Skip to main content

iping supriana

Followers

140

Following

13

Co-authors

10

Public Views

Iping Supriana received the docteur-ingenieur degree in Informatics from the Institute National Polytechniques, Grenoble, French in 1985. He is currently a Professor of the School of Electrical and Informatic Engineering, Bandung Institute of Technology, Indonesia.His research interest include: information automation, dynamic computer graphic, image analysis, recognition system, and image interpretation. He has authored or coauthored over 50 published articles.He is the inventor and the implementer of the Digital Mark Reader (DMR). DMR is software employed for evaluating examination results automatically using computer scanning. DMR is widely used in Indonesia education institutuion.

less

University of California, Santa Barbara

Harvard University

University of British Columbia

Kansas State University

Armando Marques-Guedes

UNL - New University of Lisbon

Oxford Brookes University

Roshan Chitrakar

Nepal College of Information Technology

Graduate Center of the City University of New York

Guilherme Moerbeck

UERJ - Universidade do Estado do Rio de Janeiro / Rio de Janeiro State University

Bálint Molnár

Eötvös Loránd University

Interests

Uploads

Papers by iping supriana

Mathematical Model of Skin Colour for Face Detection

by iping supriana and Setiawan Hadi

Pemanfaatan Sistem Berbasis Pengetahuan untuk Membangun Model Sistem Akuntansi yang Adaptif

by iping supriana and I Gede Made Karma

Kriteria Keamanan Blok Cipher dan Analisis Sandi Diferensial

Teknoin, 2005

Several criterions used to determine the security measure of ciphers, have been researched for te... more Several criterions used to determine the security measure of ciphers, have been researched for tens years. Shannon recommended two concepts for designing of algorithm encryption: confusion and diffusion. These criterions have been expanded with other criterions addition like avalanche property, Strict Avalanche property, Key-dependence avalanche, sequence complexity, Binary derivatives, and Bit dependencies.

Analisis Sandi Square terhadap Advance Encryption Standard (AES)

KONSEPSI PENGEMBANGAN SISTEM INFORMASI DENGAN DUKUNGAN SISTEM INTELIGEN (Keynote Paper KNSI 2014)

Pengembangan sistem informasi saat ini dihadapkan kepada dua tantangan besar, yaitu waktu yang te... more Pengembangan sistem informasi saat ini dihadapkan kepada dua tantangan besar, yaitu waktu yang terbatas (time to market) dan fleksibilitas kebutuhan pengguna. Makalah ini akan membahas konsepsi pengembangan sistem informasi dengan dukungan sistem inteligen untuk mengkonstruksi konfigurasi sistem informasi. Strategi kunci yang digunakan adalah forward strategy, yang memanfaatkan kembali (reuse) komponen fundamental yang sudah ada yang cocok dengan spesifikasi dari pengguna. Berdasarkan spesifikasi yang menjadi masukan sistem, sistem inteligen akan menentukan domain model yang diturunkan dari struktur generik, dan menghasilkan konfigurasi sistem informasi yang akan dieksekusi oleh aktuator. Pemanfaatan konsep ini tidak hanya mempersingkat waktu, tetapi juga memberikan fleksibilitas yang tinggi dalam pengembangan sistem informasi. Dengan mengadaptasi framework sistem berbasis rule, konsep ini dapat diadaptasi untuk pengembangan sistem informasi berbagai domain.

The Alignment of Information Systems and Environmental Organizations Model in Perspective Capability

