Finger Image Research Articles

Identifying of unripe Ambon and Hijau banana fruits using computer vision and extreme learning machine classifier

The unripe Indonesian cultivar bananas of ambon kuning (Ambon) and ambon hijau (Hijau) after harvesting show a very close looking, green colour, similar size and shape, even Ambon one is costly than the Hijau. Hence in this study, identification was conducted using computer vision utilizing banana finger image taken with a mobile phone camera. The feature used as a differentiating feature is the shape feature and the skin texture feature of the fruit. The shape features were then extracted using morphological descriptor and convex hull, while the texture features were extracted using local binary pattern (LBP). The extreme learning machine (ELM) classifier was used to recognize both cultivars. A total of 76 banana finger imagery data were used in 3-fold testing. The test results showed that the combined use of shape and LBP features resulted in the highest accuracy, precision and recall values more than 93%. These results showed that the combination of the two features can effectively be used to distinguish the unripe Ambon and Hijau bananas.

Reinforced Deep Learning for Verifying Finger Veins

Recently, personal verifications become crucial demands for providing securities in personal accounts and financial activities. This paper suggests a new Deep Learning (DL) model called the Re-enforced Deep Learning (RDL). This approach provides another way of personal verification by using the Finger Veins (FVs). The RDL consists of multiple layers with a feedback. Two FV fingers are employed for each person, FV of the index finger for first personal verification and FV of the middle finger for re-enforced verification. The used database is from the Hong Kong Polytechnic University Finger Image (PolyUFI) database (Version 1.0). The result shows that the proposed RDL achieved a promising performance of 91.19%. Also, other DL approaches are exploited for comparisons in this study including state-of-the-art models.

A Novel ROI Extraction Method Based on the Characteristics of the Original Finger Vein Image.

As the second generation of biometric technology, finger vein recognition has become a research hotspot due to its advantages such as high security, and living body recognition. In recent years, the global pandemic has promoted the development of contactless identification. However, the unconstrained finger vein acquisition process will introduce more uneven illumination, finger image deformation, and some other factors that may affect the recognition, so it puts forward higher requirements for the acquisition speed, accuracy and other performance. Considering the universal, obvious, and stable characteristics of the original finger vein imaging, we proposed a new Region Of Interest (ROI) extraction method based on the characteristics of finger vein image, which contains three innovative elements: a horizontal Sobel operator with additional weights; an edge detection method based on finger contour imaging characteristics; a gradient detection operator based on large receptive field. The proposed methods were evaluated and compared with some representative methods by using four different public datasets of finger veins. The experimental results show that, compared with the existing representative methods, our proposed ROI extraction method is th of the processing time of the threshold-based methods, and it is similar to the time spent for coarse extraction in the mask-based methods. The ROI extraction results show that the proposed method has better robustness for different quality images. Moreover, the results of recognition matching experiments on different datasets indicate that our method achieves the best Equal Error Rate (EER) of without the refinement of feature extraction parameters, and all the EERs are significantly lower than those of the representative methods.

A Deep Learning Method for Vision Based Force Prediction of a Soft Fin Ray Gripper Using Simulation Data.

Soft robotic grippers are increasingly desired in applications that involve grasping of complex and deformable objects. However, their flexible nature and non-linear dynamics makes the modelling and control difficult. Numerical techniques such as Finite Element Analysis (FEA) present an accurate way of modelling complex deformations. However, FEA approaches are computationally expensive and consequently challenging to employ for real-time control tasks. Existing analytical techniques simplify the modelling by approximating the deformed gripper geometry. Although this approach is less computationally demanding, it is limited in design scope and can lead to larger estimation errors. In this paper, we present a learning based framework that is able to predict contact forces as well as stress distribution from soft Fin Ray Effect (FRE) finger images in real-time. These images are used to learn internal representations for deformations using a deep neural encoder, which are further decoded to contact forces and stress maps using separate branches. The entire network is jointly learned in an end-to-end fashion. In order to address the challenge of having sufficient labelled data for training, we employ FEA to generate simulated images to supervise our framework. This leads to an accurate prediction, faster inference and availability of large and diverse data for better generalisability. Furthermore, our approach is able to predict a detailed stress distribution that can guide grasp planning, which would be particularly useful for delicate objects. Our proposed approach is validated by comparing the predicted contact forces to the computed ground-truth forces from FEA as well as real force sensor. We rigorously evaluate the performance of our approach under variations in contact point, object material, object shape, viewing angle, and level of occlusion.

