Search

Signature is a biometrics trait widely used for personal verification in financial and most other organizations where financial and relevant types of transactions are done manually with signed authorized papers. A signature verification system aims to verify the minor structural differences between genuine and forged signatures, as most skilled forgery signatures look similar to their respective genuine signatures with specific deformations. Signature verification in a multi-cultural country like India is challenging in both writer-independent and script-independent scenarios where the Indian population uses multiple scripts to write their signatures. This paper reports a writer-independent offline signature verification system that uses Convolutional Neural Network (CNN) architecture for feature extraction and classification. The objective of the proposed work is to model a CNN-based adaptable system to verify multi-scripted offline signatures. The model has been trained and tested on two publicly available databases, viz. CEDAR and BH-Sig260, which consist of Hindi, Bengali, and English signatures. Individual signature classes of unique scripts and a combination of these scripts have been considered for testing the proposed model that determines verification accuracies of 90%, 95%, 98.33%, and 93.33%, respectively. Experimental results are compelling, and the proposed model outperforms the verification accuracies of some well-known models. [ABSTRACT FROM AUTHOR]

Low resolution (LR) and very low resolution (VLR) face images captured by surveillance cameras make automatic face recognition (AFR) a challenging task. The performance of an automatic face recognition system (AFRS) degrades when these types of face images are compared with high resolution (HR) gallery images. This paper has presented a face identification system called Cross-Resolution Face Identification System, to address this issue. It makes use of the Deep Convolutional Neural Network (DCNN) having different pooling operations to extract resolution robust features from high resolution, low resolution and very low resolution face images. The proposed system is evaluated on four face databases, namely, the ORL, the extended Yale face B, the LFW, and the Georgia Tech under three cross resolution environmental conditions based on resolution of probe images (i.e., high resolution to high resolution, low resolution to high resolution, and very low resolution to high resolution).The experimental outcomes exhibit the effectiveness of the proposed face identification system. [ABSTRACT FROM AUTHOR]

Electrohydrodynamic (EHD) inkjet is one of the non-contact jet based promising technology to fabricate high-resolution features of functional materials with higher efficiency. Uniformity of the deposited droplets is one of the key demands of the EHD inkjet system for printing micro-features in microsensors, printed flexible electronics or various MEMS devices. In this study, a new methodology has been proposed to model the uniformity grade of the deposited droplets. In this present work, a significant improvement in the printing quality has been achieved with the help of some modern optimization methods coupled with some traditional statistical methods. Instead of a single fixed solution (may or may not be feasible), the proposed methodology suggests a feasible region with a large set of solutions. It extends the operators' flexibility to choose from a wide range of input parameters which yield droplet depositions with higher uniformity. The proposed methodology is further evaluated with some experimental runs to fabricate discrete dots and continuous line patterns. This method is considered to be a promising and effective alternative offline approach to increase the uniformity of the droplets. [ABSTRACT FROM AUTHOR]

Nature-inspired heuristic and/or metaheuristic algorithms have been used for solving complex real-world problems in recent years. Electrohydrodynamic (EHD) inkjet printing is a microadditive manufacturing process in which high-resolution jets of polarizable functional materials were deposited on the defined spot of a substrate at the appointed time. The quality of the printed features is derived by the complex physics of the system. Parameter modeling of this process was carried out by using regression analysis, a feed-forward neural network trained with backpropagation (BPNN) and a neural network trained with a genetic algorithm (GA-NN) separately. This study emphasizes the droplet diameter prediction of an EHD inkjet printing system and explores the applicability of the soft computing-based methods for this new emerging technology. Soft computing-based approaches have been developed for the first time in this area to model the EHD inkjet process. Five hundred data were produced through the conventional regression analysis to train the neural network-based models. Output droplet diameter was predicted for different combinations of input parameters such as standoff height (SH), applied voltage (AV) and ink flow rate (FR) using the above three approaches, and their performances were analyzed through some randomly created real experimental test cases. All three models gave good prediction accuracy with less than 10% error in the prediction of the droplet diameter. Furthermore, it had been observed that the performance of GA-NN surpasses both the regression- and BPNN-based approaches in most of the test cases. It achieved quite satisfactory average absolute percentage deviation value of 2.51% between the target and predicted output using GA-NN model, which also showed an improvement over the regression or BPNN model. [ABSTRACT FROM AUTHOR]

Face recognition is itself a very challenging task and it becomes more challenging when the input images have intra class variations and inter class similarities in a large scale. Yet the recognition accuracy can be improved in some extent by supporting the system with non-matched templates. Therefore a set of cohort images is used in this regard. But all the cohort templates of the initial cohort pool may not be relevant for each and every enrolled subject. So the main focus of this work is to select a subject specific and meaningful cohort subset. This paper proposes a cohort selection method called K-medoids Cohort Selection (KMCS) to select a reference set of non-matched templates which are almost appropriate to the respective subjects. Basically, all cohort scores of a subject are clustered first using K-medoids clustering. Afterward the cluster having more scattered members/scores from its medoid is selected as a cohort subset because this cluster is constituted with the cohorts carrying more discriminative features compared to others. The SIFT points and SURF points are extracted as facial feature. The experiments are conducted on FEI, ORL and Look-alike databases of face images. The matching scores between probe and query images are normalized using T-norm, Max-Min and Aggarwal (Max rule) cohort score normalization techniques before taking the final decision of acceptance or rejection. The results obtained from the experiments show the domination of the proposed system over the non-cohort face recognition system as well as random and Top 10 cohort selection methods. There is another comparative study between k-means and K-medoids clustering for cohort selection. [ABSTRACT FROM AUTHOR]

