False Rejection Error Research Articles

Analysis of the Efficacy of Real-Time Hand Gesture Detection with Hog and Haar-Like Features Using SVM Classification

The field of hand gesture recognition has recently reached new heights thanks to its widespread use in domains like remote sensing, robotic control, and smart home appliances, among others. Despite this, identifying gestures is difficult because of the intransigent features of the human hand, which make the codes used to decode them illegible and impossible to compare. Differentiating regional patterns is the job of pattern recognition. Pattern recognition is at the heart of sign language. People who are deaf or mute may understand the spoken language of the rest of the world by learning sign language. Any part of the body may be used to create signs in sign language. The suggested system employs a gesture recognition system trained on Indian sign language. The methods of preprocessing, hand segmentation, feature extraction, gesture identification, and classification of hand gestures are discussed in this work as they pertain to hand gesture sign language. A hybrid approach is used to extract the features, which combines the usage of Haar-like features with the application of Histogram of Oriented Gradients (HOG).The SVM classifier is then fed the characteristics it has extracted from the pictures in order to make an accurate classification. A false rejection error rate of 8% is achieved while the accuracy of hand gesture detection is improved by 93.5%.

Auditory Device Voice Activity Detection Based on Statistical Likelihood-Ratio Order Statistics

This paper proposes a technique for improving statistical-model-based voice activity detection (VAD) in noisy environments to be applied in an auditory hearing aid. The proposed method is implemented for a uniform polyphase discrete Fourier transform filter bank satisfying an auditory device time latency of 8 ms. The proposed VAD technique provides an online unified framework to overcome the frequent false rejection of the statistical-model-based likelihood-ratio test (LRT) in noisy environments. The method is based on the observation that the sparseness of speech and background noise cause high false-rejection error rates in statistical LRT-based VAD—the false rejection rate increases as the sparseness increases. We demonstrate that the false-rejection error rate can be reduced by incorporating likelihood-ratio order statistics into a conventional LRT VAD. We confirm experimentally that the proposed method relatively reduces the average detection error rate by 15.8% compared to a conventional VAD with only minimal change in the false acceptance probability for three different noise conditions whose signal-to-noise ratio ranges from 0 to 20 dB.

Normalization of Facial Occlusion in Face Recognition

Face recognition accuracy is determined by face detection results. Detected faces will be in view of clear and occlusion faces. If detected face has occlusion than recognition accuracy is reduced. This research is directed to increase recognition rate when detected occlusion face. In this paper is proposed normalization occlusion faces by Principal component analysis algorithm. After applying normalization method in occlusion faces false reject error rate is decreased.

False-Accept/False-Reject Trade-Offs for Ensembles of Biometric Authentication Systems

Biometric authentication systems, based on secret key generation, work as follows. In the enrollment stage, an individual provides a biometric signal that is mapped into a secret key and a helper message, the former being prepared to become available to the system at a later time (for authentication), and the latter is stored in a public database. When an authorized user requests authentication, claiming his/her identity to be one of those of the subscribers, he/she has to provide a biometric signal again, and then the system, which retrieves also the helper message of the claimed subscriber, produces an estimate of the secret key that is finally compared to the secret key of the claimed user. In the case of a match, the authentication request is approved; otherwise, it is rejected. Evidently, there is an inherent tension between two desired, but conflicting, properties of the helper message encoder; on the one hand, the encoding should be informative enough concerning the identity of the real subscriber, in order to approve him/her in the authentication stage, but on the other hand, it should not be too informative, as otherwise, unauthorized imposters could easily fool the system and gain access. A good encoder should then trade off the two kinds of errors: the false reject (FR) error and the false accept (FA) error. In this paper, we investigate trade-offs between the random coding FR error exponent and the best achievable FA error exponent. We compare two types of ensembles of codes: fixed-rate codes and variable-rate codes, and we show that the latter class of codes offers considerable improvement compared to the former. In doing this, we characterize ensemble-optimal rate functions for both types of codes. We also examine the effect of privacy leakage constraints for both fixed-rate codes and variable-rate codes

