Fingerprint Classification Research Articles

Brain fingerprinting classification concealed information test detects US Navy military medical information with P300.

A classification concealed information test (CIT) used the “brain fingerprinting” method of applying P300 event-related potential (ERP) in detecting information that is (1) acquired in real life and (2) unique to US Navy experts in military medicine. Military medicine experts and non-experts were asked to push buttons in response to three types of text stimuli. Targets contain known information relevant to military medicine, are identified to subjects as relevant, and require pushing one button. Subjects are told to push another button to all other stimuli. Probes contain concealed information relevant to military medicine, and are not identified to subjects. Irrelevants contain equally plausible, but incorrect/irrelevant information. Error rate was 0%. Median and mean statistical confidences for individual determinations were 99.9% with no indeterminates (results lacking sufficiently high statistical confidence to be classified). We compared error rate and statistical confidence for determinations of both information present and information absent produced by classification CIT (Is a probe ERP more similar to a target or to an irrelevant ERP?) vs. comparison CIT (Does a probe produce a larger ERP than an irrelevant?) using P300 plus the late negative component (LNP; together, P300-MERMER). Comparison CIT produced a significantly higher error rate (20%) and lower statistical confidences: mean 67%; information-absent mean was 28.9%, less than chance (50%). We compared analysis using P300 alone with the P300 + LNP. P300 alone produced the same 0% error rate but significantly lower statistical confidences. These findings add to the evidence that the brain fingerprinting methods as described here provide sufficient conditions to produce less than 1% error rate and greater than 95% median statistical confidence in a CIT on information obtained in the course of real life that is characteristic of individuals with specific training, expertise, or organizational affiliation.

Relationship between Palmar Dermatoglyphic Pattern and Academic Performance of Students in a Ghanaian Secondary School

Dermatoglyphics which is a scientific study of epidermal ridge patterns on fingers (fingerprints) and palms (palmprints) is an important tool that has been used in the areas of personal identifica-tion, criminality as well as medical diagnosis of several congenital diseases. In this study, we hy-pothesized a positive relationship between academic performance and the dermatoglyphic pattern of the hand. The palmprints and fingerprints of 320 3rd and 4th year students of Ghana Senior High School, Koforidua were analyzed according to the number of Primary crease, Intersections of pri-mary crease and Complete transverse Crease (PIC) model of classification and FBI system of fin-gerprint classification respectively. The dermatoglyphic patterns of each student were compared to the cumulative academic results of five consecutive academic terms. The study revealed that stu-dents with symmetrical palmprints performed better academically than those with asymmetrical palmprints (p<0.001). Strikingly, students with Central Pocket Loop Whorl located on the ring and middle fingers performed better academically than those with other fingerprints (p<0.0001). None of the students displayed PIC 101, 201 and 211 palmprint patterns which characterize individuals with learning difficulties. The results thus demonstrate a close association between dermatoglyphic pattern of the hand and brain cognitive functions. Dermatoglyphics can therefore be used to identi-fy potentially weak students and to design teaching and counseling strategies for them. Further research using large sized samples are recommended for further elucidation of established linkag-es.Keywords: Dermatoglyphic pattern; palmprint; fingerprints, academic performance; PIC classification

Fingerprint Classification Using Fuzzy-neural Network and Other Methods

The fingerprints are unique to each individual; they can be used as a means to distinguish one individual from another.Therefore they are used to identify a person. Fingerprint Classification is done to associate a given fingerprint to one of the existing classes, such as left loop, right loop, arch, tented arch and whorl. Classifying fingerprint images is a very complex pattern recognition problem, due to properties of intra-class diversitiesand inter-class similarities. Its objective is to reduce the responsetime and reducing the search space in an automatic identificationsystem fingerprint (AIS), in classifying fingerprints. In these papers we present a system of fingerprint classificationbased on singular characteristics for extracting feature vectorsand neural networks and fuzzy neural networks, SVM and Knearest neighbour for classifying.