Inverse Biometrics: Generating Vascular Images From Binary Templates

In this work, we investigate the possibility of generating grayscale images of finger and hand vein patterns from their corresponding binary templates. This would allow us to determine the invertibility of vascular templates, which has implications in biometric security and privacy. The transformation from binary features to a gray-scale image is accomplished using a Pix2Pix Convolutional Neural Network (CNN). The reversibility of 6 different types of binary features is evaluated using this CNN. Further, a number of experiments are conducted using 8 distinct finger vein datasets and 3 hand vein datasets. Results indicate that (a) it is possible to reconstruct the considered vascular images from their binary templates; (b) the reconstructed images can be used for biometric recognition purposes; (c) the CNN trained on one dataset can be successfully used for reconstructing images in a different dataset (cross-dataset reconstruction); and (d) the images reconstructed from one set of features can be successfully used to extract a different set of features for biometric recognition (cross-feature-set generalization). The results of this research further underscore the need for properly securing biometric templates, even if they are of binary nature.

Ignition of Electric Bike Using Fingerprint Sensor

One of the major problems facing developing countries is the safety of vehicles from theft. Hence, we created a prototype model of a fingerprint-based protection system for Electric Bike by combining the Fingerprint sensor module R307 with the Arduino Uno as a solution to the aforementioned problem. This vehicle's biometric system captures an image of the owner's finger, converts it to binary, and stores it in a database. When the motorist places his or her finger on the fingerprint module R307, the device compares its image to the image stored in the database, and if the two are identical, the vehicle's ignition system will turn on. Our primary aim in creating the project is to give users direct access to the system, enabling them to get started quickly and with a clear process that allows us to fully comprehend the system.

Examining the Hand in the Video Consultation.

Background Video consultations could support patient care in hand surgery during social distancing in the COVID-19 era. According to the literature, images of hand and fingers can support telediagnosis in hand emergencies. We present this feasibility study on online video consultation in hand surgery. Methods A structured examination was designed to query the medical history and examine motor skills, sensitivity, strength and function tests of the hand. Thirty examinations on both hands were carried out by online video consultation, then in direct contact and compared with each other. Results With 4560 evaluated range of movement of the hand and finger joints, there was a high correlation between the measurement methods of R = 0.995 (p < 0.0001, confidence interval 0.9946 – 0.9954). In the video-based examination, 84.6% of the measured values showed a deviation of less than 5° compared to the direct examination, 92.8% less than 10° deviation. Good accordance was also found in the patientʼs medical history. An estimating examination of sensitivity, function and strength during video examination is feasible with simple auxiliary aids. Deficits are evident in the detection of scars, in function tests and the absence of haptic findings. Conclusion Online video consultation allows hand examination with sufficient documentation of hand and finger movements (range of motion) and proper evaluation of symptoms. It cannot replace direct examination but complement patient care in hand surgery even beyond the current COVID-19 pandemic.