Handwriting recognition using a combination of structural elements similarity

2014 International Conference on Data and Software Engineering, Nov 1, 2014

ABSTRACT

Analisis Sandi Diferensial terhadap Full Data Encryption Standard

Seminar Nasional Aplikasi Teknologi Informasi, 2005

Abstrak DES (Data Encryption Standard) merupakan block cipher 16 ronde yang memiliki struktur Fei... more Abstrak DES (Data Encryption Standard) merupakan block cipher 16 ronde yang memiliki struktur Feistel dan memiliki masukan/keluaran 64 bit, serta memiliki kunci sepanjang 56 bit. Dengan struktur Feistel, algoritma enkripsi memiliki struktur yang sama dengan yang untuk dekripsi. Perbedaannya hanya terletak pada urutan subkey yang dimasukkan. DES memiliki fungsi F yang tidak invertible. Analisis Sandi Diferensial (ASD) adalah teknik untuk mendapatkan kunci algoritma enkripsi modern tanpa harus meminta ijin pemilik kunci. ASD dapat diterapkan terhadap bermacam-macam algoritma enkripsi modern, termasuk Data Encryption Standard (DES). ASD berusaha mendapatkan diferensial masukan yang menghasilkan diferensial keluaran dengan memiliki peluang sebesar mungkin. Untuk algoritma DES, diferensial ini berupa XOR. Pada DES, satu-satunya komponen yang tidak linear adalah kotak subtitusi. Oleh karena itu, ASD dimulai dari Kotak-S ini. Kemudian aliran diferensial ini diperluas ke komponen lainnya hingga mencapai satu ronde. Kemudian, dari satu ronde, diperluas ke ronde-ronde berikutnya hingga mencapai 16 ronde penuh.Dalam makalah ini akan ditunjukkan cara memecahkan kunci DES 56 bit 16 ronde dengan ASD. Memecahkan DES berarti bahwa kita dapat membuktikan bahwa tingkat keamanan full DES 16 ronde lebih rendah daripada yang diklaim pada waktu algoritma diumumkan. Dengan kata lain, DES dapat dipecahkan lebih cepat dari pada brute force attack. Kata kunci: Full DES, Analisis sandi diferensial, Kotak-S. __________________________________________________________________________________________ 1. PENDAHULUAN

Relation extraction with tree kernel for Indonesian sentences

2014 International Conference on Ict For Smart Society, Sep 24, 2014

ABSTRACT This paper propose of a study about kernels method for relation extraction in natural la... more ABSTRACT This paper propose of a study about kernels method for relation extraction in natural language tasks. Our study based on relation extraction using Indonesian parse tree kernel approach such as define subtree and subset tree, establish word dependency pattern and modified parse tree algorithm for testing accuracy of the dependency tree. We aim to modified the algorithm that was created by Moschitti in[2] for the evaluation of the sub tree (ST) and subset tree (SST) kernel using Indonesian sentences. The concept of Indonesian tree kernel is when production associated with n1 and n2 are different, we can avoid to evaluate delta (n1,n2) since it is 0. For experiment, we extract relation from various offline resources, with domain including academic papers in the fielsd of language practicing and science. By using 250 sentence, the highest accuracy score for node pair set &#39;Role_Staff Role owner&#39; achieved 89,2% for ST and 86,5% for SST.

Parametric Skin Distribution Modeling using Elliptical Boundary Model

Instructional Design in Serious Game for Learning Based on Inquiry and Situated Learning Theory

Advanced Science Letters, 2015

ABSTRACT Digital game for learning or Serious Game for Learning (SGfL) need to be developed and r... more ABSTRACT Digital game for learning or Serious Game for Learning (SGfL) need to be developed and refined at many level of abstraction, in particular to address concerns from education experts about aspects of learning are applied in the gaming interaction. This paper will explain about learning model that comply to be implemented in (SGfL) to make its design can be accounted for pedagogics and for high flexibility in subject/domain that be learned. Instructional design that suitable with cause-effect flow model are inquiry based learning with flexible guidance and situated learning within meaningfull learning context. Question or problem based in inquiry model was suitable with task based in flow model. Situated learning that need autothelic learning context is have same concept with immersion, especially about modeling reality. Transformation the instructional model into game design was inspired by The SIM Career. The proposed SGfL&#39;s genre is role playing and simulation of life game as profesional. TASK was transformed into working. For life, player must work. For get job position, player must have a competency certificate through Training. In working, player must complete a task. By completing the task, player learning by doing. The elements in the gameworld design adapted to the field of work, so that the player feels like working on a real-world environment. From this point can be concluded that gameworld could not be domain independent, because environment of working is dependent on the domain learned (learning context). The task completion interaction was managed like quiz or test in Moodle. It was not soo good from immersion aspect but high flexibility, so can be domain independent.

