Finger Image Research Articles

A Comparative Study of High-Resolution Chemical-Shift-Eliminated Magnetic Resonance Imaging of Finger Specimens with Microcomputed Tomography.

Objective:High-resolution images of finger joints with chemical-shift elimination can be obtained using an interleaved water-fat (IWF) sequence. This study assessed IWF imaging of finger joints in the delineation of bone structures by comparing images of cadaver fingers with those of microcomputed tomography (CT) that served as a standard reference.Materials and Methods:IWF images with spatial resolution of 176 µ × 176 µ × 300 µ were obtained from the distal and proximal interphalangeal joints of two cadaver finger specimens using a custom-built radiofrequency receive coil at 1.5T. Regular three-dimensional gradient-echo (GRE) images were also acquired with similar parameters and compared with the IWF images to evaluate the effects of chemical shift. Micro-CT scans were obtained and served as the standard reference. The image data were reviewed by two experienced musculoskeletal radiologists in consensus. The delineation of normal joint structures and abnormalities in the finger specimens as revealed by the magnetic resonance imaging (MRI) and micro-CT images were compared. The IWF and regular GRE images were assigned scores 0–3 for the depiction of apparent marginal bone defects, with zero being the same in appearance to the micro-CT image and three as having minimal resemblance to it. Statistical analysis of the scoring results was conducted to compare the two MRI techniques.Results:The high-resolution IWF images provided accurate delineation of bone and calcified structures as seen in micro-CT. The thickness of subchondral bone was depicted similarly on the IWF water + fat and the micro-CT images but not on the regular GRE images. The regular GRE sequence showed false marginal bone defects not observed with IWF and micro-CT. In addition, the IWF water-only images facilitated the identification of bone cyst by revealing its water content.Conclusion:High-resolution IWF imaging should be useful for the early diagnosis and treatment assessment of arthritis and should also benefit basic research in the pathophysiology of the disease.

Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition.

Recently, finger-based biometrics, including fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP) with high convenience and user friendliness, have attracted much attention for personal identification. The features expression which is insensitive to illumination and pose variation are beneficial for finger trimodal recognition performance improvement. Therefore, exploring suitable method of reliable feature description is of great significance for developing finger-based biometric recognition system. In this paper, we first propose a correction approach for dealing with the pose inconsistency among the finger trimodal images, and then introduce a novel local coding-based feature expression method to further implement feature fusion of FP, FV, and FKP traits. First, for the coding scheme a bank of oriented Gabor filters is used for direction feature enhancement in finger images. Then, a generalized symmetric local graph structure (GSLGS) is developed to fully express the position and orientation relationships among neighborhood pixels. Experimental results on our own-built finger trimodal database show that the proposed coding-based approach achieves excellent performance in improving the matching accuracy and recognition efficiency.

Finger Recognition by Feature Length

A small circle cake in a finger image is used to extract the partial finger image. Subsequently, the major axis length of this extracted circle cake is computed. Next, more circle cakes are extracted and the major axis length of each individual circle cake is computed. These obtained major axis lengths are chained together circularly to generate recognition features. These features are used to recognize a finger. The chain-generated feature is compared to its adjacent features to locate the most match one. For every pixel in the sample image, the address of the match target in the unknown image is recorded. The trajectories from the sample image to unknown image can be similar and can be diverted significantly depending on the similarity of the two compared images. If the trajectories are similar, the match targets can hold together. Otherwise, the match targets are deviated to different places. The convergence and deviation situation can be used as an indictor to show whether the two compared images are coming from the identical source or not.

Mirror finger patterns of apparent monozygotic twins and sib pairs with Schizophrenia.