Cohort selection benefits a biometric system by providing the information collected from non-match templates, whereas fusion benefits a system by combining information collected from different sources or from same source in different ways. The benefits of both approaches are availed here by proposing a cohort selection technique which is exploited prior to fusion and after fusion of matching scores for a face recognition system. Two robust facial features, viz. scale-invariant feature transform and speeded up robust features, are used here. This study presents a novel way of fusion based on cohort selection unlike the traditional levels of fusion (i.e., sensor, feature, match score, rank and decision level fusions). Cohort-based fusion is performed in two different fashions—pre-cohort fusion and post-cohort fusion. In case of early fusion, fusion rules like sum, max, min and average rules are applied before cohort selection to be performed. In contrast, the cohort selection is followed by the fusion in post (or late)-cohort fusion. Union operation is applied as late fusion rule. The matching scores are normalized by T-norm cohort score normalization technique prior to be compared with the threshold value to govern the decision of acceptance by the system. The experiments are carried out on FEI and the Look-alike (IIIT Delhi) face databases. The outcomes of the proposed method are looked to be encouraging and much convincing over non-cohort systems and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In a general scenario, while attending a scene containing multiple faces or looking towards a group photograph, our attention does not go equal towards all the faces. It means, we are naturally biased towards some faces. This biasness happens due to availability of dominant perceptual features in those faces. In visual saliency terminology it can be called as 'salient face'. Human's focus their gaze towards a face which carries the 'dominating look' in the crowd. This happens due to comparative saliency of the faces. Saliency of a face is determined by its feature dissimilarity with the surrounding faces. In this context there is a big role of human psychology and its cognitive science too. Therefore, enormous researches have been carried out towards modeling the computer vision system like human's vision. This paper proposed a graphical based bottom up approach to point up the salient face in the crowd or in an image having multiple faces. In this novel method, visual saliencies of faces have been calculated based on the intensity values, facial areas and their relative spatial distances. Experiment has been conducted on gray scale images. In order to verify this experiment, three level of validation has been done. In the first level, our results have been verified with the prepared ground truth. In the second level, intensity scores of proposed saliency maps have been cross verified with the saliency score. In the third level, saliency map is validated with some standard parameters. The results are found to be interesting and in some aspects saliency predictions are like human vision system. The evaluation made with the proposed approach shows moderately boost up results and hence, this idea can be useful in the future modeling of intelligent vision (robot vision) system. [ABSTRACT FROM AUTHOR]

Faces are highly challenging and dynamic objects that are employed as biometrics evidence in identity verification. Recently, biometrics systems have proven to be an essential security tools, in which bulk matching of enrolled people and watch lists is performed every day. To facilitate this process, organizations with large computing facilities need to maintain these facilities. To minimize the burden of maintaining these costly facilities for enrollment and recognition, multinational companies can transfer this responsibility to third-party vendors who can maintain cloud computing infrastructures for recognition. In this paper, we showcase cloud computing-enabled face recognition, which utilizes PCA-characterized face instances and reduces the number of invariant SIFT points that are extracted from each face. To achieve high interclass and low intraclass variances, a set of six PCA-characterized face instances is computed on columns of each face image by varying the number of principal components. Extracted SIFT keypoints are fused using sum and max fusion rules. A novel cohort selection technique is applied to increase the total performance. The proposed protomodel is tested on BioID and FEI face databases, and the efficacy of the system is proven based on the obtained results. We also compare the proposed method with other well-known methods. [ABSTRACT FROM AUTHOR]

Electrohydrodynamic (EHD) inkjet is a modern non-contact printing approach, which uses a direct writing technology of functional materials to achieve micro/nanoscale of printing resolution. As an alternative to conventional inkjet technology, the goal of the EHD inkjet printing is to generate uniformly minimized droplets on a substrate. In this study, the effects of applied voltage, standoff height and ink flow rate on droplet diameter formation in EHD inkjet printing process were analysed using Taguchi methodology and regression analysis. Several experiments were carried out using an L27 (313) orthogonal array. Based on signal to noise (S/N) ratio and mean response, optimal droplet diameter was achieved. The analysis of variance (ANOVA) was used to find the significance and percentage of contribution of each input parameter along with their interaction on the output droplet diameter. Analysis of the results revealed that the ink flow rate was the dominant factor that affected the droplet diameter mostly. The effect of the applied voltage is significant until regular ejection starts. It helps reduce droplet diameter more than five times compared with its initial droplet diameter in the absence of the electric field. A confirmation test was carried out with a 90% confidence level to illustrate the effectiveness of the Taguchi optimization method. Both linear and quadratic regression analysis were applied to predict the output droplet diameter. The predicted result from the model and actual test results are very close to each other, justifying the significance of the models. [ABSTRACT FROM AUTHOR]