http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Estimating Normalized Attention of Viewers on Account of Relative Visual Saliency of Faces (NRVS)
Ravi kant kumar,Jogendra Garain,Goutam Sanyal,Dakshina Ranjan Kisku 보안공학연구지원센터 2015 International Journal of Software Engineering and Vol.9 No.7
Humans psychological and behavioral understanding often lead to make natural decision which accurately identifies and remembers the faces which are highly appreciated or criticized by themselves in comparing to the normal viewed faces, in terms of beauty, ugliness or unique appearance. It happens due to human psychology of being biased towards the salient face in the process of face recognition and identification. This paper attempts a novel method to measure, how our attention is more restricted towards some particular faces in the crowd. This restricted attention is strongly guided by the relative visual saliency of these faces. In this paper, normalized relative visual saliency (NVRS) of the faces is evaluated using their intensity values modulated with respective spatial distance. Experiment has been carried out on test image dataset via bottom up approach. The experimental results are found to be encouraging and accuracy has also been measured exhibiting efficacy of the proposed approach.
Jogendra Garain,Ravi Kant Kumar,Goutam Sanyal,Dakshina Ranjan Kisku 보안공학연구지원센터 2015 International Journal of Security and Its Applicat Vol.9 No.6
Selection of cohort models plays a vital role to increase the accuracy of a biometric authentication system as well as to reduce the computational cost. This paper proposes a novel approach for cohort selection called Max-Min-Centroid-Cluster (MMCC) method. The clusters of cohorts are generated by K-means clustering technique. The union of the clusters having largest and smallest centroid value is taken as cohort subset. The cohort scores, after normalization using different cohort based score normalization techniques, are used in authentication process of the system. Evaluation has been carried out on FEI face datasets. The performance of this novel methodology is analyzed using T-norm and Aggarwal (max rule) normalization techniques. Experimental results exhibit the efficacy of the proposed method.
Amit Kumar Ball,Shibendu Shekhar Roy,Dakshina Ranjan Kisku,Naresh Chandra Murmu 한국정밀공학회 2020 International Journal of Precision Engineering and Vol.21 No.3
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.