Estimating Population Abundance of Burying Beetles Using Photo-Identification and Mark-Recapture Methods

Successful conservation and management of protected wildlife populations require reliable population abundance data. Traditional capture-mark-recapture methods can be costly, time-consuming, and invasive. Photographic mark-recapture (PMR) is a cost-effective, minimally invasive way to study population dynamics in species with distinct markings or color patterns. We tested the feasibility and the application of PMR using the software Hotspotter to identify Nicrophorus spp. from digital images of naturally occurring spot patterns on their elytra. We conducted a laboratory study evaluating the identification success of Hotspotter on Nicrophorus americanus (Olivier, 1790) and Nicrophorus orbicollis (Say, 1825) before implementation of a mark-recapture study in situ. We compared the performance of Hotspotter using both ‘high-quality’ and ‘low-quality’ photographs. For high-quality photographs, Hotspotter had a false rejection rate of 2.7–3.0% for laboratory-reared individuals and 3.9% for wild-caught individuals. For low-quality photographs, the false rejection rate was much higher, 48.8–53.3% for laboratory-reared individuals and 28.3% for wild-caught individuals. We subsequently analyzed encounter histories of wild-caught individuals with closed population models in Program MARK to estimate population abundance. In our study, we demonstrated the utility of using PMR in estimating population abundance for Nicrophorus spp. based on elytral spot patterns.

EAgeBioS: Enhanced Biometric System to handle the Effects of Template Aging

Biometric Systems are well-known security systems that can be used anywhere for authentication, authorization or any kind of security verifications. In biometric systems, the samples are trained first and then it can be used for testing in long runs. Many recent researches have shown that a biometric system may fail or get compromised because of the aging of the biometric templates. The fact that temporal duration affects the performance of the biometric system has shattered the belief that iris does not change over lifetime. This is also possible in the case of iris. So, the main focus of this work is to analyze the effect of aging and also to propose a new system that can deal with template aging. We have proposed a new iris recognition system with an image enhancement mechanism and different feature extraction mechanisms. In this work, three different features are extracted, which are then fused to be used as one. The full system is trained on a dataset of 2500 samples for the year 2008 and testing is done in three different phases (i) No-Lapse, (ii) 1-Year Lapse and (iii) 2-Year Lapse. A portion of the ND-Iris-Template-Aging dataset [11] is used with a period of three years lapse. Results show that the performance of the hybrid classifier AHyBrK [17] is improved as compared to KNN and ANN and the effect of aging in terms of degraded performance is clear. The performance of this system is measured in terms of False Rejection Rate, Error Rate, and Accuracy. The overall performance of AHyBrK is 51.04% and 52.98% better than KNN and ANN respectively in terms of False Rejection Rate and Error Rate whereas the accuracy of this proposed system is also improved by 5.52% and 6.04% as compared to KNN and ANN respectively. This proposed system also achieved high accuracy for all the test phases.

Studi Perbandingan Metode Wavelet Dalam Speech Recognition Pada Sistem Akses Personel

Penelitian tentang speech recognition terus berkembang terkait identifikasi personel. Pada penelitian ini, kami melakukan studi perbandingan metode wavelet dalam speech recognition. Pada penelitian ini teknologi speech recognition berbasiskan wavelett dan neuro fuzzy. Beberapa parameter yang digunakan dalam penelitian ini adalah sampel suara dengan frekuensi sampling 8000 Hz dan 8 bit per sampel dengan filter wavelet High Pass Filter (HPF). Level dekomposisi menggunakan wavelet daubechies, symlet dan coiflet. Nilai thereshold filter wavelet identifikasi personel 57,72%, False Rejection Rate (FRR) 40% dan running time 1,97 detik. Untuk nilai thereshold identifikasi personel 100%, False Rejection Rate (FRR) 0% dan running time 5,43 detik didapatkan pada level dekomposisi 5 pada wavelet db1. Identifikasi tipe wavelet dari yang terbaik adalah coiflet, symlet dan daubechies karena coif2 level 2 memberikan identifikasi 60,00%, FRR 40,00% dan running time 1,97 detik

Authentication Based on Seating Pressure Distribution using the MT System

This paper proposes a system for authentication based on seating pressure distribution, using the MT system as a new method of biometric authentication that is difficult to forge and does not inconvenience users. The main characteristic is that the only action required of the user is to sit down. Feature values were extracted based on the pressure distribution when individuals seat, and individual users were distinguished from other persons by means of the Mahalanobis-Taguchi (MT) system used in quality engineering. The result of the experiment was a False Rejection Rate of 2.2% and a False Acceptance Rate of 1.1%.

Image Matching Application Based on Modified SURF Algorithm

The key technique to increase the accuracy of electronic marking is the technique of image matching, namely to match two doubtfully duplicate images. Currently there are few technologies aiming for features on test paper images with high performance on matching accuracy. The research is based on SURF algorithm and specific to the features of test paper images. Thus the research is to put forward the modified algorithm with constraints among feature spots of orientation angles on their geometrical positions, including differential constraints on critical points from approximate blank test papers with less individual features at the same time. After processing and analyzing 2,000 test paper gathered from one actual examination, the results show that the modified detection algorithm has 100% false rejection rate and 100% accuracy when it is used to detect the test paper matching.

OFF-LINE SIGNATURE AUTHENTICATION USING RADIAL BASIS FUNCTION

A system is proposed that considers minimal features using subpattern analysis which leads to less response time in a real time scenario. Using training samples, with a high degree of certainty, the minimum variance quadtree components [MVQC] of a signature for a person are listed to be applied on a testing sample. Initially the experiment was conducted on wavelet decomposed information for a signature. The non-MVQCs and core components were analyzed. To characterize the local details Gaussian-Hermite moment was applied. Later Hu moments were applied on the selected subsections. The summation values of the subsections are provided as feature to radial basis function [RBF] and feed forward neural network classifiers. Results indicate that the RBF classifier yielded 7% false rejection rate and feed forward neural network classification technique produced 9% false rejection rate. Promising results were achieved, by experimenting on the list of most prominent minimum variance components which are core components using RBF.