AUTOMATIC LIP DETECTION FOR FACE IDENTIFICATION

4^th International Conference Humanoid, Nanotechnology, Information Technology

Communication and Control, Environment and Management (HNICEM)

The Institute of Electrical and Electronics Engineers Inc. (IEEE) – Philippine Section

March 12-15, 2009 Traders Hotel, Manila, Philippines

“A HYBRID COLOR AND SHAPE BASED AUTOMATIC LIP

DETECTION FOR FACE IDENTIFICATION”

ABSTRACT

Here, a hybrid color and shaped based method is proposed for automatic lip detection applied to identify one’s face based on his lip feature. The study tries to combine color space based technique which is improved using shape based technique. Experimental result shows that The experimental result performs 61,4% of accuracy when tested using 500 face image of Indonesian Precision and recalls is used to evaluate the proposed technique compared to the manually segmented image when were processed in face identification system. The result show less difference than manually segmented and the color based technique can be made for the real time face identification system.

Key words : Lip Detection, Color Space, Face Identification

 

Cultural Impact on Electronic Marketing in Indonesia

In The First International Seminar on Science and Technology, Yogyakarta, 2009

Abstract

The Internet is increasingly used as a medium for providing information and also service needed by consumer. Electronic marketplaces are the latest development in business to business electronic commerce that provides simple process and promising efficiency in matching buyer and supplier then traditional marketing. It becomes the global trading communities. This paper describes the impact of cultural differences to the slow growth of electronic marketing in Indonesia. Trust and ethical issue are also the impact factor of consumer acceptance to fully automated e-market. The concepts of the cultural differences, cross-cultural marketing are discussed. The problems of applying the cross-cultural e-marketing in Indonesia are pointed out in this preliminary study and the countermeasures against these problems are put forward. As the result, culture mainly influences the customer preferences and behavior using electronic market as part of their culture.

Keywords: e-Market, Cultural Differences, Cultural Impact

 

ARTIFICIAL NEURAL NETWORK BASED SOFTWARE

ARTIFICIAL NEURAL NETWORK BASED SOFTWARE

FOR DENTAL ARCH FORM ANALYSIS

Accepted In Computer Science Journal of Petra University, Surabaya, May 2008

Abstract

In this paper, dental arch form classification system using back propagation algorithm is proposed. Some features of dental arch are selected for neural network input based on statistical analysis to dependent variables of dental arch. The system contains some features for training and testing the neural network, and for recognizing the arch form based on input parameters. The experiment uses randomly selected data set contains 190 numerical data of upper dental arch that are extracted from dental model images. The images were obtained by scanning the original 3D dental models of Indonesian patient that were collected from some orthodontic clinics in Jakarta. This experimental result shows that 76,3158% of correctness in classifying the arch form can be reached by neural network system. The system can be applied for supporting the orthodontic treatment.

Keywords : Neural Network, Dental Arch Form, Statistical Analysis

 

Developing Question Answering System Using Probabilistic Approach for Health Domain

In Proceeding Of Second International Malindo Workshop, June 2008, Malaysia

Abstract

Our study is concerned with an Indonesian question answering system used in the hospital domain. We use factoid questions which are questions regarding person, location, date, and organization. There are four steps in the question answering process, namely query type identification, document retrieval, passage scoring, and answer extraction. We use probabilistic approach to extract the answers. The results of our experiment show that correct answers are obtained for 60% of the person and organization questions, and 40% of the date and location questions.

 

ANALISIS CITRA WAJAH DENGAN HIMPUNAN FUZZY EIGEN TERBESAR

In The Proceeding of Seminar Nasional Aplikasi Teknologi Informasi 2008 (SNATI 2008 ) Yogyakarta, Juli 2008

Abstrak

Beragam metode telah dikembangkan untuk pengenalan wajah. Dalam tulisan ini akan dipaparkan metode himpunan fuzzy eigen terbesar untuk analisis citra wajah yang dapat mengekstrak ciri dalam citra. Untuk uji coba efektifitas, metode himpunan fuzzy eigen diterapkan dalam sebuah sistem identifikasi wajah. Basis data yang digunakan merupakan data sekunder yang terdiri dari citra wajah tampak depan dengan berbagai ekspresi. Hasil uji coba menunjukkan bahwa himpunan fuzzy eigen terbesar efektif mengekstrak ciri untuk perolehan citra wajah dengan nilai precision-recall rata-rata sebesar 58,8%. Hasil uji coba yang didapat menjadi landasan yang cukup kuat untuk pengembangan metode ekstraksi ciri berbasis teori fuzzy untuk identifikasi wajah yang optimal.

Keywords: Himpunan Fuzzy Eigen Terbesar, Ekstraksi Ciri, Pengenalan Wajah

 

PENYELESAIAN KOMBINATORIAL DALAM ILMU KOMPUTER

In Algoritma Journal of STMIK MDP

Abstrak : Perhitungan kombinatorial dalam aplikasi program komputer dapat dilakukan dengan menggunakan relasi rekursif. Dalam tulisan ini akan dibahas dua cara yang dapat digunakan yaitu, menggunakan struktur perulangan proses dan pemanggilan sub program. Masing- masing cara perhitungan akan dibuat sebuah bagan alir untuk menyelesaikan suatu permasalahan . Lalu hasilnya akan dianalisa dan dibandingkan mana cara yang lebih baik untuk menyelesaikan perhitungan kombinatorial.

Kata-kata kunci : Kombinatorial, relasi rekursif

 

Menuju Sum-Sel Sejahtera Melalui TIK dan e-Government

Seminar Nasional Masyarakat Telematika Sumatera Bagian Selatan

Abstrak

E-government merupakan pemerintahan digital yang dikembangkan dalam upaya peningkatan layanan kepada masyarakat untuk meningkatkan kesejahteraan rakyat. Namun pelaksanaannya belum optimal. Penerapan e-market sebagai bagian perekonomian digital yang saat ini berkembang memerlukan dukungan dan kemudahan layanan dari pemerintah. Perpaduan antara e-government yang baik dan perekonomian yang stabil akan membuka pangsa pasar global untuk distribusi hasil produksi dan pemasaran pariwisata Sumatera Selatan yang akan berdampak pada kesejahteraan rakyat di masa datang.

Kata Kunci : Teknologi Informasi dan Komunikasi, E-government, Kesejahteraan masyarakat