Background:Although mirror images are noted in some twins, no such reports are available for twins and subjects with schizophrenia.Aim:The study was to assess the occurrence of mirror image finger patterns in apparent monozygotic twins with schizophrenia. Another objective was to elucidate these characteristics among sib pairs with schizophrenia for comparison with those of the twins.Materials and Methods:Eight apparent monozygotic twin pairs and eight sib pairs with schizophrenia were investigated. The frequency of identical patterns in the right side finger of one twin and the corresponding left side finger of the other twin was assessed, and similarly on other sides. Similar assessment was made in sib pairs with schizophrenia and normal sib pairs.Results:The left middle finger pattern of one of the twin pair was found to be the mirror image of the right middle finger of the other twin in all the twin pairs studied and so was in seven of the sib pairs with schizophrenia. These mirror images of sib pairs with schizophrenia was more than those of normal sib pairs. This difference was accentuated with significantly more of these patterns in the twins in comparison to those among normal sib pairs. Notably, no difference emerged between the sib pairs with schizophrenia and the twins in any of their finger pairs.Conclusion:Mirror images that are probably due to factors like abnormal genotypes and L- DNA, appear to be promising tools to study the etiology of schizophrenia.

Finger-Vein Recognition Based on Deep DenseNet Using Composite Image

Finger-vein recognition has the advantages of high immutability, as finger veins are located under the skin, high user convenience, as a non-invasive and contactless capture device, is used, and high readability even when one of the fingers is damaged or not available for recognition. However, there is an issue of recognition performance degradation caused by finger positional variation, misalignment, and shading from uneven illumination. The existing hand-crafted feature-based methods have exhibited varied performance depending on how these issues were handled by pre-processing. To overcome this shortcoming of hand-crafted feature-based methods, convolutional neural network (CNN)-based recognition methods have been researched. The existing systems based on a CNN use two methods: using a difference image as the input to the network and calculating the distance between feature vectors extracted from the CNN. Difference images can be susceptible to noise as they are generated by differences in pixel values. Also, the method for calculating the distance between feature vectors cannot employ all layers of the trained network and has less accuracy than the method employing difference images. To address these issues, this paper examined a method less susceptible to noise and which uses the entire network; a composite image of two finger-vein images was used as the input to a deep, densely-connected convolutional network (DenseNet). Two open databases, namely Shandong University homologous multi-modal traits (SDUMLA-HMT) finger-vein database and The Hong Kong Polytechnic University finger image database (version 1), were used for experiments and the results show that the proposed method has greater performance than the existing methods.

Pengenalan Gestur Jari Menggunakan Pengolahan Citra untuk Mengendalikan Joint pada Base Robot Lengan

The Robot is a technology that can help human to do daily activities. One type of robot is an arm robot, arm robot can work automatically, manually, and a combination of both. Some techniques that can be used to give commands to the robot are to use hand and finger gestures, to do the techniques can utilize the vision machine. One of the advantages of using a vision machine is that it does not require many electronic components to recognize hand and finger gestures. The focus of this research is to implement a camera to recognize the operator’s finger gestures so that the gesture can give commands to the robot. The camera captures the image of operator's finger, the image is a process inside the computer to obtain the pixel coordinate parameters of the index fingertip and right lower pixel of the image, and then the angle obtained from both coordinates using trigonometric equations. The result is that the robot can follow the movement of the finger when the angle between 30° to 150°.

Multimodal Biometric Recognition Based on Convolutional Neural Network by the Fusion of Finger-Vein and Finger Shape Using Near-Infrared (NIR) Camera Sensor.

Finger-vein recognition, which is one of the conventional biometrics, hinders fake attacks, is cheaper, and it features a higher level of user-convenience than other biometrics because it uses miniaturized devices. However, the recognition performance of finger-vein recognition methods may decrease due to a variety of factors, such as image misalignment that is caused by finger position changes during image acquisition or illumination variation caused by non-uniform near-infrared (NIR) light. To solve such problems, multimodal biometric systems that are able to simultaneously recognize both finger-veins and fingerprints have been researched. However, because the image-acquisition positions for finger-veins and fingerprints are different, not to mention that finger-vein images must be acquired in NIR light environments and fingerprints in visible light environments, either two sensors must be used, or the size of the image acquisition device must be enlarged. Hence, there are multimodal biometrics based on finger-veins and finger shapes. However, such methods recognize individuals that are based on handcrafted features, which present certain limitations in terms of performance improvement. To solve these problems, finger-vein and finger shape multimodal biometrics using near-infrared (NIR) light camera sensor based on a deep convolutional neural network (CNN) are proposed in this research. Experimental results obtained using two types of open databases, the Shandong University homologous multi-modal traits (SDUMLA-HMT) and the Hong Kong Polytechnic University Finger Image Database (version 1), revealed that the proposed method in the present study features superior performance to the conventional methods.