Computer vision applied to dual-energy computed tomography images for precise calcinosis cutis quantification in patients with systemic sclerosis

BackgroundAlthough treatments have been proposed for calcinosis cutis (CC) in patients with systemic sclerosis (SSc), a standardized and validated method for CC burden quantification is necessary to enable valid clinical trials. We tested the hypothesis that computer vision applied to dual-energy computed tomography (DECT) finger images is a useful approach for precise and accurate CC quantification in SSc patients.MethodsDe-identified 2-dimensional (2D) DECT images from SSc patients with clinically evident lesser finger CC lesions were obtained. An expert musculoskeletal radiologist confirmed accurate manual segmentation (subtraction) of the phalanges for each image as a gold standard, and a U-Net Convolutional Neural Network (CNN) computer vision model for segmentation of healthy phalanges was developed and tested. A validation study was performed in an independent dataset whereby two independent radiologists manually measured the longest length and perpendicular short axis of each lesion and then calculated an estimated area by assuming the lesion was elliptical using the formula long axis/2 × short axis/2 × π, and a computer scientist used a region growing technique to calculate the area of CC lesions. Spearman’s correlation coefficient, Lin’s concordance correlation coefficient with 95% confidence intervals (CI), and a Bland-Altman plot (Stata V 15.1, College Station, TX) were used to test for equivalence between the radiologists’ and the CNN algorithm-generated area estimates.ResultsForty de-identified 2D DECT images from SSc patients with clinically evident finger CC lesions were obtained and divided into training (N = 30 with image rotation × 3 to expand the set to N = 120) and test sets (N = 10). In the training set, five hundred epochs (iterations) were required to train the CNN algorithm to segment phalanges from adjacent CC, and accurate segmentation was evaluated using the ten held-out images. To test model performance, CC lesional area estimates calculated by two independent radiologists and a computer scientist were compared (radiologist 1 vs. radiologist 2 and radiologist 1 vs. computer vision approach) using an independent test dataset comprised of 31 images (8 index finger and 23 other fingers). For the two radiologists’, and the radiologist vs. computer vision measurements, Spearman’s rho was 0.91 and 0.94, respectively, both p < 0.0001; Lin’s concordance correlation coefficient was 0.91 (95% CI 0.85–0.98, p < 0.001) and 0.95 (95% CI 0.91–0.99, p < 0.001); and Bland-Altman plots demonstrated a mean difference between radiologist vs. radiologist, and radiologist vs. computer vision area estimates of − 0.5 mm2 (95% limits of agreement − 10.0–9.0 mm2) and 1.7 mm2 (95% limits of agreement − 6.0–9.5 mm2, respectively.ConclusionsWe demonstrate that CNN quantification has a high degree of correlation with expert radiologist measurement of finger CC area measurements. Future work will include segmentation of 3-dimensional (3D) images for volumetric and density quantification, as well as validation in larger, independent cohorts.

Image Recognition Method for Pitching Fingers of Basketball Players Based on Symmetry Algorithm

In the basketball game, the accuracy and standardization of pitching are directly related to the score. So it is very important to analyze the pitching figure movement to have a better positioning of the fingers. There are limited techniques to recognize the movement. The human motion recognition method is one of them. It utilizes the spatiotemporal image segmentation and interactive region detection to recognize images of pitching finger movement of basketball players. This method has a limitation that the symmetrical information of the human body and sphere cannot be excavated, which leads to certain errors in recognition effect. This paper presents a method of recognizing pitching finger movement of basketball players based on symmetry algorithm, constructs an acquisition model, carries out edge contour detection and adaptive feature segmentation of images of pitching finger movement of basketball players, and uses a fixed threshold to segment finger image to extract players’ hand contour and locate the middle axis of the finger. On this basis, the symmetry recognition method based on nematode recognition algorithm is used to recognize the symmetry of basketball pitching finger movement image and complete the accurate recognition of basketball pitching finger movement image. The experimental results show that the proposed method can effectively recognize the basketball player’s finger movement image. The average recognition accuracy is 98%, the growth rate of recognition speed is 98%, and the maximum recognition time is 12 s. The robustness of the proposed method is 0.45.