Noisy and incomplete fingerprint classification using local ridge distribution models

Fingerprint images acquired from live-scan devices may have various noises, such as cuts and smears and be incomplete due to shifted and partial scanning. We propose a novel fingerprint classification method that is able to effectively classify noisy and incomplete fingerprints, which are acquired by live-scan devices. Fingerprint images are divided into blocks of 16×16 pixels and representative directional values of each block are extracted. Based on the representative directional values, the core blocks including the core points are identified by core block Markov models. Then, fingerprints are divided into 4 regions with respect to the core blocks and each region is modeled with the distribution of the ridge directional values in its region. Fingerprint classification is carried out by using the regional local models. If a fingerprint is given, each local model determines the probabilities that the given fingerprint belongs to all the fingerprint classes. The final decision on the classification is made by probabilistic integration of the classification results of local models. Since the proposed method analyzes ridges based on blocks of 16×16 pixels and classifies based on regional local models, it can be robustly applied to noisy and incomplete fingerprint images. A performance evaluation based on the live scanned fingerprint databases FVC 2000, 2002, and 2004 shows a good classification accuracy of 97.4%.

Classifying many-class high-dimensional fingerprint datasets using random forest of oblique decision trees

Classifying fingerprint images may require an important features extraction step. The scale-invariant feature transform which extracts local descriptors from images is robust to image scale, rotation and also to changes in illumination, noise, etc. It allows to represent an image in term of the comfortable bag-of-visual-words. This representation leads to a very large number of dimensions. In this case, random forest of oblique decision trees is very efficient for a small number of classes. However, in fingerprint classification, there are as many classes as individuals. A multi-class version of random forest of oblique decision trees is thus proposed. The numerical tests on seven real datasets (up to 5,000 dimensions and 389 classes) show that our proposal has very high accuracy and outperforms state-of-the-art algorithms.

Quantum fingerprinting with coherent states and a constant mean number of photons

We present a protocol for quantum fingerprinting that is ready to be implemented with current technology and is robust to experimental errors. The basis of our scheme is an implementation of the signal states in terms of a coherent state in a superposition of time-bin modes. Experimentally, this requires only the ability to prepare coherent states of low amplitude and to interfere them in a balanced beam splitter. The states used in the protocol are arbitrarily close in trace distance to states of $O({log}_{2}n)$ qubits, thus exhibiting an exponential separation in abstract communication complexity compared to the classical case. The protocol uses a number of optical modes that is proportional to the size $n$ of the input bit strings but a total mean photon number that is constant and independent of $n$. Given the expended resources, our protocol achieves a task that is provably impossible using classical communication only. In fact, even in the presence of realistic experimental errors and loss, we show that there exist a large range of input sizes for which our quantum protocol transmits an amount of information that can be more than two orders of magnitude smaller than a classical fingerprinting protocol.

Fingerprint Ridge Orientation Extraction: A Review of State of the Art Techniques

Personal identification based on fingerprints is very popular compared to identification based on other biometric features like iris, gait and face etc. Performance of automatic fingerprints identification systems depends upon the quality of fingerprints. Extraction of fingerprints features in poor quality fingerprints is challenging task. Accurate measurement of fingerprints feature improves the accuracy of identification systems. Fingerprints consists of ridge and valley structures and offers different types of features, they are categorized as level 1, level 2 and level 3 features. Level 1 features are singular points which are used for fingerprints registration, classification etc. Level 2 features are ridge features like minutiae points, ridge orientation etc., and commercially available fingerprint recognition systems are based on level 2 features. Level 3 features include sweat pores, incipient ridges etc. Among these features ridge orientation is used for fingerprint enhancement, fingerprint classification, indexing and fingerprint segmentation. This paper provides an overview of existing state of the art techniques for ridge orientation estimation.