An intelligent technique for uniquely recognising face and finger image using learning vector quantisation (LVQ)-based template key generation

An intelligent technique for uniquely recognising face and finger image using learning vector quantisation (LVQ)-based template key generation

Sharpness Enhancement of Finger-Vein Image Based on Modified Un-sharp Mask with Log-Gabor Filter

Finger vein biometric trait has been increasingly used for personal verification or identification in security applications. Normally, the sample image of finger vein is captured under uneven illumination due to geometry variation of finger and it is usually in low contrast condition which will affect the extracted pattern of the vein. In order to have a reliable vein pattern extraction, the contrast and sharpness enhancement of finger image is executed before the pattern extraction procedure. Un-sharp Mask technique has been considered as one of good tools for the sharpness and contrast enhancement of images. However, it suffers with two drawbacks for our intended purpose which are halo effect appears around the finger image and over enhancement of noise to the vein image. Due to this problem, this paper proposes a Modified Un-sharp Mask (MUM) with Log-Gabor filter method to enhance the sharpness and contrast of finger vein image. In this study, the Modified Repeated Line Tracking (MRLT) algorithm is then used to extract the features from the enhanced vein pattern. The experimental results show that the extracted pattern of finger vein contains more details of vein and detection of small details of finger vascular is facilitated after applying the proposed finger vein enhancement method.

An intelligent technique for uniquely recognising face and finger image using learning vector quantisation (LVQ)-based template key generation

In current days, to identify, verify and detect the humans by using the bio recognition based on multimodal biometric was speedily developed which focus to necessitate the security keys in the authentication process of industries/organisation. The main goal of this organisation system is to integrate the instability biometric feature of the users and it is also used to formulate the key unimaginable to an unauthorised person. In this proposed work, in multimodal biometrics methods, particularly face and fingerprint based novel pattern matching is described. There are three modules to be used for exact feature extraction; multimodal biometric pattern generation and pattern matching are used to achieve better result for this proposed work. At first, from the face images and finger prints the minutiae points, face features and some other features are extracted. Consequently, by using a density-based score level fusion, the extracted features are merged together at match score level to create the multi-biometric pattern. After that, learning vector quantisation is used to perform the pattern matching. The assessment process was performed using large scale subjects to enter the system proving the ability of the proposed system over the state of art.

Frequency of inflammatory-like MR imaging findings in asymptomatic fingers of healthy volunteers.

To describe the frequency of inflammatory-like findings on MR imaging in asymptomatic volunteers and compare them with patients with known rheumatoid arthritis and psoriatic arthritis. MR images of fingers in 42 asymptomatic volunteers and 33 patients with rheumatoid/psoriatic arthritis were analyzed. The Outcome Measures in Rheumatology Clinical Trials (OMERACT) Rheumatoid/Psoriatic Arthritis MRI Scoring System (RAMRIS/PsAMRIS) and tenosynovitis scoring system were used to assess: bone marrow edema (BME), erosions, tendon sheath fluid/tenosynovitis, joint effusion, and soft-tissue edema. Findings and scores were compared between volunteers and patients. Inter-reader agreement was calculated (intraclass correlation coefficients, ICC). In volunteers, tendon sheath fluid was very common in at least one location (42/42 volunteers for reader 1, 34/42 volunteers for reader 2). BME, erosions, joint effusion, and soft-tissue edema were absent (except one BME in the 3rd proximal phalanx for reader 1). Tendon sheath fluid scores in volunteers and tenosynovitis scores in patients were high (reader 1, 7.17 and 5.39; reader 2, 2.31 and 5.45). Overall, inter-reader agreement was substantial (ICC=0.696-0.844), except for tendon sheath fluid (ICC=0.258). Fluid in the finger flexor tendon sheaths may be a normal finding and without gadolinium administration should not be interpreted as tenosynovitis. Bone marrow edema, erosions, joint effusion, and soft-tissue edema in the fingers most likely reflect pathology if present.

