Siradjuddin, Indah Agustien
Program Studi Teknik Informatika, Fakultas Teknik, Universitas Trunojoyo Madura

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

PARTICLE FILTER WITH BINARY GAUSSIAN WEIGHTING AND SUPPORT VECTOR MACHINE FOR HUMAN POSE INTERPRETATION Indah Agustien; Muhammad Rahmat Widyanto; Sukmawati Endah; Tarzan Basaruddin
MAKARA Journal of Technology Vol 14, No 1 (2010): April
Publisher : Directorate of Research and Community Engagement, Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Human pose interpretation using Particle filter with Binary Gaussian Weighting and Support Vector Machine isproposed. In the proposed system, Particle filter is used to track human object, then this human object is skeletonizedusing thinning algorithm and classified using Support Vector Machine. The classification is to identify human pose,whether a normal or abnormal behavior. Here Particle filter is modified through weight calculation using Gaussiandistribution to reduce the computational time. The modified particle filter consists of four main phases. First, particlesare generated to predict target’s location. Second, weight of certain particles is calculated and these particles are used tobuild Gaussian distribution. Third, weight of all particles is calculated based on Gaussian distribution. Fourth, updateparticles based on each weight. The modified particle filter could reduce computational time of object tracking sincethis method does not have to calculate particle’s weight one by one. To calculate weight, the proposed method buildsGaussian distribution and calculates particle’s weight using this distribution. Through experiment using video datataken in front of cashier of convenient store, the proposed method reduced computational time in tracking process until68.34% in average compare to the conventional one, meanwhile the accuracy of tracking with this new method iscomparable with particle filter method i.e. 90.3%. Combination particle filter with binary Gaussian weighting andsupport vector machine is promising for advanced early crime scene investigation.Keywords: particle filter, prediction, skeletonization, support vector machine, update
KEAMANAN CITRA DENGAN WATERMARKING MENGGUNAKAN PENGEMBANGAN ALGORITMA LEAST SIGNIFICANT BIT Kurniawan, Kurniawan; Siradjuddin, Indah Agustien; Muntasa, Arif
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 (667.819 KB) | DOI: 10.9744/informatika.13.1.9-14

Abstract

Image security is a process to save digital. One method of securing image digital is watermarking using Least Significant Bit algorithm. Main concept of image security using LSB algorithm is to replace bit value of image at specific location so that created pattern. The pattern result of replacing the bit value of image is called by watermark. Giving watermark at image digital using LSB algorithm has simple concept so that the information which is embedded will lost easily when attacked such as noise attack or compression. So need modification like development of LSB algorithm. This is done to decrease distortion of watermark information against those attacks. In this research is divided by 6 process which are color extraction of cover image, busy area search, watermark embed, count the accuracy of watermark embed, watermark extraction, and count the accuracy of watermark extraction. Color extraction of cover image is process to get blue color component from cover image. Watermark information will embed at busy area by search the area which has the greatest number of unsure from cover image. Then watermark image is embedded into cover image so that produce watermarked image using some development of LSB algorithm and search the accuracy by count the Peak Signal to Noise Ratio value. Before the watermarked image is extracted, need to test by giving noise and doing compression into jpg format. The accuracy of extraction result is searched by count the Bit Error Rate value.
Particle Filter with Binary Gaussian Weighting and Support Vector Machine for Human Pose Interpretation Agustien, Indah; Widyanto, Muhammad Rahmat; Endah, Sukmawati; Basaruddin, Tarzan
Makara Journal of Technology Vol 14, No 1 (2010)
Publisher : Directorate of Research and Community Services, Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (142.461 KB) | DOI: 10.7454/mst.v14i1.174