Fingerprint Classification Method based on J-divergence Entropy and SVM

Fingerprint classification is one of the key technologies in Automatic Fingerp rint Identification System (AFIS). However, the performance of most recent fingerprint classification methods is lo w when the quality of the fingerprint image was low. To overcome this problem, a novel method based on j-divergence entropy and SVM (Support Vector Machine) classifier is proposed in this paper. Firstly, our method transforms the fingerprint images from spatial doma in to frequency domain and constructs the directional images according to frequency spectrum energy. Secondly, eigenvector around the core point is extracted. Thirdly, the dimension of eigenvector is reduced by j-divergence entropy. At last, the input image is classified by SVM classifier. Experimental results on NIST-4 database show the validity of our method, and the classification accuracy reaches 9 4.7% for four-class classification and 91.5% for five-class classification with zero rejection rate.

Exploration and classification of chromatographic fingerprints as additional tool for identification and quality control of several Artemisia species

The World Health Organization accepts chromatographic fingerprints as a tool for identification and quality control of herbal medicines. This is the first study in which the distinction, identification and quality control of four different Artemisia species, i.e. Artemisia vulgaris, A. absinthium, A. annua and A. capillaris samples, is performed based on the evaluation of entire chromatographic fingerprint profiles developed with identical experimental conditions. High-Performance Liquid Chromatography (HPLC) with Diode Array Detection (DAD) was used to develop the fingerprints. Application of factorial designs leads to methanol/water (80:20 (v/v)) as the best extraction solvent for the pulverised plant material and to a shaking bath for 30min as extraction method. Further, so-called screening, optimisation and fine-tuning phases were performed during fingerprint development. Most information about the different Artemisia species, i.e. the highest number of separated peaks in the fingerprint, was acquired on four coupled Chromolith columns (100mm×4.6mm I.D.). Trifluoroacetic acid 0.05% (v/v) was used as mobile-phase additive in a stepwise linear methanol/water gradient, i.e. 5, 34, 41, 72 and 95% (v/v) methanol at 0, 9, 30, 44 and 51min, where the last mobile phase composition was kept isocratic till 60min. One detection wavelength was selected to perform data analysis. The lowest similarity between the fingerprints of the four species was present at 214nm. The HPLC/DAD method was applied on 199 herbal samples of the four Artemisia species, resulting in 357 fingerprints. The within- and between-day variation of the entire method, as well as the quality control fingerprints obtained during routine analysis, were found acceptable. The distinction of these Artemisia species was evaluated based on the entire chromatographic profiles, developed by a shared method, and visualised in score plots by means of the Principal Component Analysis (PCA) exploratory data-analysis technique. Samples of different quality could be indicated on the score plots. No multi-component analysis was required to reach the goal. Furthermore, differences related to the origin of some of the not-certified samples were shown. The importance of the specific herbal part used for its identification was also presented. In addition, no differences were observed among fingerprints of lyophilised or conditioned-air dried samples. Finally, a classification technique, Soft Independent Modelling by Class Analogy (SIMCA), was successfully evaluated as identification technique for unknown samples. Six additional Artemisia species (29 herbal samples) were identified as not belonging to any of the four modelled classes. The developed chromatographic fingerprints and the evaluation of the entire profiles provide an added value to the distinction, identification and quality control of the simultaneously investigated Artemisia species.