Palm Vein Recognition System Based on Derived Pattern and Feature Vectors

Biometrics is a technology for recognition under which Palm vein recognition stems. They are of crucial importance in various applications of high sensitivity. This article develops a palm vein recognition model, based on derived pattern and feature vectors. All the palm print images used in this work were obtained from CASIA Multi-Spectral Palmprint Image Database V1.0 (CASIA database). First, a Region of Interest (ROI) was identified and extracted from the palm print images. Next, Histogram Equalization was used to enhance the area of the palm print image in the Region of Interest. The enhanced image obtained was subjected to the Zhang Suen's Thinning Algorithm to extract appropriate features in the palm print images needed for authentication. The features derived based on this vascular pattern thinning algorithm which are then compared and evaluated to carry out ‘matching'. The Pattern Matching itself was done using the Euclidean Distance for subsequent matching. The model was designed using UML, and implemented with C# and MS SQL on Microsoft Visual Studio platform. The developed system was evaluated based on False Acceptance, False Rejection and Equal Error Rate (EER) values obtained from the system. The results of testing and evaluation show that the developed system has achieved high recognition accuracy.

Detection of Fingerprints in Advanced Biometric System Design

The objective of this research is to incorporate fingerprint authentication to thwart the intruders attack in a network. A complete feature extraction process to propose an authentication scheme is presented in this paper. False Acceptance Error and False Rejection Error have been stressed to measure the performance of the proposed scheme. The main finding is to obtain an authentication system with a better strength. Majority of authentication techniques are unable to provide verification efficiency leads to competent negligence without being recognized. The primary goal of this document is to introduce and apply an innovative strategy that customs the finger print modus operandi to enhance a host based attack recognition program in to advance its level of verification.

Effects of Photo and Genotype-Based Misidentification Error on Estimates of Survival, Detection and State Transition using Multistate Survival Models.

We simulated multistate capture histories (CHs) by varying state survival (ϕ), detection (p) and transition (ψ), number of total capture occasions and releases per capture occasion and then modified these scenarios to mimic false rejection error (FRE), a common misidentification error, resulting from the failure to match samples of the same individual. We then fit a multistate model and estimated accuracy, bias and precision of state-specific ϕ, p and ψ to better understand the effects of FRE on different simulation scenarios. As expected, ϕ, and p, decreased in accuracy with FRE, with lower accuracy when CHs were simulated under a shorter-term study and a lower number of releases per capture occasion (lower sample size). Accuracy of ψ estimates were robust to FRE except in those CH scenarios simulated using low sample size. The effect of FRE on bias was not consistent among parameters and differed by CH scenario. As expected, ϕ was negatively biased with increased FRE (except for the low ϕ low p CH scenario simulated with a low sample size), but we found that the magnitude of bias differed by scenario (high p CH scenarios were more negatively biased). State transition was relatively unbiased, except for the low p CH scenarios simulated with a low sample size, which were positively biased with FRE, and high p CH scenarios simulated with a low sample size. The effect of FRE on precision was not consistent among parameters and differed by scenario and sample size. Precision of ϕ decreased with FRE and was lowest with the low ϕ low p CH scenarios. Precision of p estimates also decreased with FRE under all scenarios, except the low ϕ high p CH scenarios. However, precision of ψ increased with FRE, except for those CH scenarios simulated with a low sample size. Our results demonstrate how FRE leads to loss of accuracy in parameter estimates in a multistate model with the exception of ψ when estimated using an adequate sample size.