Joint discriminative feature learning for multimodal finger recognition

Recently, finger-based multimodal biometrics, due to its high security and stability, has received considerable attention compared with unimodal biometrics. However, existing multimodal finger feature extraction approaches separately extract the features of different modalities, at the same time ignoring correlations among these different modalities. Furthermore, most of the conventional finger feature representation approaches are hand-crafted by design, which require strong prior knowledge. It is therefore very important to explore and develop a suitable feature representation and fusion strategy for multimodal biometrics recognition. In this paper, we proposed a joint discriminative feature learning (JDFL) framework for multimodal finger recognition by combining finger vein (FV) and finger knuckle print (FKP) patterns. For the FV and FKP images, we first established the informative dominant direction vector by convoluting a bank of Gabor filters and the original finger image. Then, we developed a simple yet effective feature learning algorithm, which simultaneously maximized the distance of between-class samples and minimized the distance of within-class samples, as well as maximized the correlation among inter-modality samples of the within-class. Finally, we integrated the block-wise histograms of the learned feature maps together for multimodal finger fusion recognition. Experimental results demonstrated that the proposed approach has a better recognition performance than state-of-the-art finger recognition methods.

Musculoskeletal Abnormality Detection in Medical Imaging Using GnCNNr (Group Normalized Convolutional Neural Networks with Regularization)

Musculoskeletal abnormality detection serves as an advantage to the professionals in the medical domain and also serves as an assistance in the diagnosis as well as the treatment of the abnormalities. This paper mainly focuses on accurately detecting musculoskeletal abnormalities using various deep learning models and techniques. MURA dataset has been used for experimentation. MURA dataset has 14,863 images of finger, wrist, elbow, shoulder, forearm and hand which has been analyzed using deep learning models. In this research paper, authors have proposed GnCNNr model which utilizes group normalization, weight standardization and cyclic learning rate scheduler to enhance the accuracy, precision and other model interpretation metrics. The musculoskeletal abnormality has been detected by using various deep learning models. Accuracy and Cohen Kappa have been taken as the evaluation criteria. The highest accuracy of 85% and Cohen Kappa statistic of 0.698 was achieved by the GnCNNr model in comparison with the conventional deep learning methods like DenseNet, Inception, Inception v2 model.

Local discriminant coding based convolutional feature representation for multimodal finger recognition

Compared with unimodal biometrics systems, multimodal systems can effectively improve the recognition performance in accuracy and security. However, exploring a robust feature representation approach suitable for multiple modalities remains a crucial and challenging problem in the personal authentication community. In this paper, we proposed a discriminant local coding based convolutional neural network (LC-CNN) for multimodal finger recognition by fusing fingerprint, finger-vein, and finger-knuckle-print traits. Specifically, for each tri-modal finger images, we first presented a weighted local gradient coding (WLGC) operator to enhance the discriminant characteristics and formed the local coding layer (LC-layer) by reconstructing the WLGC operator with a bank of predefined convolution layers. Then, we established a simple yet effective LC-CNN model to extract deeper tri-modal finger features. Finally, the extracted feature vectors of three modalities are concatenated and input into a Support Vector Machine (SVM) for image classification. Experimental results demonstrate that the proposed method achieves a stable, highly accurate, and robust performance in multimodal finger recognition.

Stable complex conjugate artifact removal in OCT using circularly polarized light as reference

In Fourier domain optical coherence tomography (FDOCT), the depth profile is mirrored about the zero delay between the sample and reference optical paths, limiting the imaging depth to half of the entire ranging space and undermining the optimal sensitivity window. We present a new method, to the best of our knowledge, to remove the complex conjugate artifact by using circularly polarized light as reference. Quadrature detection of the complex fringe is achieved by utilizing the intrinsic λ/4 delay between two polarization channels. We use passive broadband polarization optics to control the polarization state of the light in the reference and sample arms and a balanced polarization diversity detection unit to simultaneously detect phase-shifted fringes. We demonstrate a 40 dB artifact suppression ratio with a swept-source optical coherence tomography system. Our proposed method is immune to sample motion and laser phase noise, and imposes no restrictions to the source bandwidth, imaging speed, or computational power. In vivo images of the human finger, as well as the cornea and retina of a non-human primate, were demonstrated.

