<span lang="EN-US">Nowadays, the fingerprint identification system is the most exploited sector of biometric. Fingerprint image segmentation is considered one of its first processing stage. Thus, this stage affects typically the feature extraction and matching process which leads to fingerprint recognition system with high accuracy. In this paper, three major steps are proposed. First, Soble and TopHat filtering method have been used to improve the quality of the fingerprint images. Then, for each local block in fingerprint image, an accurate separation of the foreground and background region is obtained by K-means clustering for combining 5-dimensional characteristics vector (variance, difference of mean, gradient coherence, ridge direction and energy spectrum). Additionally, in our approach, the local variance thresholding is used to reduce computing time for segmentation. Finally, we are combined to our system DBSCAN clustering which has been performed in order to overcome the drawbacks of K-means classification in fingerprint images segmentation. The proposed algorithm is tested on four different databases. Experimental results demonstrate that our approach is significantly efficacy against some recently published techniques in terms of separation between the ridge and non-ridge region.</span>

In recent years, the need for security of personal data is becoming progressively important. In this regard, the identification system based on fusion of multibiometric is most recommended for significantly improving and achieving the high performance accuracy. The main purpose of this paper is to propose a hybrid system of combining the effect of tree efficient models: Convolutional neural network (CNN), Softmax and Random forest (RF) classifier based on multi-biometric fingerprint, finger-vein and face identification system. In conventional fingerprint system, image pre-processed is applied to separate the foreground and background region based on K-means and DBSCAN algorithm. Furthermore, the features are extracted using CNNs and dropout approach, after that, the Softmax performs as a recognizer. In conventional fingervein system, the region of interest image contrast enhancement using exposure fusion framework is input into the CNNs model. Moreover, the RF classifier is proposed for classification. In conventional face system, the CNNs architecture and Softmax are required to generate face feature vectors and classify personal recognition. The score provided by these systems is combined for improving Human identification. The proposed algorithm is evaluated on publicly available SDUMLA-HMT real multimodal biometric database using a GPU based implementation. Experimental results on the datasets has shown significant capability for identification biometric system. The proposed work can offer an accurate and efficient matching compared with other system based on unimodal, bimodal, multimodal characteristics.

No abstract

<p>In this paper, we present a multimodal biometric recognition system that combines fingerprint, fingervein and face images based on cascade advanced and decision level fusion. First, in fingerprint recognition system, the images are enhanced using gabor filter, binarized and passed to thinning method. Then, the minutiae points are extracted to identify that an individual is genuine or impostor. In fingervein recognition system, image processing is required using Linear Regression Line, Canny and local histogram equalization technique to improve better the quality of images. Next, the features are obtained using Histogram of Oriented Gradient (HOG). Moreover, the Convolutional Neural Networks (CNN) and the Local Binary Pattern (LBP) are applied to detect and extract the features of the face images, respectively. In addition, we proposed three different modes in our work. At the first, the person is identified when the recognition system of one single biometric modality is matched. At the second, the fusion is achieved at cascade decision level method based on AND rule when the recognition system of both biometric traits is validated. At the last mode, the fusion is accomplished at decision level method based on AND rule using three types of biometric. The simulation results have demonstrated that the proposed fusion algorithm increases the accuracy to 99,43% than the other system based on unimodal or bimodal characteristics.</p>

In the last decade, the biometrics refers to automatic recognition of persons using their physiological or behavioral characteristics. The combination of multiple biometrics or, multimodal biometrics have higher accuracy to verify the person and ensure that its information or data is safer compared to system based on single biometrics modality. In this regard, this paper introduces a scheme for multimodal biometric recognition system based on the fusion of finger-vein and face images using Convolutional Neural Network (CNN) and different classifiers. The pre-processed finger-vein image using Adaptive Histogram Equalization (AHE) is input into a CNN model. Then, Random Forest (RF) classifier performs as a recognizer. In addition, a hybrid CNN-Linear Support Vector Machine (SVM) model is used for recognizing face images. After this process, the score level fusion of bimodal biometric based on the weighted concatenation is applied to identify the identity of the individual. Experimental results on publicly available VERA Fingervein database, Color Feret and Ar face database have shown significant capability of identification biometric system. The proposed system provides high recognition accuracy rate by 99,98% compared with other classical methods and traditional techniques based on normal recognition or CNN architectures.