Yogesh Kumar - Academia.edu (original) (raw)

Papers by Yogesh Kumar

International Journal of Biometrics, 2020

The problem of automatic facial expression recognition is both interesting and challenging with a... more The problem of automatic facial expression recognition is both interesting and challenging with a strong impact on many application areas such as animation and human-computer interaction. The field has shown tremendous growth over the past years with its benchmarking efforts and progress. In this paper, an automated system to recognise facial expressions using the deep convolutional neural network is presented. The proposed system has used the appearance based features to recognise the facial expressions from imagery data with pose variations. The appearance based features are extracted by implementing an integrated approach of Gabor filter with local binary pattern method and the selection process of extracted features is executed using the concept of principal component analysis (PCA). The proposed system performance is accessed using the evaluation metrics of precision, recall, f-measure, and recognition rate for the frontal and half side pose images of the JAFFE and KDEF datasets.

The Journal of Chemical Physics, 1997

A theoretical model for electron-impact total ionization cross sections, which has been found to ... more A theoretical model for electron-impact total ionization cross sections, which has been found to be reliable for a wide range of molecules, is applied to molecules of interest to atmospheric science. The new theory, the binary-encounter-Bethe ͑BEB͒ model, combines the binary-encounter theory and the Bethe theory for electron-impact ionization, and uses simple theoretical data for the ground state of the target molecule, which are readily available from molecular structure codes. Total ionization cross sections of 11 molecules, CS, CS 2 , COS, CH 4 , H 2 S, NH 3 , NO 2 , N 2 O, O 3 , S 2 , and SO 2 , are presented for incident electron energies from threshold to 1 keV with an average accuracy of 15% or better at the cross section peak. We also found that the use of vertical ionization potentials ͑IPs͒ rather than adiabatic IPs for the lowest IPs significantly improves BEB cross sections between the threshold and cross section peak for molecules whose adiabatic and vertical IPs are different by ϳ1 eV or more ͑CH 4 and NH 3). The BEB cross sections are presented in a compact analytic form with a small number of constants, making the cross sections suitable for modeling applications.

International Journal of Biometrics, 2020

The problem of automatic facial expression recognition is both interesting and challenging with a... more The problem of automatic facial expression recognition is both interesting and challenging with a strong impact on many application areas such as animation and human-computer interaction. The field has shown tremendous growth over the past years with its benchmarking efforts and progress. In this paper, an automated system to recognise facial expressions using the deep convolutional neural network is presented. The proposed system has used the appearance based features to recognise the facial expressions from imagery data with pose variations. The appearance based features are extracted by implementing an integrated approach of Gabor filter with local binary pattern method and the selection process of extracted features is executed using the concept of principal component analysis (PCA). The proposed system performance is accessed using the evaluation metrics of precision, recall, f-measure, and recognition rate for the frontal and half side pose images of the JAFFE and KDEF datasets.

The Journal of Chemical Physics, 1997

A theoretical model for electron-impact total ionization cross sections, which has been found to ... more A theoretical model for electron-impact total ionization cross sections, which has been found to be reliable for a wide range of molecules, is applied to molecules of interest to atmospheric science. The new theory, the binary-encounter-Bethe ͑BEB͒ model, combines the binary-encounter theory and the Bethe theory for electron-impact ionization, and uses simple theoretical data for the ground state of the target molecule, which are readily available from molecular structure codes. Total ionization cross sections of 11 molecules, CS, CS 2 , COS, CH 4 , H 2 S, NH 3 , NO 2 , N 2 O, O 3 , S 2 , and SO 2 , are presented for incident electron energies from threshold to 1 keV with an average accuracy of 15% or better at the cross section peak. We also found that the use of vertical ionization potentials ͑IPs͒ rather than adiabatic IPs for the lowest IPs significantly improves BEB cross sections between the threshold and cross section peak for molecules whose adiabatic and vertical IPs are different by ϳ1 eV or more ͑CH 4 and NH 3). The BEB cross sections are presented in a compact analytic form with a small number of constants, making the cross sections suitable for modeling applications.