A Digital Camera-Based Rotation-Invariant Fingerprint Verification Method

Fingerprint registration and verification is an active area of research in the field of image processing. Usually, fingerprints are obtained from sensors; however, there is recent interest in using images of fingers obtained from digital cameras instead of scanners. An unaddressed issue in the processing of fingerprints extracted from digital images is the angle of the finger during image capture. To match a fingerprint with 100% accuracy, the angles of the matching features should be similar. This paper proposes a rotation and scale-invariant decision-making method for the intelligent registration and recognition of fingerprints. A digital image of a finger is taken as the input and compared with a reference image for derotation. Derotation is performed by applying binary segmentation on both images, followed by the application of speeded up robust feature (SURF) extraction and then feature matching. Potential inliers are extracted from matched features by applying the M-estimator. Matched inlier points are used to form a homography matrix, the difference in the rotation angles of the finger in both the input and reference images is calculated, and finally, derotation is performed. Input fingerprint features are extracted and compared or stored based on the decision support system required for the situation.

Feature-Level Fusion of Finger Vein and Fingerprint Based on a Single Finger Image: The Use of Incompletely Closed Near-Infrared Equipment

Due to its portability, convenience, and low cost, incompletely closed near-infrared (ICNIR) imaging equipment (mixed light reflection imaging) is used for ultra thin sensor modules and have good application prospects. However, equipment with incompletely closed structure also brings some problems. Some finger vein images are not clear and there are sparse or even missing veins, which results in poor recognition performance. For these poor quality ICNIR images, however, there is additional fingerprint information in the image. The analysis of ICNIR images reveals that the fingerprint and finger vein in a single ICNIR image can be enhanced and separated. We propose a feature-level fusion recognition algorithm using a single ICNIR finger image. Firstly, we propose contrast limited adaptive histogram equalization (CLAHE) and grayscale normalization to enhance fingerprint and finger vein texture, respectively. Then we propose an adaptive radius local binary pattern (ADLBP) feature combined with uniform pattern to extract the features of fingerprint and finger vein. It solves the problem that traditional local binary pattern (LBP) is unable to describe the texture features of different sizes in ICNIR images. Finally, we fuse the feature vectors of ADLBP block histogram for a fingerprint and finger vein, and realize feature-layer fusion recognition by a threshold decision support vector machine (T-SVM). The experimentation results showed that the performance of the proposed algorithm was noticeably better than that of the single model recognition algorithm.

Review: Clinical in vivo multiphoton FLIM tomography

Fluorescence Lifetime Imaging (FLIM) in life sciences based on ultrashort laser scanning microscopy and time-correlated single photon counting (TCSPC) started 30 years ago in Jena/East-Germany. One decade later, first two-photon FLIM images of a human finger were taken with a lab microscope based on a tunable femtosecond Ti:sapphire laser. In 2002/2003, first clinical non-invasive two-photon FLIM studies on patients with dermatological disorders were performed using a novel multiphoton tomograph. Current in vivo two-photon FLIM studies on human subjects are based on TCSPC and focus on (i) patients with skin inflammation and skin cancer as well as brain tumors, (ii) cosmetic research on volunteers to evaluate anti-ageing cremes, (iii) pharmaceutical research on volunteers to gain information on in situ pharmacokinetics, and (iv) space medicine to study non-invasively skin modifications on astronauts during long-term space flights. Two-photon FLIM studies on volunteers and patients are performed with multiphoton FLIM tomographs using near infrared femtosecond laser technology that provide rapid non-invasive and label-free intratissue autofluorescence biopsies with picosecond temporal resolution.