Age estimation using a hierarchical classifier based on global and local facial features

The research related to age estimation using face images has become increasingly important, due to the fact it has a variety of potentially useful applications. An age estimation system is generally composed of aging feature extraction and feature classification; both of which are important in order to improve the performance. For the aging feature extraction, the hybrid features, which are a combination of global and local features, have received a great deal of attention, because this method can compensate for defects found in individual global and local features. As for feature classification, the hierarchical classifier, which is composed of an age group classification (e.g. the class of less than 20 years old, the class of 20-39 years old, etc.) and a detailed age estimation (e.g. 17, 23 years old, etc.), provide a much better performance than other methods. However, both the hybrid features and hierarchical classifier methods have only been studied independently and no research combining them has yet been conducted in the previous works. Consequently, we propose a new age estimation method using a hierarchical classifier method based on both global and local facial features. Our research is novel in the following three ways, compared to the previous works. Firstly, age estimation accuracy is greatly improved through a combination of the proposed hybrid features and the hierarchical classifier. Secondly, new local feature extraction methods are proposed in order to improve the performance of the hybrid features. The wrinkle feature is extracted using a set of region specific Gabor filters, each of which is designed based on the regional direction of the wrinkles, and the skin feature is extracted using a local binary pattern (LBP), capable of extracting the detailed textures of skin. Thirdly, the improved hierarchical classifier is based on a support vector machine (SVM) and a support vector regression (SVR). To reduce the error propagation of the hierarchical classifier, each age group classifier is designed so that the age range to be estimated is overlapped by consideration of false acceptance error (FAE) and false rejection error (FRE) of each classifier. The experimental results showed that the performance of the proposed method was superior to that of the previous methods when using the BERC, PAL and FG-Net aging databases.

Finger vein recognition using minutia‐based alignment and local binary pattern‐based feature extraction

AbstractWith recent increases in security requirements, biometrics such as fingerprints, faces, and irises have been widely used in many recognition applications including door access control, personal authentication for computers, Internet banking, automatic teller machines, and border‐crossing controls. Finger vein recognition uses the unique patterns of finger veins to identify individuals at a high level of accuracy. This article proposes a new finger vein recognition method using minutia‐based alignment and local binary pattern (LBP)‐based feature extraction. Our study makes three novelties compared to previous works. First, we use minutia points such as bifurcation and ending points of the finger vein region for image alignment. Second, instead of using the whole finger vein region, we use several extracted minutia points and a simple affine transform for alignment, which can be performed at fast computational speed. Third, after aligning the finger vein image based on minutia points, we extract a unique finger vein code using a LBP, which reduces false rejection error and thus the equal error rate (EER) significantly. Our resulting EER was 0.081% with a total processing time of 118.6 ms. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 179–186, 2009

TWO-STAGE BIOMETRIC AUTHENTICATION METHOD USING THOUGHT ACTIVITY BRAIN WAVES

Brain waves are proposed as a biometric for verification of the identities of individuals in a small group. The approach is based on a novel two-stage biometric authentication method that minimizes both false accept error (FAE) and false reject error (FRE). These brain waves (or electroencephalogram (EEG) signals) are recorded while the user performs either one or several thought activities. As different individuals have different thought processes, this idea would be appropriate for individual authentication. In this study, autoregressive coefficients, channel spectral powers, inter-hemispheric channel spectral power differences, inter-hemispheric channel linear complexity and non-linear complexity (approximate entropy) values were used as EEG features by the two-stage authentication method with a modified four fold cross validation procedure. The results indicated that perfect accuracy was obtained, i.e. the FRE and FAE were both zero when the proposed method was tested on five subjects using certain thought activities. This initial study has shown that the combination of the two-stage authentication method with EEG features from thought activities has good potential as a biometric as it is highly resistant to fraud. However, this is only a pilot type of study and further extensive research with more subjects would be necessary to establish the suitability of the proposed method for biometric applications.

Recovery from false rejection using statistical partial pattern trees for sentence verification

In conversational speech recognition, recognizers are generally equipped with a keyword spotting capability to accommodate a variety of speaking styles. In addition, language model incorporation generally improves the recognition performance. In conversational speech keyword spotting, there are two types of errors, false alarm and false rejection. These two types of errors are not modeled in language models and therefore offset the contribution of the language models. This paper describes a partial pattern tree (PPT) to model the partial grammatical rules of sentences resulting from recognition errors and ungrammatical sentences. Using the PPT and a proposed sentence-scoring algorithm, the false rejection errors can be recovered first. A sentence verification approach is then employed to re-rank and verify the recovered sentence hypotheses to give the results. A PPT merging algorithm is also proposed to reduce the number of partial patterns with similar syntactic structure and thus reduce the PPT tree size. An automatic call manager and an airline query system are implemented to assess the performance. The keyword error rates for these two systems using the proposed approach achieved 10.40% and 14.67%, respectively. The proposed method was compared with conventional approaches to show its superior performance.