Intelligent Interface for a Knowledge-based System - Abstract

Every knowledge-based system has its own knowledge formalism depending on the problem that needs ... more Every knowledge-based system has its own knowledge formalism depending on the problem that needs solving, goal to be achieved, and proposed solution. This means the knowledge contained in the system will differ from one system to another. This also means that this knowledge cannot be used by another system, which in turn means every system must start with a learning phase right at the beginning. One of the solutions to overcoming this problem is providing a unified model that can accept all types of knowledge, which guarantees automatic interaction between the knowledge-based systems. Interaction in this paper is defined as knowledge sharing, integration, and transfer from one system to another. This research provides a model and conducts a test on interaction capability. It will help to accelerate the establishment of a new knowledge-based system because it does not need knowledge initialization.

Mathematical Model of Skin Colour for Face Detection

Skin colour in digital image is important element that is very useful for preprocessing task in s... more Skin colour in digital image is important element that is very useful for preprocessing task in skin-based automatic image detection. In this paper, skin colour was investigated and its representation in several colour spaces has been explored. A mathematical model for the representation has been developed and successfully implemented for automatic single frontal face detection conjuncted with mathematics morphological and segmentation image processing filters and simple 4-neigbourhood image measurement algorithm. The experiment has been conducted based from our proposed method using face database images that have been collected from several sources, such as standard FERET Colour face database and local native face database.

Makalah Nomor: KNSI-402 FAKTOR PERILAKU MANUSIA DALAM KOLABORASI PENGEMBANGAN PERANGKAT LUNAK

Keberhasilan proyek pengembangan perangkat lunak masih relatif kecil jika dibandingkan dengan keb... more Keberhasilan proyek pengembangan perangkat lunak masih relatif kecil jika dibandingkan dengan keberhasilan proyek dibidang lain. Kualitas dan kecepatan proyek perangkat lunak sangat tergantung pada faktor sumberdaya manusia. Oleh karena itu pada makalah ini akan dibahas mengenai faktor manusia khusunya mengenai perilaku dalam kolaborasi pengembangan perangkat lunak sebagai kunci kesuksesan pengembangan proyek perangkat lunak. Tujuan makalah ini adalah menentukan properti perilaku manusia dalam melakukan kolaborasi pengembangan perangkat lunak. Properti perilaku tersebut akan di kaitkan dengan kualitas produk, dalam hal ini adalah kualitas intrinsik produk.Dengan merumuskan properti perilaku manusia tersebut diharapkan dapat digunakan untuk memilih anggota tim yang tepat ataupun untuk menentukan metode kolaborasi yang tepat untuk suatu tim yang sudah ditentukan sehingga dapat mencapai kesuksesan proyek. Adapaun metode yang digunakan dalam menentukan properti perilaku ini dengan berdasarkan framework perilaku Human Behavior Representation (HBR) yang diturunkan dalam metode kolaborasi dan proses pengembangan perangkat lunak. Hasil penelitan dalam makalah ini adalah pemetaan perilaku dalam kolaborasi perangkat lunak yang meliputi properti komunikasi, koordinasi, interaksi, kemampuan menggunakan tool, kondisi psikologi (motivasi dan kedekatan), serta pengalaman anggota tim. Berdasarkan uji coba dalam beberapa tim kecil disimpulkan bahwa peranserta anggota berpengalaman dalam proses perancangan dan kemampuan rata-rata anggota tim yang tinggi akan meberikan kualitas kode (kualitas instrinsik produk). Sebagai kelanjutan dari hasil penelitian ini, dapat dilakukan penelitian lanjutan dengan menentukan metode pengukuran properti perilaku dalam melakukan kolaborasi pengembangan perangkat lunak dengan lebih baik sehingga semua aspek perilaku dapat terukur secara kuantitatif.

