Static Signature Verification Based on Texture Analysis Using Support Vector Machine

2017 ◽  
Vol 8 (2) ◽  
pp. 22-32 ◽  
Author(s):  
Subhash Chandra ◽  
Sushila Maheshkar
Keyword(s):  
Support Vector Machine ◽  
Texture Features ◽  
Signature Verification ◽  
Support Vector ◽  
Gray Level ◽  
Global Level ◽  
First Order ◽  
Svm Model ◽  
Level Information ◽  
Occurrence Matrix

Off-line hand written signature verification performs at the global level of image. It processes the gray level information in the image using statistical texture features. The textures and co-occurrence matrix are analyzed for features extraction. A first order histogram is also processed to reduce different writing ink pens used by signers. Samples of signature are trained with SVM model where random and skilled forgeries have been used for testing. Experimental results are performed on two databases: MCYT-75 and GPDS Synthetic Signature Corpus.

Segmentasi Citra menggunakan Support Vector Machine (SVM) dan Ellipsoid Region Search Strategy (ERSS) Arimoto Entropy berdasarkan Ciri Warna dan Tekstur

2016 ◽  
Vol 2 (1) ◽  
pp. 11
Author(s):  
Lukman Hakim ◽  
Siti Mutrofin ◽  
Evy Kamilah Ratnasari
Keyword(s):  
Support Vector Machine ◽  
Image Segmentation ◽  
Color Image ◽  
Support Vector ◽  
Gray Level ◽  
Segmentation Method ◽  
Local Homogeneity ◽  
Segmented Image ◽  
Svm Model ◽  
Occurrence Matrix

Abstrak Segmentasi citra merupakan suatu metode penting dalam pengolahan citra digital yang bertujuan membagi citra menjadi beberapa region yang homogen berdasarkan kriteria kemiripan tertentu. Salah satu syarat utama yang harus dimiliki suatu metode segmentasi citra yaitu menghasilkan citra boundary yang optimal.Untuk memenuhi syarat tersebut suatu metode segmentasi membutuhkan suatu klasifikasi piksel citra yang dapat memisahkan piksel secara linier dan non-linear. Pada penelitian ini, penulis mengusulkan metode segmentasi citra menggunakan SVM dan entropi Arimoto berbasis ERSS sehingga tahan terhadap derau dan mempunyai kompleksitas yang rendah untuk menghasilkan citra boundary yang optimal. Pertama, ekstraksi ciri warna dengan local homogeneity dan ciri tekstur dengan menggunakan Gray Level Co-occurrence Matrix (GLCM) yang menghasilkan beberapa fitur. Kedua, pelabelan dengan Arimoto berbasis ERSS yang digunakan sebagai kelas dalam klasifikasi. Ketiga, hasil ekstraksi fitur dan training kemudian diklasifikasi berdasarkan label dengan SVM yang telah di-training. Dari percobaan yang dilakukan menunjukkan hasil segmentasi kurang optimal dengan akurasi 69 %. Reduksi fitur perlu dilakukan untuk menghasilkan citra yang tersegmentasi dengan baik. Kata kunci: segmentasi citra, support vector machine, ERSS Arimoto Entropy, ekstraksi ciri. Abstract Image segmentation is an important tool in image processing that divides an image into homogeneous regions based on certain similarity criteria, which ideally should be meaning-full for a certain purpose. Optimal boundary is one of the main criteria that an image segmentation method should has. A classification method that can partitions pixel linearly or non-linearly is needed by an image segmentation method. We propose a color image segmentation using Support Vector Machine (SVM) classification and ERSS Arimoto entropy thresholding to get optimal boundary of segmented image that noise-free and low complexity. Firstly, the pixel-level color feature and texture feature of the image, which is used as input to SVM model (classifier), are extracted via the local homogeneity and Gray Level Co-Occurrence Matrix (GLCM). Then, determine class of classifier using Arimoto based ERSS thresholding. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation result less satisfied segmented image with 69 % accuracy. Feature reduction is needed to get an effective image segmentation. Key word: image segmentation, support vector machine, ERSS Arimoto Entropy, feature extraction.

scholarly journals Digit Classification of Majapahit Relic Inscription using GLCM-SVM

