A Performance of Combined Methods of VCG and 16BCD for Feature Extraction on HSV

Abstract

The digital signature image is a digital pattern with highly variable features. The pattern recognition of digital signature images aims to build a specific characteristic capable of representing a considerable pattern variation while maintaining the boundary conditions of authentication. The feature as an attribute that describes the characteristics of a pattern becomes a determinant factor of reliability of a method of recognizing digital signature image pattern for Handwritten Signature Verification (HSV). To construct HSV required two types of signature samples that are the original signature samples used as training samples and the guess signature samples (consist of valid and imposter signature) which are used as test samples. This study proposes two unique features of 16-Bits Binary Chain to Decimal (16BCD) and Virtual Center of Gravity (VCG). The 16BCD feature obtained from image segmentation with a 4x4 pixel region. All pixels in each region of the segmentation result rearranged into a 16-bit binary chain. The VCG feature is a virtual representation of the Original Signature Pattern (OSP) gravity center against Pattern Space and Background. The verification mechanism uses criteria: the percent of acceptable correlation coefficients for the acceptable feature of 16BCD feature, Mean Absolute Error (MAE) against 16BCD, and the percent deviation of acceptable distance to the VCG feature prototype. Verification test results obtained Acceptance Rate (AR) 80% (which states the percentage of HSV success based on a number of original signature samples) with an efficiency of 90% (which states the percentage of success of HSV in distinguishing valid or forgery signature based on a sample of guessing signatures).

Classification of Maturity Levels in Areca Fruit Based on HSV Image Using the KNN Method

“…After dividing 80% of the train dataset and 20% of the test dataset, implementing the HSV (Hue Saturation Value) feature extraction, in this stage the aim is to obtain the calculation results of the extraction value of the image object. The following is the calculation of the results of the test dataset and training dataset obtained from feature extraction using HSV (Putra, et al, 2021). The first step to get the HSV feature extraction image is the steps that will be processed.…”

Gender Classification from Behavioural Biometric Data using Convolutional Neural Network

“…Recently, identification and authentication from ancillary information of biometric methods are extensively researched issues, whereas softbiometrics and hard-biometrics work together to ensure best recognition rate for a specific environment [2]. Signatures are behavioural biometrics which is inconsistent and change due to an emotional and physical state like age, mood, and ecological conditions [3]. The word "signature" comes from the Latin word "signure", which means "to mark".…”

Sports-Assisted Education Based on a Support Vector Machine and Genetic Algorithm

“…Feature Fusion. Feature extraction is central to the implementation of sports action recognition[14]. In this paper, we combine the characteristics of sports action, consider the comprehensiveness of feature extraction and the description of local features, and use the eight-star model and Zernike moments commonly used in sports posture multifeature extraction to extract sports action multifeatures.…”