An Evolving Signature Recognition System

Jayasekara, A. G. Buddhika P.; Jayasiri, Awantha; Udawatta, Lanka

doi:10.1109/iciis.2006.365785

Cited by 12 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fitness of the chromosomes is assessed with a function normally denoted as objective or fitness function (Oluleye et al, 2014). Realizing a worthy fitness assessment can make it easier for NGA to develop a beneficial scheme (Gunavathi & Premalatha, 2014; Jayasekara, Jayasiri, & Udawatta, 2006). For a NGA to choose a subclass of document's descriptors, a fitness function must be regulated to estimate the discriminative competence of each subclass of descriptors.…”

Section: Methodsmentioning

confidence: 99%

Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm

Darwish

Elgohary²

2020

Expert Systems

View full text Add to dashboard Cite

Inside digital forensic science, expert systems are utilized to clarify suspicions where normally one or more human experts would need to be consulted. Expert systems‐based printer identification is provided with the objective of distinguishing the printer that produced a suspicious or questioned document. The arising problem is that the extraction of many features of the printed document for printer forensics sometimes increases the time and decreases the classification accuracy as many of the printed document descriptors may emanate to be recurring and non‐valuable. Therefore, the distinct combinatorial collection of features (knowledge base) will demand to be acquired in order to preserve the essence of operative features' fusion to accomplish the maximum accuracy. This paper presents a bio‐inspired expert system for printer forensics that integrates both texture features conveyed from the grey level co‐occurrence matrix of the printed letter ‘WOO’ and niching genetic search to select the good enough reduced feature set. This combination intends to realize high classification precision relies on a trivial collection of discriminative descriptors. Niching methods extend genetic algorithms to domains that require the location and maintenance of multiple solutions based on adjusting the crossover ratio and occurrence of mutation of each individual and employs the slope of the individuals to choose their mutation value. For categorization, the scheme exploits k‐nearest neighbours (KNN) to distinguish the brand of the printer for its simplicity. Results confirm that the suggested approach has high classification accuracy and needs less computation time.

show abstract

Section: Methodsmentioning

confidence: 99%

Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm

Darwish

Elgohary²

2020

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Unlike traditional gradientbased methods, GA's can be used to evolve systems with any kind of fitness measurement functions including those that are non-differentiable, discontinuous. Finding a good fitness measurement can make it easier for GA to evolve a useful system [27]. For a GA to select a subset of features, a fitness function must be defined to evaluate the discriminative capability of each subset of features.…”

Section: Feature Extraction Based On Glcmmentioning

confidence: 99%

Bio-inspired Expert System based on Genetic Algorithm for Printer Identification in Forensic Science

Darwish

Elgohary²

2018

Int. J. Art. Intell. Research

View full text Add to dashboard Cite

Printer identification models are provided for the goal of distinguishing the printer that produced a suspicious imprinted document. Source identification of a published document can easily be a significant procedure intended for the forensic science. The arising problem is that the extraction of many features of the printed document for printer identification sometimes increases time and reduces the classification accuracy since a lot of the document features may come to be repetitive and non-beneficial. Distinct combinatorial collection of features will need to be acquired in order to preserve the most effective fusion to accomplish the maximum accuracy. This paper presents an intelligent machine learning algorithm for printer identification that adopts both of texture features formulated from gray level co-occurrence matrix of the printed letter ''WOO'' and genetic heuristic search to select the optimal reduced feature set. This integration aims to achieve high classification accuracy based on small group of discriminative features. For classification, the system utilizes k-nearest neighbors (KNN) to recognize the source model of the printer for its simplicity. Experimental results validate that the suggested system has high taxonomy accuracy and requires less computation time.

show abstract

“…Biometric system is a pattern recognition system that works by taking biometric data from a person, extracting a feature set from that data, and comparing feature set with a template one in the database (Jain et al, 2004;Phillips, 2002;Jayasekara et al, 2006;Choras et al, 2006). Applications of biometric system may operate in two modes as follows:…”

Section: Background and Related Workmentioning

confidence: 99%

“…Biometric characteristics can be divided into two classes: physiological and behavioral characteristics, which can be obtained from speech, signature, hand-and-finger geometry, face shape, DNA, gait pattern, ear shape, fingerprint, iris scan, retinal scan…etc (Jain et al, 2008;Jin et al, 2009;Jayasekara et al, 2006;Jain et al, 2004).…”

Section: Background and Related Workmentioning

confidence: 99%

Automatic Identity Recognition Using Speech Biometric

Abushariah

Alqudah

2016

ESJ

View full text Add to dashboard Cite

Biometric technology refers to the automatic identification of a person using physical or behavioral traits associated with him/her. This technology can be an excellent candidate for developing intelligent systems such as speaker identification, facial recognition, signature verification...etc. Biometric technology can be used to design and develop automatic identity recognition systems, which are highly demanded and can be used in banking systems, employee identification, immigration, e-commerce…etc. The first phase of this research emphasizes on the development of automatic identity recognizer using speech biometric technology based on Artificial Intelligence (AI) techniques provided in MATLAB. For our phase one, speech data is collected from 20 (10 male and 10 female) participants in order to develop the recognizer. The speech data include utterances recorded for the English language digits (0 to 9), where each participant recorded each digit 3 times, which resulted in a total of 600 utterances for all participants. For our phase two, speech data is collected from 100 (50 male and 50 female) participants in order to develop the recognizer. The speech data is divided into text-dependent and text-independent data, whereby each participant selected his/her full name and recorded it 30 times, which makes up the text-independent data. On the other hand, the text-dependent data is represented by a short Arabic language story that contains 16 sentences, whereby every sentence was recorded by every participant 5 times. As a result, this new corpus contains 3000 (30 utterances * 100 speakers) sound files that represent the text-independent data using their full names and 8000 (16 sentences * 5 utterances * 100 speakers) sound files that represent the text-dependent data using the short story. For the purpose of our phase one of developing the automatic identity recognizer using speech, the 600 utterances have undergone the feature extraction and feature classification phases. The speech-based automatic identity recognition system is based on the most dominating feature extraction technique, which is known as the Mel-Frequency Cepstral Coefficient (MFCC). For feature classification phase, the system is based on the Vector Quantization (VQ) algorithm. Based on our experimental results, the highest accuracy achieved is 76%. The experimental results have shown acceptable performance, but can be improved further in our phase two using larger speech data size and better performance classification techniques such as the Hidden Markov Model (HMM).

show abstract

An Evolving Signature Recognition System

Cited by 12 publications

References 24 publications

Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm

Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm

Bio-inspired Expert System based on Genetic Algorithm for Printer Identification in Forensic Science

Automatic Identity Recognition Using Speech Biometric

Contact Info

Product

Resources

About