Making sense of silence: finiteness and the (OC) pro vs. pro distinction

In this commentary paper, I discuss and further develop three points raised in Kissock (2013). First, I focus on Kissock’s proposal that all instances of null subject in Telugu are pro rather than OC pro. I argue that such a claim must be re-evaluated in light of the idea that (OC) pro and pro are not primitives: they both happen to be silent on the surface, but what crucially distinguishes them is that the former is always a bound-variable anaphor, whereas the latter can refer deictically. Thus, the claim that a language lacks OC pro reduces to a question about whether obligatorily bound variables are capable of being silent. The second part of the paper looks at whether there might be evidence for a lurking OC pro in Telugu after all. To this end, I take a closer look at complements embedded under the verb prajatninc- (roughly translated as “try”) and also investigate new evidence from clauses embedded under modalu- (“begin”), the latter showing that the subject of these clauses bears the classic fingerprint of OC pro. The third and final part of the paper expands on a minor point in Kissock’s paper involving non-finite clauses in Telugu, a subject pro-drop language, that allow both overt non-coreferent, and null coreferent subjects. Kissock assumes that the possibility of an overt non-coreferent subject automatically entails the possibility of a pro subject and argues, on this basis, that the null subjects in these clauses are pro, not pro. I propose that Kissock’s assumption is not an innocuous one to make and argue, on the strength of comparable examples from a range of languages, that subject pro-drop is restricted in non-finite clauses for independent reasons. Thus, the availability of an overt, non-coreferent subject in non-finite clauses doesn’t entail that of a pro subject.

Fingerprint Classification Combining Curvelet Transform and Gray-Level Cooccurrence Matrix

Fingerprint classification is an important indexing scheme to reduce fingerprint matching time for a large database for efficient large-scale identification. The abilities of Curvelet transform capturing directional edges of fingerprint images make the fingerprint suitable to be classified for higher classification accuracy. This paper presents an efficient algorithm for fingerprint classification combining Curvelet transform (CT) and gray-level cooccurrence matrix (GLCM). Firstly, we use fast discrete Curvelet transform warping (FDCT_WARPING) to decompose the original image into five scales Curvelet coefficients and construct the Curvelet filter by Curvelet coefficients relationship at adjacent scales to remove the noise from signals. Secondly, we compute the GLCMs of Curvelet coefficients at the coarsest scale and calculate 16 texture features based on 4 GLCMs. Thirdly, we construct 49 direction features of Curvelet coefficients at the other four scales. Finally, fingerprint classification is accomplished byK-nearest neighbor classifiers. Extensive experiments were performed on 4000 images in the NIST-4 database. The proposed algorithm achieves the classification accuracy of 94.6 percent for the five-class classification problem and 96.8 percent for the four-class classification problem with 1.8 percent rejection, respectively. The experimental results verify that proposed algorithm has higher recognition rate than that of wavelet-based techniques.

A Review on Classification of Fingerprint Images

Fingerprint is most widely used in individual identification especially in civilian applications, forensic laboratories etc. due to large bio-invariant characteristics of human fingerprints. A search over all the records in a data base takes a very long time and deteriorates accuracy as database is very large. To avoid this inconvenience, automatic fingerprint classification method is employed that does not require any user's interaction, reduce the search space and time and also increases accuracy of identifications. Classifying fingerprint images is a very difficult pattern recognition problem, due to the small interclass variability, the large intraclass variability, and the presence of noise and the ambiguous properties of fingerprints. In this paper we discuss about fingerprint classification and also review existing methods that have been applied for the classification problem.

A Study of Tin-containing Block Copolymers

The controlled synthesis of poly(styrene-block-trimethylstannylstyrene) has been accomplished. Thin films of the polymer were successfully oriented perpendicular to the substrate through use of neutral top and bottom coats to produce well-formed lamellae with the classical finger print pattern. Preliminary blanket etch studies show that the inclusion of tin into the block copolymer provides very high etch contrast for selective removal of the styrene block in both oxygen and fluorine plasma conditions. The etch rate of the tin polymer is significantly slower than that of thermal oxide under the conditions studied. Future work will be directed toward the synthesis of a sample with smaller pitch and to a study of the potential for use of organotin polymers for the patterning of fused silica imprint templates.