Abstract

Human pose interpretation using Particle filter with Binary Gaussian Weighting and Support Vector Machine is proposed. In the proposed system, Particle filter is used to track human object, then this human object is skeletonized using thinning algorithm and classified using Support Vector Machine. The classification is to identify human pose, whether a normal or abnormal behavior. Here Particle filter is modified through weight calculation using Gaussiandistribution to reduce the computational time. The modified particle filter consists of four main phases. First, particles are generated to predict target’s location. Second, weight of certain particles is calculated and these particles are used to build Gaussian distribution. Third, weight of all particles is calculated based on Gaussian distribution. Fourth, update particles based on each weight. The modified particle filter could reduce computational time of object tracking since this method does not have to calculate particle’s weight one by one. To calculate weight, the proposed method builds Gaussian distribution and calculates particle’s weight using this distribution. Through experiment using video data taken in front of cashier of convenient store, the proposed method reduced computational time in tracking process until 68.34% in average compare to the conventional one, meanwhile the accuracy of tracking with this new method is comparable with particle filter method i.e. 90.3%. Combination particle filter with binary Gaussian weighting and support vector machine is promising for advanced early crime scene investigation.
DETEKSI MANUSIA MENGGUNAKAN METODE HISTOGRAM OF ORIENTED GRADIENT DAN EUCLIDEAN DISTANCE Mufarroha, Fifin Ayu; Sirajuddin, Indah Agustien; Kusumaningsih, Ari
Network Engineering Research Operation [NERO] Vol 3, No 3 (2018): NERO
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Prinsip utama dari human detection adalah menemukan objek atau manusia didalam sebuah gambar. Banyak keuntungan yang bisa diambil dari hal ini, terutama dalam video pengawasan. Human detection dalam sebuah gambar lebih sulit karena banyaknya kendala yang dihadapi seperti pencahayaan, pakaian atau penampilan objek dan pose objek didalam setiap gambar yang berbeda. Pada penelitian ini akan diusulkan suatu metode ekstraksi fitur yang menggunakan histogram untuk melakukan human detection disebut dengan histogram of oriented gradient. Metode diawali dengan menghitung nilai gradien dari konversi citra grayscale yang kemudian citra akan dibagi menjadi sel dan tiap sel akan dibuat sebuah histogram dari nilai perhitungan gradien tersebut. Langkah selanjutnya adalah membentuk sebuah blok yang merupakan kumpulan dari sel. Setelah di bentuk sebuah blok, blok tersebut akan dinormalisasi dan hasil dari normalisasi blok tersebut adalah fitur. Sehingga dari hasil ekstraksi fitur akan dilakukan pengukuran kemiripan dengan citra file dengan menggunakan metode Euclidean Distance. Citra pelatihan  dan citra pengujian coba yang digunakan adalah 200 citra dengan 50 data positif, 50 data negatif, dan 100 citra uji. Dari uji coba aplikasi menggunakan pengukuran kemiripan Euclidean Distance dengan nilai threshold= 2,3,4, dan 5 pada skenario 1 dan 2 diperoleh rata – rata akurasi sebesar 80,55%.Kata kunci: Deteksi, fitur, Human Detection, Histogram of Oriented Gradient, Euclidean Distance.
Particle Filter with Gaussian Weighting for Human Tracking Siradjuddin, Indah Agustien; Widyanto, M. Rahmat; Basaruddin, T.
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Particle filter for object tracking could achieve high tracking accuracy.  To track the object, this method generates a number of particles which is the representation of the candidate target object.  The location of target object is determined by particles and each weight. The disadvantage of conventional particle filter is the computational time especially on the computation of particle’s weight.  Particle filter with Gaussian weighting is proposed to accomplish the computational problem.  There are two main stages in this method, i.e. prediction and update.  The difference between the conventional particle filter and particle filter with Gaussian weighting is in the update Stage.  In the conventional particle filter method, the weight is calculated in each particle, meanwhile in the proposed method, only certain particle’s weight is calculated, and the remain particle’s weight is calculated using the Gaussian weighting.  Experiment is done using artificial dataset.  The average accuracy is 80,862%.  The high accuracy that is achieved by this method could use for the real time system tracking. DOI:  http://dx.doi.org/10.11591/telkomnika.v10i6.1187