Structural offline handwriting character recognition using levenshtein distance

2015 International Conference on Electrical Engineering and Informatics (ICEEI), 2015

Research in offline handwriting recognition for unconstrained text remains a difficult challenge.... more Research in offline handwriting recognition for unconstrained text remains a difficult challenge. Some problems such as noise in image, skew of text, cursive letters, and various handwriting style is still an open problem. Many method has been researched to solve those problems, such as k-NN, Neural Network, SVM and HMM. And to improve the recognition result, there are many methods can be implemented in the prerocessing stage. One of them is Kimura's method for slant correction that using chain code for character slant prediction. Those method consumes time and resource in its computation, meanwhile the accuracy is not improved significantly. Therefore, this paper propose to create handwritten character into graph with string representation based on structural approach. The purpose is to provide ability in improving recognition accuracy without relying on normalisation technique. The similarity distance between graphs measured using levenshtein distance. Experiment conducted to recognize handwritten upper-case letters and digits character images which taken from ETL-1 AIST databases. Levenshtein distance has an accuracy of 84.69% on digits and 67.01% on alphabet with 5% size of data for training and value 10 for string representation length. As a comparison, the Kimura's method are implemented for slant correction which results in a reduction of accuracy until 6%. Comparisons also made with some of previous work.

Ekstraksi Bangun Poligonal Dan Optimasi Deskripsinya

Abstrak-Dalam melakukan vektorisasi pada citra-citra nonsintesis, misalnya foto, ukuran citra vek... more Abstrak-Dalam melakukan vektorisasi pada citra-citra nonsintesis, misalnya foto, ukuran citra vektor bisa jadi sangat besar, terkadang bahkan melebihi ukuran citra rasternya. Hal ini dapat menimbulkan masalah dalam proses rasterisasi maupun penyimpanan citra vektor tersebut. Oleh karena itu, penelitian ini berusaha mengurangi ukuran citra vektor dengan meminimalkan redundansi pada definisinya, yaitu semua sisi yang memisahkan 2 bangun didefinisikan 2 kali. Solusi yang ditawarkan adalah dengan menumpukkan bangun-bangun tersebut sehingga bangun yang berada di bawah tidak perlu mendefinisikan sebagian sisinya. Hal ini dilakukan dengan membangun hierarki antar bangun dan mengembangkan algoritma untuk menyederhanakan bangun yang tertumpuk tanpa mengubah hasil rasterisasi secara visual.

Pengembangan Sistem Aplikasi Grafik Multi Domen

Mécanisme prédictif d'évaluation des caractéristiques géométriques des circuits VLSI

Sistem Manajemen Transformasi Gramatika

Aspek 3D

Mathematical Model of Skin Colour for Face Detection

by iping supriana and Setiawan Hadi

Pemanfaatan Sistem Berbasis Pengetahuan untuk Membangun Model Sistem Akuntansi yang Adaptif

by iping supriana and I Gede Made Karma

Kriteria Keamanan Blok Cipher dan Analisis Sandi Diferensial

Teknoin, 2005

Several criterions used to determine the security measure of ciphers, have been researched for te... more Several criterions used to determine the security measure of ciphers, have been researched for tens years. Shannon recommended two concepts for designing of algorithm encryption: confusion and diffusion. These criterions have been expanded with other criterions addition like avalanche property, Strict Avalanche property, Key-dependence avalanche, sequence complexity, Binary derivatives, and Bit dependencies.

Analisis Sandi Square terhadap Advance Encryption Standard (AES)

KONSEPSI PENGEMBANGAN SISTEM INFORMASI DENGAN DUKUNGAN SISTEM INTELIGEN (Keynote Paper KNSI 2014)