指纹图像的旋转校正与分类

为了提高在大容量指纹数据库中指纹识别率的速度和正确率，也为了提取出更多的细节特征，提出了一种旋正图像并使用中心点特征进行指纹分类的方法。首先，根据指纹图像的最小外接椭圆和矩形，获得旋转角度并对指纹进行仿射变换以校正图像；然后，针对现有Poincare index方法存在伪点的问题，通过对其改进实现中心点的确定，并总结人眼识别的经验对采集到的中心点去噪；最后，利用中心点的绝对方向角度、螺径等细节特征对指纹进行分类。对于无法分类或分类不正确的图像，采取二次匹配保证正确率。在从电容式指纹传感器FPC1011F采集到的400幅图像上，分类的准确率为91.25%，实验结果验证了该方法的有效性和鲁棒性。 In order not only to improve the speed and accuracy of fingerprint recognition in the large-capacity database, but also to extract more detailed features, this paper presents a classification algorithm by using the features of cores, which are extracted from a corrected fingerprint. In the first phase, according to the smallest external ellipse and rectangle, the declining fingerprint is corrected by the affine transformation. In the second phase, to heighten anti-noise capability of traditional Poincare index, an improved algorithm is proposed, and then false points are denoised by summarizing the human recognition experience. Finally, the absolute direction, the diameter of screw and other features are the basis for fingerprint classification. 400 fingerprint images collected by FPC1011F fingerprint sensor are used for an experimental test, and the accuracy rate on classification is 91.25%. The experimental results show its effectiveness and robustness.

Fingerprint Identification Based on Mopso in SVM

Abstract. The problem of fingerprint classification is discussed for many years. Support Vector Machine (SVM) is a traditional artificial intelligence algorithm developed for dealing classification problems. In this paper, we used the idea of multi-objective optimization to transform SVM into a new form, since the core concept of SVM is built up on a single optimization equation, and some parameters for this algorithm still need user to make tons of experiment to determine. Our algorithm has successfully proved that user do not need to make experiment to determine the penalty parameter C. NIST-4 database is used to assess our proposed algorithm. The experiment results show our method can get good classification results.

Error Estimation Method for Matrix Correlation-Based Wi-Fi Indoor Localization

A novel neighbor selection-based fingerprinting algorithm using matrix correlation (MC) for Wi-Fi localization is presented in this paper. Compared with classic fingerprinting algorithms that usually employ a single received signal strength (RSS) sample, the presented algorithm uses multiple on-line RSS samples in the form of a matrix and measures correlations between the on-line RSS matrix and RSS matrices in the radio-map. The algorithm makes efficient use of on-line RSS information and considers RSS variations of reference points (RPs) for localization, so it offers more accurate localization results than classic neighbor selection-based algorithms. Based on the MC algorithm, an error estimation method using artificial neural network is also presented to fuse available information that includes RSS samples and localization results computed by the MC algorithm and model the nonlinear relationship between the available information and localization errors. In the on-line phase, localization errors are estimated and then used to correct the localization results to reduce negative influences caused by a static radio-map and RP distribution. Experimental results demonstrate that the MC algorithm outperforms the other neighbor selection-based algorithms and the error estimation method can reduce the mean of localization errors by nearly half.

Ecological coherence of diversity patterns derived from classical fingerprinting and Next Generation Sequencing techniques

Changes in richness and bacterial community structure obtained via 454 Massively Parallel Tag Sequencing (MPTS) and Automated Ribosomal Intergenic Analysis (ARISA) were systematically compared to determine whether and how the ecological knowledge obtained from both molecular techniques could be combined. We evaluated community changes over time and depth in marine coastal sands at different levels of taxonomic resolutions, sequence corrections and sequence abundances. Although richness over depth layers or sampling dates greatly varied [∼ 30% and 70–80% new operational taxonomic units (OTU) between two samples with ARISA and MPTS respectively], overall patterns of community variations were similar with both approaches. Alpha-diversity estimated by ARISA-derived OTU was most similar to that obtained from MPTS-derived OTU defined at the order level. Similar patterns of OTU replacement were also found with MPTS at the family level and with 20–25% rare types removed. Using ARISA or MPTS datasets with lower resolution, such as those containing only resident OTU, yielded a similar set of significant contextual variables explaining bacterial community changes. Hence, ARISA as a rapid and low-cost fingerprinting technique represents a valid starting point for more in-depth exploration of community composition when complemented by the detailed taxonomic description offered by MPTS.

