An Unsupervised Intelligent System to Detect Fabrication in Photocopy Document using Geometric Moments and Gray Level Co-Occurrence Matrix

Patgar, Suman V; Vasudev, T

doi:10.5120/12939-9995

Cited by 8 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Selanjutnya menjumlahkan semua elemen untuk menghitung probabilitas setiap elemen dengan cara membagi setiap elemen GLCM dengan total semua elemen [10]. Kemudian dapat dilanjutkan dengan menghitung ciri statistik dari fitur GLCM yang terdiri dari energy, contrast, variance, correlation, sum average, sum entropy, sum variance, maximum probability [11].…”

Section: Ekstraksi Ciriunclassified

Ekstraksi Pola Iris Mata Berwarna Biru dan Cokelat dengan Metode GrayLevel Cooccurrence Matrix

Mentari,

Nurhasanah,

Sanubary

2018

Prism. Fis.

View full text Add to dashboard Cite

Penelitian ekstraksi pola iris mata berwarna biru dan cokelat dengan metode graylevel coocurrence matrix (GLCM)telah dilakukan untuk mengetahui perbedaan pola setiap fitur pada GLCM terhadap perbedaan warna iris mata. Penelitian ini menggunakan data citra iris mata terdiri dari 10 citra iris mata berwarna biru dan 10 citra iris mata berwarna cokelat. Tahap preprocessing dimulai dengan memotong citra kemudian dilanjutkan dengan mengubah citra dalam bentuk aras keabuan, membuat histogram dan ekualisasi histogram untuk memperbaiki kualitas citra. Proses selanjutnya menghitung ciri statistik menggunakan gray level cooccurrence matrix (GLCM) 4 arah (0˚, 45˚, 90˚ dan 135˚) dengan jarak d=1. Parameter yang digunakan ada 8 yaituenergy, contras, variance, correlation, sum average, sum entropy, sum variance, maximum probability. Hasil yang diperoleh pada citra iris mata biru memiliki tingkat keabuan lebih besar dibandingkan dengan citra iris mata cokelat (fitur maximum probability). Tingkat perbedaan level keabuan terlihat lebih besar pada citra iris mata biru dari pada citra iris mata cokelat (sum variance). Citra iris mata biru mempunyai tingkat keabuan rata-rata paling tinggi dibandingkan citra iris mata cokelat (variance).Citra iris mata biru memiliki nilai keseragaman lebih tinggi sedangkan pada citra iris mata cokelat memiliki tingkat keabuan yang konstan (energy).Pada citra iris mata biru warna yang dihasilkan citra lebih gelap dibandingkan dengan citra iris mata cokelat citra terlihat lebih terang (contrast). Tekstur yang dimiliki citra iris mata biru lebih halus dari pada citra iris mata cokelat karena memiliki nilai kerapatan piksel yang lebih tinggi (sum average). Citra iris mata cokelat terlihat hubungan yang linear antara tingkat keabuan dari pasangan piksel dari pada citra iris mata biru (correlation). Citra iris mata cokelat memiliki level keabuan yang acak atau nilai ketidakseragaman yang lebih tinggi dibandingkan dengan citra iris mata biru (sum entropy). Tekstur yang dimiliki citra iris mata cokelat lebih besar dari pada citra iris mata biru. Maka, citra iris mata berwarna biru dan cokelat dapat dibedakan menggunakan ekstrasi ciri GLCM. Kata kunci : Ekstraksi Pola, Citra Iris Mata, GLCM

show abstract

Section: Ekstraksi Ciriunclassified

Ekstraksi Pola Iris Mata Berwarna Biru dan Cokelat dengan Metode GrayLevel Cooccurrence Matrix

Mentari,

Nurhasanah,

Sanubary

2018

Prism. Fis.

View full text Add to dashboard Cite

show abstract

“…In literature no significant effort is noticed towards research on fabricated photocopy documents except for the work of detection of fabrication in photocopy document using GLCM features [4]. In this work, attempt is made to detect fabrication of photocopy documents in which text in variable region is fabricated by putting new contents in many ways.…”

Section: Related Workmentioning

confidence: 99%

“…The next stage considers the image and segment variable regions from the document image for detection of fabrication in the segmented area [12]. The segmented part is used to detect fabrication in the variable region [4,10,13].…”

Section: Related Workmentioning

confidence: 99%

“…As the area/ region of fabrication in the document is relatively smaller, compared to entire document it is quite hard to take decision whether the document is fabricated or non-fabricated. Hence it is favorable to employ all the three methods to check for the fabrication [4,10,13]. The content in the variable region is decided as fabricated when one or more of the approaches lead to the classification as fabricated class.…”

Section: Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

A System for Detection of Fabrication in Photocopy Document

Patgar¹,

Vasudev²,

Murali³

2015

Computer Science &Amp; Information Technology ( CS &Amp; IT )

Self Cite

View full text Add to dashboard Cite

Photocopy documents are very common in our normal life. In India, people are permitted to carry and produce photocopied documents frequently, to avoid damages or losing the original documents. But this provision is misused for temporary benefits by fabricating fake photocopied documents. When a photocopied document is produced, it may be required to check for its originality. An attempt is made in this direction to detect such fabricated photocopied documents. This paper proposes an unsupervised system to detect fabrication in photocopied document. The work in this paper mainly focuses on detection of fabrication in photocopied documents in which some contents are manipulated by new contents above it using different ways. Testing is performed with a different set of collected testing samples resulted in an average detection rate of 70.14%.

show abstract

“…Further, in literature no significant effort is noticed towards research on fabricated photocopy documents except for the work of detection of fabrication in photocopy document using GLCM features [4]. In this work, attempt is made to detect fabrication of photocopy documents in which text in variable region is fabricated by putting new contents in many ways.…”

Section: Introductionmentioning

confidence: 99%

Detection of Fabrication in Photocopy Document Using Texture Features Through K-Means Clustering

Patgar¹,

Y.H²,

Vasudev³

2014

SIPIJ

Self Cite

View full text Add to dashboard Cite

show abstract

An Unsupervised Intelligent System to Detect Fabrication in Photocopy Document using Geometric Moments and Gray Level Co-Occurrence Matrix

Cited by 8 publications

References 11 publications

Ekstraksi Pola Iris Mata Berwarna Biru dan Cokelat dengan Metode GrayLevel Cooccurrence Matrix

Ekstraksi Pola Iris Mata Berwarna Biru dan Cokelat dengan Metode GrayLevel Cooccurrence Matrix

A System for Detection of Fabrication in Photocopy Document

Detection of Fabrication in Photocopy Document Using Texture Features Through K-Means Clustering

Contact Info

Product

Resources

About