Pengembangan sistem informasi saat ini dihadapkan kepada dua tantangan besar, yaitu waktu yang te... more Pengembangan sistem informasi saat ini dihadapkan kepada dua tantangan besar, yaitu waktu yang terbatas (time to market) dan fleksibilitas kebutuhan pengguna. Makalah ini akan membahas konsepsi pengembangan sistem informasi dengan dukungan sistem inteligen untuk mengkonstruksi konfigurasi sistem informasi. Strategi kunci yang digunakan adalah forward strategy, yang memanfaatkan kembali (reuse) komponen fundamental yang sudah ada yang cocok dengan spesifikasi dari pengguna. Berdasarkan spesifikasi yang menjadi masukan sistem, sistem inteligen akan menentukan domain model yang diturunkan dari struktur generik, dan menghasilkan konfigurasi sistem informasi yang akan dieksekusi oleh aktuator. Pemanfaatan konsep ini tidak hanya mempersingkat waktu, tetapi juga memberikan fleksibilitas yang tinggi dalam pengembangan sistem informasi. Dengan mengadaptasi framework sistem berbasis rule, konsep ini dapat diadaptasi untuk pengembangan sistem informasi berbagai domain.

The Alignment of Information Systems and Environmental Organizations Model in Perspective Capability

Handwriting recognition using a combination of structural elements similarity

2014 International Conference on Data and Software Engineering, Nov 1, 2014

ABSTRACT

Analisis Sandi Diferensial terhadap Full Data Encryption Standard

Seminar Nasional Aplikasi Teknologi Informasi, 2005

Abstrak DES (Data Encryption Standard) merupakan block cipher 16 ronde yang memiliki struktur Fei... more Abstrak DES (Data Encryption Standard) merupakan block cipher 16 ronde yang memiliki struktur Feistel dan memiliki masukan/keluaran 64 bit, serta memiliki kunci sepanjang 56 bit. Dengan struktur Feistel, algoritma enkripsi memiliki struktur yang sama dengan yang untuk dekripsi. Perbedaannya hanya terletak pada urutan subkey yang dimasukkan. DES memiliki fungsi F yang tidak invertible. Analisis Sandi Diferensial (ASD) adalah teknik untuk mendapatkan kunci algoritma enkripsi modern tanpa harus meminta ijin pemilik kunci. ASD dapat diterapkan terhadap bermacam-macam algoritma enkripsi modern, termasuk Data Encryption Standard (DES). ASD berusaha mendapatkan diferensial masukan yang menghasilkan diferensial keluaran dengan memiliki peluang sebesar mungkin. Untuk algoritma DES, diferensial ini berupa XOR. Pada DES, satu-satunya komponen yang tidak linear adalah kotak subtitusi. Oleh karena itu, ASD dimulai dari Kotak-S ini. Kemudian aliran diferensial ini diperluas ke komponen lainnya hingga mencapai satu ronde. Kemudian, dari satu ronde, diperluas ke ronde-ronde berikutnya hingga mencapai 16 ronde penuh.Dalam makalah ini akan ditunjukkan cara memecahkan kunci DES 56 bit 16 ronde dengan ASD. Memecahkan DES berarti bahwa kita dapat membuktikan bahwa tingkat keamanan full DES 16 ronde lebih rendah daripada yang diklaim pada waktu algoritma diumumkan. Dengan kata lain, DES dapat dipecahkan lebih cepat dari pada brute force attack. Kata kunci: Full DES, Analisis sandi diferensial, Kotak-S. __________________________________________________________________________________________ 1. PENDAHULUAN

Relation extraction with tree kernel for Indonesian sentences

2014 International Conference on Ict For Smart Society, Sep 24, 2014

ABSTRACT This paper propose of a study about kernels method for relation extraction in natural la... more ABSTRACT This paper propose of a study about kernels method for relation extraction in natural language tasks. Our study based on relation extraction using Indonesian parse tree kernel approach such as define subtree and subset tree, establish word dependency pattern and modified parse tree algorithm for testing accuracy of the dependency tree. We aim to modified the algorithm that was created by Moschitti in[2] for the evaluation of the sub tree (ST) and subset tree (SST) kernel using Indonesian sentences. The concept of Indonesian tree kernel is when production associated with n1 and n2 are different, we can avoid to evaluate delta (n1,n2) since it is 0. For experiment, we extract relation from various offline resources, with domain including academic papers in the fielsd of language practicing and science. By using 250 sentence, the highest accuracy score for node pair set &#39;Role_Staff Role owner&#39; achieved 89,2% for ST and 86,5% for SST.