Fingerprint classification based on decision tree from singular points and orientation field

In this study, a high accuracy fingerprint classification method is proposed to enhance the performance in terms of efficiency for fingerprint recognition system. The recognition system has been considered as a reliable mechanism for criminal identification and forensic for its invariance property, yet the huge database is the key issue to make the system obtuse. In former works, the pre-classifying manner is an effective way to speed up the process, yet the accuracy of the classification dominates the further recognition rate and processing speed. In this paper, a rule-based fingerprint classification method is proposed, wherein the two features, including the types of singular points and the number of each type of point are adopted to distinguish different fingerprints. Moreover, when fingerprints are indistinguishable, the proposed Center-to-Delta Flow (CDF) and Balance Arm Flow (BAF) are catered for further classification. As documented in the experimental results, a good accuracy rate can be achieved, which endorses the effectiveness of the fingerprint classification scheme for the further fingerprint recognition system.

명암도 동시발생 행렬과 웨이블릿 특징 조합에 기반한 지문 분류 방법

본 논문에서는 생체인증 시스템의 하나인 지문인식 시스템의 정확도와 효율성을 높이기 위한 새로운 지문 분류 방법을 제안한다. 기존 연구에 따르면 지문은 융선과 골의 방향과 형상에 따라 몇 가지 유형으로 분류할 수 있다. 지문 데이터베이스를 사전에 유형에 따라 분류해 놓고 인식 대상인 지문의 유형을 정확하게 분류할 수 있다면 지문 인식 시간을 크게 줄일 수 있다. 왜냐하면 선택된 부류 안의 지문들만을 상대로 인증 대상인 지문과 비교하면 되기 때문이다. 본 논문은 우선 지문 영상으로부터 실제 지문 정보가 위치하는 관심영역 추출 방법을 제시한다. 다음엔 추출된 관심영역을 대상으로 질감 인식기반의 명암도 동시발생 행렬과 웨이브릿 변환을 통한 특징 추출 방법을 제시하고 기존의 명암도 동시발생 행렬만을 이용한 특징 추출 방법과 다층 퍼셉트론 및 서포트 벡터 머신을 사용해 성능을 비교한다. In this paper, we propose a novel fingerprint classification method to enhance the accuracy and efficiency of the fingerprint identification system, one of biometrics systems. According to the previous researches, fingerprints can be categorized into the several patterns based on their pattern of ridges and valleys. After construction of fingerprint database based on their patters, fingerprint classification approach can help to accelerate the fingerprint recognition. The reason is that classification methods reduce the size of the search space to the fingerprints of the same category before matching. First, we suggest a method to extract region of interest (ROI) which have real information about fingerprint from the image. And then we propose a feature extraction method which combines gray level co-occurrence matrix (GLCM) and wavelet features. Finally, we compare the performance of our proposed method with the existing method which use only GLCM as the feature of fingerprint by using the multi-layer perceptron and support vector machine.

Development of a Multimodal Biometric Identification and Verification System using Two Fingerprints

Fingerprint recognition is one of the research hotspots of biometrics techniques. Fingerprints are the most widely used biometric feature for identification and verification in the field of biometrics. [1]. The traditional fingerprint recognition systems have such disadvantages as high computation complexity, low speed, low recognition rate to uncompleted or defiled fingerprints, and not robust[2]. In this paper, we propose a multimodel fingerprint identification and verification method based on pattern recognition, which emphasizes global features of fingerprint. With lots of artificial fingerprint samples, the results show that the proposed method is effective, fast, robust and shows the Improvement in rate of false acceptance and false rejections. Experimental results are analyzed and a fingerprint recognition system is introduced. General Terms Pattern Recognition, Fingerprint classification and verification