Automatic person identification system using handwritten signatures

Abushariah, Ahmad A. M.; Gunawan, Teddy Surya; Chebil, Jalel; Abushariah, Mohammad A. M.

doi:10.1109/iccce.2012.6271249

Cited by 15 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penelitian pengenalan tulisan tangan telah dilakukan dengan berbabagi teknik.Mohammed dan Shamsuddin menggunakan invariant discretization untuk mengenali pola tulisan tangan pada pasangan kembar.Penelitian tersebut menujukkan bahwa pasangan kembar memiliki pola tulisan tangan yang berbeda (Mohammed dan Shamsuddin, 2012).Discrete Wavelet Transform juga terlah berhasil digunakan untuk mengektraksi fitur pergerakan pena dan pergerakan sudut untuk mengenali pola tulisan tangan (Fahmy, 2010). Bertolini et almenggunakan local binary patterns dan local phase quantization untuk mengekstraski ciri tektur pada tulisan tangan (Bertolini et al, 2013).Pengenalan tulisan tangan yang dilakukan oleh Abushariah et al menggunakan global fitur dan Neural Network menghasilkan akurasi 53% -79%.Pernelitian tersebut juga menghasilkan akurasi 81% dengan menggunakan algoritma KNN (Abushariah et al, 2012). Beberapa penelitian telah dilakukan untuk mengdentifikasi penulis melalui pola tulisan tangan.…”

Section: Studi Literaturunclassified

Identifikasi Penulis Melalui Pola Tulisan Tangan Menggunakan Algoritma Support Vector Machine

Handhayani

2017

JMSTKIK

View full text Add to dashboard Cite

Tulisan tangan merupakan ciri biometrik karena setiap orang memiliki pola tulisan tangan yang unik. Keunikan tersebut dapat dimanfaatkan sebagai identitasbiometrik. Pada penelitian ini, peneliti menggunakan algoritma Support Vector Machine beserta fitur GLCM dan Histogram untuk melakukan pengenalan pola tulisan tangan. Pengenalan pola tulisan tangan tersebut digunakan untuk mengidentifkasi penulisnya. Eksperimen dilakukan dengan menggunakan data citra tulisan tangan dari 47 respoden. Pembagian data latih dan data uji secara acak dengan perbandingan 70%:30%. Pada eskperimen pertama, identifikasi penulis melalui pola tulisan tangan dilakukan dengan membandingkan pola tulisan dari setiap responden secara berpasangan. Support Vector Machine kernel linear berhasil mengidentifikasi penulis dengan rata-rata akurasi 99%. Pada eksperimen ke dua, identifikasi penulis dilakukan menggunkan keseluruhan data. Pada eksperimen ini, Support Vector Machine kernel linear menghasilkan rata-rata akurasi 93.5%.Kata kunci: pengenalan tulisan tangan, SVM, GLCM, Histogram

show abstract

Section: Studi Literaturunclassified

Identifikasi Penulis Melalui Pola Tulisan Tangan Menggunakan Algoritma Support Vector Machine

Handhayani

2017

JMSTKIK

View full text Add to dashboard Cite

show abstract

“…The database consists of 663 Arabic words and in a total of 367 sentences where each sentence is made up of 2 up to 9 words [6]. Another data corpus that has been developed by Abushariah et al [4] consists of 415 Arabic statements. The majority of the statements were recorded by Alghamdi et al [6] and another 48 sentences were added based on 51 Arabic mother tongue individuals that comprised of 23 males and 28 females.…”

Section: IImentioning

confidence: 99%

“…But this area of research is still lack of contributed corpuses and that leads to lack of data to train Arabic ASR. As reported by Abushariah et al [4], written corpuses are much more than spoken corpuses which mean that the spoken training data needs more contributions which can assist researchers to explore unrevealed Arabic Speech Recognition (ASR) area especially for Muslims who are Non-native Arabic speakers.…”

Section: Introductionmentioning

confidence: 96%

Arabic letters corpus based Malay speaker-independent

Almisreb

Abidin

Tahir

2013

2013 IEEE 3rd International Conference on System Engineering and Technology

View full text Add to dashboard Cite

Arabic language is used as a second language by a wide category of Muslims for reciting the Holy book of Muslims (Qur'an). In this paper, a description of an effective and usable Arabic letters corpus uttered by Malay speakers. This corpus can be used to study the properties and the differences of pronunciations for non native. The designed corpus consists of 1400 samples recorded by 50 Malay individuals (25 males and 25 females). The corpus is recorded using low sensitive device with Zero-Crossing Rate used for removing the noise and sustained only the significant portion of speech signal with 11025 Hz as sampling rate. This database will be the pioneer corpuses database in speech recognition specifically for Malay community.

show abstract

“…The result of classification depends on the result given during feature extraction process. The ultimate goal in this classification process is eventually able to divide data by the corresponding class [17]. Classification is the last step required to perform signature recognition [18].…”

Section: Classification Of Signaturementioning

confidence: 99%

“…Neural Network has many layers are that are confined to reduce the time to solve the existing problems [17]. Multilayer Perceptron is an example of Artificial Neural Network (ANN) that is typically used to provide solutions to different problems, for example for pattern recognition and interpolation [19].…”

Section: A Multi Layer Perceptron (Mlp)mentioning

confidence: 99%

A comparative study on signature recognition

Ratri

Nugroho

Adji

2014

2014 the 1st International Conference on Information Technology, Computer, and Electrical Engineering

View full text Add to dashboard Cite

Contour and shape are the major point for signature recognition. There are a few approaches that have been used for shape detection, particularly to signature recognition. Combination methods of geometric features such as ratio, contour, shape or moment like Zernike moment, Moment Invariants (Hu) usually have been used to identifY the signature. One method never been used for signature recognition, Polar Fourier Transform. In this paper, a comparative study is conducted to compare three methods, Moment Invariants (Hu), Zernike Moment, and Polar Fourier Transform (PFT). Support Vector Machine (SVM) and Multilayer Perceptron (MLP) are used to classifY 20 person data set in each of which consists of 15 genuine signatures and 15 forgery signatures. The result shows that the methods using PFT and SVM achieves accuracy of 86.67%. Whilst the computational time of SVM is faster than MLP. The SVM method had an average value of 0.012 seconds for computational time.

show abstract

Automatic person identification system using handwritten signatures

Cited by 15 publications

References 16 publications

Identifikasi Penulis Melalui Pola Tulisan Tangan Menggunakan Algoritma Support Vector Machine

Identifikasi Penulis Melalui Pola Tulisan Tangan Menggunakan Algoritma Support Vector Machine

Arabic letters corpus based Malay speaker-independent

A comparative study on signature recognition

Contact Info

Product

Resources

About