Parametric Skin Distribution Modeling using Elliptical Boundary Model

Instructional Design in Serious Game for Learning Based on Inquiry and Situated Learning Theory

Advanced Science Letters, 2015

ABSTRACT Digital game for learning or Serious Game for Learning (SGfL) need to be developed and r... more ABSTRACT Digital game for learning or Serious Game for Learning (SGfL) need to be developed and refined at many level of abstraction, in particular to address concerns from education experts about aspects of learning are applied in the gaming interaction. This paper will explain about learning model that comply to be implemented in (SGfL) to make its design can be accounted for pedagogics and for high flexibility in subject/domain that be learned. Instructional design that suitable with cause-effect flow model are inquiry based learning with flexible guidance and situated learning within meaningfull learning context. Question or problem based in inquiry model was suitable with task based in flow model. Situated learning that need autothelic learning context is have same concept with immersion, especially about modeling reality. Transformation the instructional model into game design was inspired by The SIM Career. The proposed SGfL&#39;s genre is role playing and simulation of life game as profesional. TASK was transformed into working. For life, player must work. For get job position, player must have a competency certificate through Training. In working, player must complete a task. By completing the task, player learning by doing. The elements in the gameworld design adapted to the field of work, so that the player feels like working on a real-world environment. From this point can be concluded that gameworld could not be domain independent, because environment of working is dependent on the domain learned (learning context). The task completion interaction was managed like quiz or test in Moodle. It was not soo good from immersion aspect but high flexibility, so can be domain independent.

Intelligent Interface for a Knowledge-based System - Abstract

Every knowledge-based system has its own knowledge formalism depending on the problem that needs ... more Every knowledge-based system has its own knowledge formalism depending on the problem that needs solving, goal to be achieved, and proposed solution. This means the knowledge contained in the system will differ from one system to another. This also means that this knowledge cannot be used by another system, which in turn means every system must start with a learning phase right at the beginning. One of the solutions to overcoming this problem is providing a unified model that can accept all types of knowledge, which guarantees automatic interaction between the knowledge-based systems. Interaction in this paper is defined as knowledge sharing, integration, and transfer from one system to another. This research provides a model and conducts a test on interaction capability. It will help to accelerate the establishment of a new knowledge-based system because it does not need knowledge initialization.

Mathematical Model of Skin Colour for Face Detection

Skin colour in digital image is important element that is very useful for preprocessing task in s... more Skin colour in digital image is important element that is very useful for preprocessing task in skin-based automatic image detection. In this paper, skin colour was investigated and its representation in several colour spaces has been explored. A mathematical model for the representation has been developed and successfully implemented for automatic single frontal face detection conjuncted with mathematics morphological and segmentation image processing filters and simple 4-neigbourhood image measurement algorithm. The experiment has been conducted based from our proposed method using face database images that have been collected from several sources, such as standard FERET Colour face database and local native face database.

