN PENATAAN ULANG BARANG DI GUDANG DENGAN PENERAPAN STACK MENGGUNAKAN METODE GENETIC ALGORITHM Lim, Resmana; Gang, Ong Wie; Gunadi, Kartika
Jurnal Informatika Vol 5, No 1 (2004): MAY 2004
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/informatika.5.1.pp. 39-52

Abstract

Industrial field which getting more advance needs computer to help them. In industrial field, computer will make something get easier, fetching and reordering goods in warehouse is including here. A software including that needs have been made by writers. This software is specified for a warehouse which goods stored in plates at the rack in the warehouse. To reordering goods, writers use the Genetic Algorithm, which will process making population, finding the fitness cost with counting the vast and weight of the goods, sorting, immigration, cross over, and mutation. With this software, user can also check the condition of the warehouse in two and three dimensions, using OpenGL. This optimation software have been tried and give fitness cost average up to 90%, this software have been succeed to operate the function. Abstract in Bahasa Indonesia : Dunia industri yang semakin maju membutuhkan komputer sebagai alat bantu utama. Sistem komputerisasi di dalam dunia industri akan membuat beberapa hal menjadi lebih mudah, antara lain dalam pengambilan barang dan penataan ulang barang di gudang. Suatu perangkat lunak untuk keperluan tersebut telah dibuat oleh penulis. Perangkat lunak yang dibuat ini dikhususkan untuk gudang yang barang-barangnya disimpan dalam palet-palet pada rak di gudang. Penataan ulang barang ini menggunakan algoritma genetika, yang akan melalui proses pembuatan populasi awal, pencarian fitness cost dengan memperhitungkan luas area dan berat barang, pengurutan data, imigrasi, persilangan, dan mutasi. Melalui perangkat lunak ini, user juga dapat melihat kondisi gudang secara baik secara 2 dimensi ataupun 3 dimensi, yang dalam pengerjaannya menggunakan OpenGL. Sistem dari perangkat lunak yang dibuat ini sudah diuji coba dan memberikan nilai rata-rata fitness cost di atas 90%, ini berarti perangkat lunak ini telah sukses dalam menjalankan fungsinya. Kata kunci: penataan barang, pengambilan barang dari gudang, penataan ulang barang, rak, palet, Algoritma Genetika, imigrasi, persilangan, mutasi, OpenGL.