scholarly journals An Improved Geo-Textural Based Feature Extraction Vector For Offline Signature Verification

2019 ◽  
pp. 1-14 ◽  
Author(s):  
Kennedy Gyimah ◽  
Justice Kwame Appati ◽  
Kwaku Darkwah ◽  
Kwabena Ansah
Keyword(s):  
Feature Extraction ◽  
Feature Vector ◽  
Least Square Method ◽  
Kernel Functions ◽  
Least Square ◽  
Signature Verification ◽  
Support Vector ◽  
Offline Signature Verification ◽  
Occurrence Matrix ◽  
Handwritten Signature

In the field of pattern recognition, automatic handwritten signature verification is of the essence. The uniqueness of each person’s signature makes it a preferred choice of human biometrics. However, the unavoidable side-effect is that they can be misused to feign data authenticity. In this paper, we present an improved feature extraction vector for offline signature verification system by combining features of grey level occurrence matrix (GLCM) and properties of image regions. In evaluating the performance of the proposed scheme, the resultant feature vector is tested on a support vector machine (SVM) with varying kernel functions. However, to keep the parameters of the kernel functions optimized, the sequential minimal optimization (SMO) and the least square method was used. Results of the study explained that the radial basis function (RBF) coupled with SMO best support the improved featured vector proposed.

FREEMAN CHAIN CODE AS REPRESENTATION IN OFFLINE SIGNATURE VERIFICATION SYSTEM

2016 ◽  
Vol 78 (8-2) ◽  
Author(s):  
Aini Najwa Azmi ◽  
Dewi Nasien ◽  
Azurah Abu Samah
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Rejection Rate ◽  
Data Representation ◽  
Signature Verification ◽  
Global Features ◽  
Chain Code ◽  
Verification System ◽  
Offline Signature Verification ◽  
Handwritten Signature

Over recent years, there has been an explosive growth of interest in the pattern recognition. For example, handwritten signature is one of human biometric that can be used in many areas in terms of access control and security. However, handwritten signature is not a uniform characteristic such as fingerprint, iris or vein. It may change to several factors; mood, environment and age. Signature Verification System (SVS) is a part of pattern recognition that can be a solution for such situation. The system can be decomposed into three stages: data acquisition and preprocessing, feature extraction and verification. This paper presents techniques for SVS that uses Freeman chain code (FCC) as data representation. In the first part of feature extraction stage, the FCC was extracted by using boundary-based style on the largest contiguous part of the signature images. The extracted FCC was divided into four, eight or sixteen equal parts. In the second part of feature extraction, six global features were calculated. Finally, verification utilized k-Nearest Neighbour (k-NN) to test the performance. MCYT bimodal database was used in every stage in the system. Based on our systems, the best result achieved was False Rejection Rate (FRR) 14.67%, False Acceptance Rate (FAR) 15.83% and Equal Error Rate (EER) 0.43% with shortest computation, 7.53 seconds and 47 numbers of features.

scholarly journals Writer Independent Manipuri Offline Signature Verification using Transfer Learning Technique of Convolutional Neural Network

2019 ◽  
Vol 9 (1S) ◽  
pp. 76-80
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Learning Ability ◽  
Signature Verification ◽  
Support Vector ◽  
Svm Classifier ◽  
Powerful Learning ◽  
Offline Signature Verification ◽  
Learning Technique ◽  
Handwritten Signature

Automatic Signature Verification system is used to verify whether a signature is genuine or forged. Forged Signatures are those signatures that a person produced by imitating the signature of another person. Automatic Signature Verification is very important as a person’s handwritten signature is used everywhere to authenticate themselves and there is not very much difference between a genuine signature and the imitation of it, i.e. a forged signature. In this work, signature verification is done using different pre-trained Convolutional Neural Networks (CNNs). Convolutional Neural Network has powerful learning ability, and it can be used to distinguish between a genuine and a forged signature automatically. In this experiment, Manipuri signature dataset was used, the dataset was prepared originally and it contains 729 genuine signatures and 243 forged signatures. Features were extracted from pre-trained networks and classification was done using binary Support Vector Machine (SVM) classifier and the performances of the networks were compared. And according to the experiment we achieved a classification accuracy of 84.7 using VGG19 features, accuracy of 86.8 using VGG16 features and accuracy of 81.9 using Alexnet features.