Makalah Nomor: KNSI-402 FAKTOR PERILAKU MANUSIA DALAM KOLABORASI PENGEMBANGAN PERANGKAT LUNAK

Keberhasilan proyek pengembangan perangkat lunak masih relatif kecil jika dibandingkan dengan keb... more Keberhasilan proyek pengembangan perangkat lunak masih relatif kecil jika dibandingkan dengan keberhasilan proyek dibidang lain. Kualitas dan kecepatan proyek perangkat lunak sangat tergantung pada faktor sumberdaya manusia. Oleh karena itu pada makalah ini akan dibahas mengenai faktor manusia khusunya mengenai perilaku dalam kolaborasi pengembangan perangkat lunak sebagai kunci kesuksesan pengembangan proyek perangkat lunak. Tujuan makalah ini adalah menentukan properti perilaku manusia dalam melakukan kolaborasi pengembangan perangkat lunak. Properti perilaku tersebut akan di kaitkan dengan kualitas produk, dalam hal ini adalah kualitas intrinsik produk.Dengan merumuskan properti perilaku manusia tersebut diharapkan dapat digunakan untuk memilih anggota tim yang tepat ataupun untuk menentukan metode kolaborasi yang tepat untuk suatu tim yang sudah ditentukan sehingga dapat mencapai kesuksesan proyek. Adapaun metode yang digunakan dalam menentukan properti perilaku ini dengan berdasarkan framework perilaku Human Behavior Representation (HBR) yang diturunkan dalam metode kolaborasi dan proses pengembangan perangkat lunak. Hasil penelitan dalam makalah ini adalah pemetaan perilaku dalam kolaborasi perangkat lunak yang meliputi properti komunikasi, koordinasi, interaksi, kemampuan menggunakan tool, kondisi psikologi (motivasi dan kedekatan), serta pengalaman anggota tim. Berdasarkan uji coba dalam beberapa tim kecil disimpulkan bahwa peranserta anggota berpengalaman dalam proses perancangan dan kemampuan rata-rata anggota tim yang tinggi akan meberikan kualitas kode (kualitas instrinsik produk). Sebagai kelanjutan dari hasil penelitian ini, dapat dilakukan penelitian lanjutan dengan menentukan metode pengukuran properti perilaku dalam melakukan kolaborasi pengembangan perangkat lunak dengan lebih baik sehingga semua aspek perilaku dapat terukur secara kuantitatif.

Structural offline handwriting character recognition using levenshtein distance

2015 International Conference on Electrical Engineering and Informatics (ICEEI), 2015

Research in offline handwriting recognition for unconstrained text remains a difficult challenge.... more Research in offline handwriting recognition for unconstrained text remains a difficult challenge. Some problems such as noise in image, skew of text, cursive letters, and various handwriting style is still an open problem. Many method has been researched to solve those problems, such as k-NN, Neural Network, SVM and HMM. And to improve the recognition result, there are many methods can be implemented in the prerocessing stage. One of them is Kimura's method for slant correction that using chain code for character slant prediction. Those method consumes time and resource in its computation, meanwhile the accuracy is not improved significantly. Therefore, this paper propose to create handwritten character into graph with string representation based on structural approach. The purpose is to provide ability in improving recognition accuracy without relying on normalisation technique. The similarity distance between graphs measured using levenshtein distance. Experiment conducted to recognize handwritten upper-case letters and digits character images which taken from ETL-1 AIST databases. Levenshtein distance has an accuracy of 84.69% on digits and 67.01% on alphabet with 5% size of data for training and value 10 for string representation length. As a comparison, the Kimura's method are implemented for slant correction which results in a reduction of accuracy until 6%. Comparisons also made with some of previous work.

Ekstraksi Bangun Poligonal Dan Optimasi Deskripsinya

Abstrak-Dalam melakukan vektorisasi pada citra-citra nonsintesis, misalnya foto, ukuran citra vek... more Abstrak-Dalam melakukan vektorisasi pada citra-citra nonsintesis, misalnya foto, ukuran citra vektor bisa jadi sangat besar, terkadang bahkan melebihi ukuran citra rasternya. Hal ini dapat menimbulkan masalah dalam proses rasterisasi maupun penyimpanan citra vektor tersebut. Oleh karena itu, penelitian ini berusaha mengurangi ukuran citra vektor dengan meminimalkan redundansi pada definisinya, yaitu semua sisi yang memisahkan 2 bangun didefinisikan 2 kali. Solusi yang ditawarkan adalah dengan menumpukkan bangun-bangun tersebut sehingga bangun yang berada di bawah tidak perlu mendefinisikan sebagian sisinya. Hal ini dilakukan dengan membangun hierarki antar bangun dan mengembangkan algoritma untuk menyederhanakan bangun yang tertumpuk tanpa mengubah hasil rasterisasi secara visual.

Pengembangan Sistem Aplikasi Grafik Multi Domen

Mécanisme prédictif d'évaluation des caractéristiques géométriques des circuits VLSI

Sistem Manajemen Transformasi Gramatika

Aspek 3D