RETRACTED ARTICLE: An efficient method for human hand gesture detection and recognition using deep learning convolutional neural networks

The physical movement of the human hand produces gestures, and hand gesture recognition leads to the advancement in automated vehicle movement system. In this paper, the human hand gestures are detected and recognized using convolutional neural networks (CNN) classification approach. This process flow consists of hand region of interest segmentation using mask image, fingers segmentation, normalization of segmented finger image and finger recognition using CNN classifier. The hand region of the image is segmented from the whole image using mask images. The adaptive histogram equalization method is used as enhancement method for improving the contrast of each pixel in an image. In this paper, connected component analysis algorithm is used in order to segment the finger tips from hand image. The segmented finger regions from hand image are given to the CNN classification algorithm which classifies the image into various classes. The proposed hand gesture detection and recognition methodology using CNN classification approach with enhancement technique stated in this paper achieves high performance with state-of-the-art methods.

Finger-Vein Recognition Based on Densely Connected Convolutional Network Using Score-Level Fusion With Shape and Texture Images

Biometrics using finger-veins is a recognition method based on the shape of veins in fingers, and it has the advantage of difficulty to be forged. However, a shade is inevitably produced due to the bones and fingernails, and a change in illumination occurs when acquiring the images of finger-veins. Previous studies have conducted finger-vein recognition using a single-type texture image or finger-vein segmented image (shape image). A texture image provides numerous features, but it is vulnerable to the changes in illumination during recognition and contains noises in regions other than the finger-vein region. A shape image is less affected by noises; however, the recognition accuracy is significantly reduced due to fewer features available and mis-segmented regions caused by shades. In this study, therefore, rough finger-vein regions in an image are detected to reduce the effect of mis-segmented regions, to complement the drawbacks of shape image-based finger-vein recognition. Furthermore, score-level fusion is performed for two output scores of deep convolutional neural network extracted from the texture and shape images, which can reduce the sensitivity to noise, while diverse features provided in the texture image are used efficiently. Two open databases, the Shandong University homologous multi-modal traits finger-vein database and Hong Kong Polytech University finger image database, are used for experiments, and the proposed method shows better recognition performance than the state-of-the-art method.

Pre-trained based CNN model to identify finger vein

In current biometric security systems using images for security authentication, finger vein-based systems are getting special attention in particular attributable to the facts such as insurance of data confidentiality and higher accuracy. Previous studies were mostly based on finger-print, palm vein etc. however, due to being more secure than fingerprint system and due to the fact that each person's finger vein is different from others finger vein are impossible to use to do forgery as veins reside under the skin. The system that we worked on functions by recognizing vein patterns from images of fingers which are captured using near Infrared(NIR) technology. Due to the lack of an available database, we created and used our own dataset which was pre-trained using transfer learning of AlexNet model and verification is done by applying correct as well as incorrect test images. The result of deep convolutional neural network (CNN) based several experimental results are shown with training accuracy, training loss, Receiver Operating Characteristic (ROC) Curve and Area Under the Curve (AUC).

FV-GAN: Finger Vein Representation Using Generative Adversarial Networks

In finger vein verification, the most important and challenging part is to robustly extract finger vein patterns from low-contrast infrared finger images with limited a priori knowledge. Although recent convolutional neural network (CNN)-based methods for finger vein verification have shown powerful capacity for feature representation and promising perspective in this area, they still have two critical issues to address. First, these CNN-based methods unexceptionally utilize fully connected layers, which restrict the size of finger vein images to process and increase the processing time. Second, the capacity of CNN for feature representation generally suffers from the low quality of finger vein ground-truth pattern maps for training, particularly due to outliers and vessel breaks. To address these issues, in this paper, we propose a novel approach termed FV-GAN to finger vein extraction and verification, based on generative adversarial network (GAN), as the first attempt in this area. Unlike the CNN-based methods, FV-GAN learns from the joint distribution of finger vein images and pattern maps rather than the direct mapping between them, with the aim at achieving stronger robustness against outliers and vessel breaks. Moreover, FV-GAN adopts fully convolutional networks as the basic architecture and discards fully connected layers, which relaxes the constraint on the input image size and reduces the computational expenditure for feature extraction. Furthermore, we design an adversarial training strategy and propose a hybrid loss function for FV-GAN. The experimental results on two public databases show significant improvement by FV-GAN in finger vein verification in terms of both verification accuracy and equal error rate.