High‐resolution and compact virtual mouse using lens arrays to capture finger images on light sensors

AbstractTo realize a finger positioning device, as called “virtual mouse,” to replace a touchpad, touchscreen, or even real mouse, current positioning technologies cannot achieve a sufficient resolution, a compact volume, and a simple detection algorithm simultaneously. For this problem, using a light‐emitting diode source, two lens arrays, and two light sensors, we design and implement a virtual mouse prototype. The optical architecture is carefully determined for a compact volume, a sufficient resolution, and a high detection accuracy. Corresponding to a compact system volume of 3.1 mm (thickness) × 4.5 mm (length) × 2, a theoretical resolution higher than 25 pixels per inch (ppi) can be obtained over a working area of 10 cm × 10 cm. Experiments are also implemented, in which a mean detection error of 0.24 cm that corresponds to approximately two distinguishable points, and a minimal resolution of 26 ppi over the whole working area are verified. If the system thickness is relaxed to 25 mm, a resolution higher than 200 ppi can be achieved. The proposed virtual mouse, which is simple enough and potential to be extended for three‐dimensional position detection, can be integrated with a flat panel display to achieve a compact display application that can interact with users.

A fusion approach based on infrared finger vein transmitting model by using multi-light-intensity imaging

An infrared transmitting model from the observed finger vein images is proposed in this paper by using multi-light-intensity imaging. This model is estimated from many pixels’ values under different intensity light in the same scene. Due to the fusion method could be applied in biometric system, the vein images of finger captured in the system, we proposed in this paper, will be normalized and preserved the intact of the vein patterns of the biometric data from tested human’s body. From observed pixels under multi-light-intensity, the curve of the transmitting model is recovered by sliding both of the sampled curve segments and using curve-fitting. The fusion method with each pixel level weighting based on the proposed transmitting model curve is adopted by the smooth spatial and estimation of the block quality. Finally, the results shown that our approach is a convenient and practicable approach for the infrared image fusion and subsequent processing for biometric applications.

Rapid volumetric photoacoustic tomographic imaging with a Fabry-Perot ultrasound sensor depicts peripheral arteries and microvascular vasomotor responses to thermal stimuli

PurposeTo determine if a new photoacoustic imaging (PAI) system successfully depicts (1) peripheral arteries and (2) microvascular circulatory changes in response to thermal stimuli.MethodsFollowing ethical permission, 8 consenting subjects underwent PAI of the dorsalis pedis (DP) artery, and 13 completed PAI of the index fingertip. Finger images were obtained after immersion in warm (30-35 °C) or cold (10-15 °C) water to promote vasodilation or vasoconstriction. The PAI instrument used a Fabry-Perot interferometeric ultrasound sensor and a 30-Hz 750-nm pulsed excitation laser. Volumetric images were acquired through a 14 × 14 × 14-mm volume over 90 s. Images were evaluated subjectively and quantitatively to determine if PAI could depict cold-induced vasoconstriction. The full width at half maximum (FWHM) of resolvable vessels was measured.ResultsFingertip vessels were visible in all participants, with mean FWHM of 125 μm. Two radiologists used PAI to correctly identify vasoconstricted fingertip capillary beds with 100% accuracy (95% CI 77.2-100.0%, p < 0.001). The number of voxels exhibiting vascular signal was significantly smaller after cold water immersion (cold: 5263 voxels; warm: 363,470 voxels, p < 0.001). The DP artery was visible in 7/8 participants (87.5%).ConclusionPAI achieves rapid, volumetric, high-resolution imaging of peripheral limb vessels and the microvasculature and is responsive to vasomotor changes induced by thermal stimuli.Key points• Fabry-Perot interferometer-based photoacoustic imaging (PAI) generates volumetric, high-resolution images of the peripheral vasculature.• The system reliably detects thermally induced peripheral vasoconstriction (100% correct identification rate, p < 0.001).• Vessels measuring less than 100 μm in diameter can be depicted in vivo.

Piezoelectric line detector array for photoacoustic tomography

Photoacoustic tomography relies on a dense coverage of the surface surrounding the imaged object with ultrasound sensors in order to enable an accurate reconstruction. A curved arrangement of integrating line sensors is proposed that is able to acquire data for a linear projection image of the absorbed energy density distribution in the object. Upon rotation of the object relative to the array, three-dimensional (3D) images can be obtained.The proposed design is based on the cost-effective piezoelectric polymer film technology with 64 line shaped sensors arranged on a half-cylindrical surface. It is combined with an optical parametric oscillator for the near infrared as a source for laser pulses. Image reconstruction from recorded signals consists of two-dimensional (2D) back projection followed by an inverse Radon transform.The tomograph exhibits a spatial resolution on the order of 200 to 250μm. In a phantom experiment, the steps from acquisition of a single, 2D projection image to a full 3D image are demonstrated. Finally, in vivo projection images of a human finger are shown, revealing the near real-time imaging capability of the device in 2D.