2018 ◽  
Vol 1 (2) ◽  
pp. 46
Author(s):  
Tri Septianto ◽  
Endang Setyati ◽  
Joan Santoso
Keyword(s):  
Image Processing ◽  
Support Vector Machine ◽  
Feature Extraction ◽  
Template Matching ◽  
Support Vector ◽  
Gray Level ◽  
Class 1 ◽  
Occurrence Matrix ◽  
Handwritten Recognition

A higher level of image processing usually contains some kind of classification or recognition. Digit classification is an important subfield in handwritten recognition. Handwritten digits are characterized by large variations so template matching, in general, is inefficient and low in accuracy. In this paper, we propose the classification of the digit of the year of a relic inscription in the Kingdom of Majapahit using Support Vector Machine (SVM). This method is able to cope with very large feature dimensions and without reducing existing features extraction. While the method used for feature extraction using the Gray-Level Co-Occurrence Matrix (GLCM), special for texture analysis. This experiment is divided into 10 classification class, namely: class 1, 2, 3, 4, 5, 6, 7, 8, 9, and class 0. Each class is tested with 10 data so that the whole data testing are 100 data number year. The use of GLCM and SVM methods have obtained an average of classification results about 77 %.

KLASIFIKASI TUMOR JINAK DAN TUMOR GANAS PADA CITRA MAMMOGRAM MENGGUNAKAN GRAY LEVEL CO-OCCURRENCE MATRIX (GLCM) DAN SUPPORT VECTOR MACHINE (SVM)

2021 ◽  
Vol 26 (2) ◽  
pp. 176-186
Author(s):  
Lulu Mawaddah Wisudawati
Keyword(s):  
Support Vector Machine ◽  
World Health Organization ◽  
Computer Aided Diagnosis ◽  
World Health ◽  
Support Vector ◽  
Gray Level ◽  
Computer Aided ◽  
Health Organization ◽  
Occurrence Matrix ◽  
Aided Diagnosis

Kanker payudara merupakan penyebab utama kematian pada wanita. Data Global Cancer Observatory 2018 dari World Health Organization (WHO, 2020) menunjukkan kasus kanker yang paling banyak terjadi di Indonesia adalah kanker payudara, yakni 58.256 kasus atau 16.7% dari total 348.809 kasus kanker. Mamografi merupakan teknik yang paling umum digunakan dalam mendeteksi tumor payudara menggunakan sistem sinar-X dosis rendah. Ada beberapa tipe abnormalitas dalam citra mammogram, yaitu mikrokalsifikasi dan massa. Penelitian ini bertujuan untuk meningkatkan performa sistem Computer-Aided Diagnosis (CAD) dalam mengklasifikasi tumor jinak dan tumor ganas dengan mengembangkan metode ekstraksi fitur menggunakan Gray Level Co-Occurrence Matrix (GLCM) dan metode klasifikasi menggunakan Support Vector Machine (SVM). Uji coba dilakukan dengan menggunakan database DDSM dengan 256 citra abnormal (95 tumor jinak dan 161 tumor ganas) menghasilkan nilai akurasi sebesar 83.59% dengan nilai sensitivitas dan spesifisitas 87.58% dan 76.84%. Selain itu, didapatkan nilai AUC sebesar 0.98%. Metode tersebut menunjukkan bahwa sistem memberikan hasil performa yang baik dalam mengklasifikasi tumor jinak dan tumor ganas.

scholarly journals A Novel Framework for Detection of Cervical Cancer

2018 ◽  
Vol 7 (2) ◽  
pp. 26-30
Author(s):  
V. Pushpalatha
Keyword(s):  
Cervical Cancer ◽  
Support Vector Machine ◽  
Curvelet Transform ◽  
Uterine Cervical Cancer ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Gray Level ◽  
Adaptive Support ◽  
Occurrence Matrix ◽  
Five Phases

Today, Uterine Cervical Cancer is most general form of cancer for women. Prevention of cervical cancer is possible via various screening courses. Colposcopy images of cervix are analyzed in this study for the recognition of cervical cancer. An innovative framework is suggested to correctly identify cervical cancer by employing effective pre-processing, image enhancement, and image segmentation techniques. This framework comprises of five phases, (i) Dual tree discrete wavelet transform to pre-process the image (ii) Curvelet transform and contour transform to enhance the image (iii) K-means for segmentation (iv) features computation using Gray level co-occurrence matrix (v) classification using adaptive Support vector machine. The experimental results evident that proposed technique is superior to existing methodologies.

Sign in / Sign up

Export Citation Format

Share Document