scholarly journals The regression model for the procedure of correction of photos damaged by backlighting

2019 ◽  
pp. 326-333
Author(s):  
A V Goncharova ◽  
I V Safonov ◽  
I A Romanov
Keyword(s):  
Random Forest ◽  
Regression Model ◽  
Least Square Method ◽  
Least Square ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Local Contrast ◽  
Initial Model ◽  
Occurrence Matrix ◽  
Quality Assessments

In the paper, we propose an approach for selection a correction parameter for images damaged by backlighting. We consider the photos containing underexposed areas due to backlit conditions. Such areas are dark and have poorly discernible details. The correction parameter controls the level of amplification of local contrast in shadow tones. Besides, the correction parameter can be considered as a quality estimation factor for such photos. For an automatic selection of the correction parameter, we apply regression by supervised machine learning. We propose new features calculated from the co-occurrence matrix for the training of the regression model. We compare the performance of the following techniques: the least square method, support vector machine, random forest, CART, random forest, two shallow neural networks as well as blending and staking of several models. We apply two-stage approach for the collection of a big dataset for training: initial model is trained on a manually labeled dataset containing about two hundred of photos, after that we use the initial model for searching for photos damaged by backlit in social networks having public API. Such approach allowed to collect about 1000 photos in conjunction with their preliminary quality assessments that were corrected by experts if it was necessary. In addition, we investigate an application of several well-known blind quality metrics for the estimation of photos affected by backlit.

scholarly journals Offline Signature Verification System Using SVM Classifier with Image Pre-processing Steps and SURF Algorithm

2021 ◽  
Vol 2107 (1) ◽  
pp. 012069
Author(s):  
Li Wen Goon ◽  
Swee Kheng Eng
Keyword(s):  
Feature Extraction ◽  
Noise Removal ◽  
Signature Verification ◽  
Support Vector ◽  
Svm Classifier ◽  
Speeded Up Robust Features ◽  
Verification System ◽  
Offline Signature Verification ◽  
Average Accuracy ◽  
Processing Steps

Abstract A signature is a mark or name that represents the identity of the people and the Signature Verification System (SVS) is used to validate the identity of people. The signature verification system is mostly used for bank cheques, vouchers, intelligence agencies and others. There are two types of SVS which are online and offline signature verification systems. The paper deals with an offline signature verification system. The proposed system consists of four main stages, (i) image acquisition, (ii) image pre-processing, (iii) feature extraction and (iv) classification. The image pre-processing steps involved binarization, noise removal using Gaussian filter and image resizing and thinning. In the feature extraction stage, Bag-of-Features with the Speeded Up Robust Features (SURF) extractor was utilized. In the third stage, the Support Vector Machine (SVM) classifier is used. Lastly, the confusion matrix and the verification rate were used to evaluate the performance of the classifier. In this paper, we implement and compare the performance of the signature verification system without entering the user ID and the signature verification system entering the user ID. For the ratio of 75% and 25% of the training and testing, respectively, the average accuracy for the signature verification system without entering the user ID is 71.36%, whereas the average accuracy for the signature verification system entering the user ID is 79.55%.

scholarly journals Offline Signature Identification and Verification Based on Capsule Representations

2020 ◽  
Vol 20 (5) ◽  
pp. 60-67
Author(s):  
Dilara Gumusbas ◽  
Tulay Yildirim
Keyword(s):  
Feature Extraction ◽  
Daily Life ◽  
Extraction Methods ◽  
Signature Verification ◽  
Verification Task ◽  
Feature Representations ◽  
Automatic Feature Extraction ◽  
Offline Signature Verification ◽  
Orientation Information ◽  
Trained Network