ARTeM: a new system for human authentication using finger vein images

A new system (ARTeM) for human authentication using finger vein images is described here. The developed algorithm combines 1) a fuzzy contrast enhancement algorithm with 2) a mutual information and affine transformation based registration technique and 3) a correlation coefficient based template matching algorithm, to detect the identity of a person based on the match-scores with finger vein images stored in the database. For performance assessment of the ARTeM algorithm, the benchmark SDUMLA multimodal biometric database containing 3816 images of 106 persons is used. On the complete database, up to 95.28% classification accuracy is achieved with single finger images; while up to 98.11% accuracy is observed with a consensus of two fingers. On a reduced subset of 86 persons’ database, 98.84% accuracy is achieved with single finger classification and cent percent classification is obtained using a consensus of two fingers. Comparative analyses with other works also validate the effectiveness of the developed methodology.

Finger-vein recognition based on dual-sliding window localization and pseudo-elliptical transformer

Uneven illumination occurs during finger imaging because of the influence of several factors, including the position and posture of the finger, the uniformity of near-infrared light, and the influence of ambient light. Existing phalangeal joint locating methods are sensitive to light illumination and cannot locate phalangeal joint stably. In this study, we propose a dual-sliding window model to accurately detect the position of the phalangeal joint of the finger-vein image, which is robust to light illumination, and to extract a more stable region of interest. Planar imaging generates different finger-vein images of the same finger at different acquisitions by space rotation of the finger. Thus, a pseudo-elliptical sampling model is proposed to retain the spatial distribution of vein patterns, to reduce the redundant information in finger images, and to reduce differences. Finally, a two-dimensional principal component analysis is used to project the transformed image for feature extraction. We calculated the Euclidean distance to measure the similarity between the test and training samples. Experiments in the three different databases show that the proposed method is effective and reliable and improves the performance of a finger-vein identification system.

Finger image quality assessment features – definitions and evaluation

Finger image quality assessment is a crucial part of any system where a high biometric performance and user satisfaction is desired. Several algorithms measuring selected aspects of finger image quality have been proposed in the literature, yet only few of them have found their way into quality assessment algorithms used in practice. The authors provide comprehensive algorithm descriptions and make available implementations of adaptations of ten quality assessment algorithms from the literature which operates at the local or the global image level. They evaluate the performance on four datasets in terms of the capability in determining samples causing false non-matches and by their Spearman correlation with sample utility. The authors' evaluation shows that both the capability in rejecting samples causing false non-matches and the correlation between features varies depending on the dataset.

Ứng dụng chu tuyến vào việc loại bỏ đối tượng nhỏ trong quá trình véc tơ hoá tự động

In this paper, we describe a method of using contours to delete small objects for improving feature images. In general, small objects are holes or noises. Therefore, they can be detected and filled or deleted easily by using our method without patterns in automatic vectorizing process. Besides, the paper also shows. types of maps that can be vectorized and have been verified by using this method in MAPSCAN software package that has been developed in the Oepartment of Pattern Recognition and Knowledge Engineering such as: - Topography, hydrography and transports maps etc. - Technical, designing, electronic circle drawings and finger images etc.

Biometric Security Technique: A Review

The objective of this paper is to present different techniques of the fingerprint recognition. Two significant techniques Minutia based technique and the correlation based technique are reviewed. Both have their own significance. Minutia is working on specific part of the finger image called ridge and bifurcation. Correlation works on the gray level image data that extract from the finger image. Minutia based technique used different algorithm to extract the features and to check the accuracy and reduce the error rate. Ransac (random sample census) algorithm is tries to work on some random transformation and find the good one. Algorithm for local correlation based on the Markov random field modal which is used to smooth the orientation field. The main finding is to get the better authentication system with a better strength.