A false acceptance error controlling method for hyperspherical classifiers

Controlling false acceptance errors is of critical importance in many pattern recognition applications, including signature and speaker verification problems. Toward this goal, this paper presents two post-processing methods to improve the performance of hyperspherical classifiers in rejecting patterns from unknown classes. The first method uses a self-organizational approach to design minimum radius hyperspheres, reducing the redundancy of the class region defined by the hyperspherical classifiers. The second method removes additional redundant class regions from the hyperspheres by using a clustering technique to generate a number of smaller hyperspheres. Simulation and experimental results demonstrate that by removing redundant regions these two post-processing methods can reduce the false acceptance error without significantly increasing the false rejection error.

ON-LINE SIGNATURE VERIFICATION BASED ON LOGARITHMIC SPECTRUM

In this paper, an on-line signature verification scheme based on similarity measurement of logarithmic spectrum is proposed. The principal components of the logarithmic spectrum of each signature are extracted. We then compute the similarity of logarithmic spectrum between input signature and the reference template. By comparing the similarity of logarithmic spectrum with the verification threshold, we can determine the authenticity of the input signature. Based on the experimentation, the rates of false rejection errors and false acceptance errors are as low as 1.4 and 2.8%, respectively. This demonstrates the effectiveness of the proposed scheme.

High confidence visual recognition of persons by a test of statistical independence

A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence. The most unique phenotypic feature visible in a person's face is the detailed texture of each eye's iris. The visible texture of a person's in a real-time video image is encoded into a compact sequence of multi-scale quadrature 2-D Gabor wavelet coefficients, whose most-significant bits comprise a 256-byte iris code. Statistical decision theory generates identification decisions from Exclusive-OR comparisons of complete codes at the rate of 4000 per second, including calculation of decision confidence levels. The distributions observed empirically in such comparisons imply a theoretical cross-over error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates. In the typical recognition case, given the mean observed degree of code agreement, the decision confidence levels correspond formally to a conditional false accept probability of one in about 10/sup 31/. >

Computer evaluation of statistical procedures, and a new quality-control statistical procedure.

I describe a program for definitive comparison of different quality-control statistical procedures. A microcomputer simulates quality-control results generated by repetitive analytical runs. It applies various statistical rules to each result, tabulating rule breaks to evaluate rules as routinely applied by the analyst. The process repeats with increasing amounts of random and systematic error. Rate of false rejection and true error detection for currently popular statistical procedures were comparatively evaluated together with a new multirule procedure described here. The nature of the analyst's response to out-of-control signals was also evaluated. A single-rule protocol that is as effective as the multirule protocol of Westgard et al. (Clin Chem 27:493, 1981) is reported.

Detectability of Multiple Flaws

Two experiments measured detectability, d', and two measures of criterion location for multiple flaws presented separately versus mixed. In the first experiment, the different flaws were the same in type but differed in magnitude; in the second experiment the flaws were of different types. In Experiment 1 there was no difference in d' for either magnitude of flaw as a result of the separate versus mixed conditions, (i.e., each magnitude of flaw had its own d' in both separate and mixed conditions). However, in Experiment 2 all flaws had lower d's in the mixed condition than when each was presented alone. In neither experiment was there any difference in average criterion location between the separate and mixed conditions, nor did individual criterion locations for easy versus hard flaws presented separately differ in Experiment 1. In Experiment 2 there was a difference in individual criterion locations for the different flaws presented separately, such that for the hardest to detect flaw, false rejection error rate was lower and miss rate higher than for either of the two flaws with larger d's.