AbstractOffline signature is one of the frequently used biometric traits in daily life and yet skilled forgeries are posing a great challenge for offline signature verification. To differentiate forgeries, a variety of research has been conducted on hand-crafted feature extraction methods until now. However, these methods have recently been set aside for automatic feature extraction methods such as Convolutional Neural Networks (CNN). Although these CNN-based algorithms often achieve satisfying results, they require either many samples in training or pre-trained network weights. Recently, Capsule Network has been proposed to model with fewer data by using the advantage of convolutional layers for automatic feature extraction. Moreover, feature representations are obtained as vectors instead of scalar activation values in CNN to keep orientation information. Since signature samples per user are limited and feature orientations in signature samples are highly informative, this paper first aims to evaluate the capability of Capsule Network for signature identification tasks on three benchmark databases. Capsule Network achieves 97 96, 94 89, 95 and 91% accuracy on CEDAR, GPDS-100 and MCYT databases for 64×64 and 32×32 resolutions, which are lower than usual, respectively. The second aim of the paper is to generalize the capability of Capsule Network concerning the verification task. Capsule Network achieves average 91, 86, and 89% accuracy on CEDAR, GPDS-100 and MCYT databases for 64×64 resolutions, respectively. Through this evaluation, the capability of Capsule Network is shown for offline verification and identification tasks.

scholarly journals MATCHING AERIAL IMAGES TO 3D BUILDING MODELS BASED ON CONTEXT-BASED GEOMETRIC HASHING

2016 ◽  
Vol III-1 ◽  
pp. 17-23 ◽  
Author(s):  
J. Jung ◽  
K. Bang ◽  
G. Sohn ◽  
C. Armenakis
Keyword(s):  
Feature Extraction ◽  
Texture Mapping ◽  
Least Square Method ◽  
Least Square ◽  
Aerial Images ◽  
Single Image ◽  
Registration Method ◽  
Geometric Hashing ◽  
Building Models ◽  
Corner Points

In this paper, a new model-to-image framework to automatically align a single airborne image with existing 3D building models using geometric hashing is proposed. As a prerequisite process for various applications such as data fusion, object tracking, change detection and texture mapping, the proposed registration method is used for determining accurate exterior orientation parameters (EOPs) of a single image. This model-to-image matching process consists of three steps: 1) feature extraction, 2) similarity measure and matching, and 3) adjustment of EOPs of a single image. For feature extraction, we proposed two types of matching cues, edged corner points representing the saliency of building corner points with associated edges and contextual relations among the edged corner points within an individual roof. These matching features are extracted from both 3D building and a single airborne image. A set of matched corners are found with given proximity measure through geometric hashing and optimal matches are then finally determined by maximizing the matching cost encoding contextual similarity between matching candidates. Final matched corners are used for adjusting EOPs of the single airborne image by the least square method based on co-linearity equations. The result shows that acceptable accuracy of single image's EOP can be achievable by the proposed registration approach as an alternative to labour-intensive manual registration process.

scholarly journals Copy Move Forgery Detection Through Differential Excitation Component-Based Texture Features

2020 ◽  
Vol 12 (3) ◽  
pp. 27-44
Author(s):  
Gulivindala Suresh ◽  
Chanamallu Srinivasa Rao
Keyword(s):  
Feature Vector ◽  
Texture Feature ◽  
Texture Features ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Detection Accuracy ◽  
Detection Techniques ◽  
Copy Move Forgery Detection ◽  
Occurrence Matrix ◽  
Differential Excitation

Copy-move forgery (CMF) is an established process to copy an image segment and pastes it within the same image to hide or duplicate a portion of the image. Several CMF detection techniques are available; however, better detection accuracy with low feature vector is always substantial. For this, differential excitation component (DEC) of Weber Law descriptor in combination with the gray level co-occurrence matrix (GLCM) approach of texture feature extraction for CMFD is proposed. GLCM Texture features are computed in four directions on DEC and this acts as a feature vector for support vector machine classifier. These texture features are more distinguishable and it is validated through other two proposed methods based on discrete wavelet transform-GLCM (DWT-GLCM) and GLCM. Experimentation is carried out on CoMoFoD and CASIA databases to validate the efficacy of proposed methods. Proposed methods exhibit resilience against many post-processing attacks. Comparative analysis with existing methods shows the superiority of the proposed method (DEC-GLCM) with regard to detection accuracy.

Sign in / Sign up

Export Citation Format

Share Document