• Journal of Multimedia Information System
• /
• v.6 no.2
• /
• pp.91-98
• /
• 2019

Many researchers have attempted to recognize three-dimensional faces using feature points extracted from two-dimensional facial photographs. However, due to the limit of flat photographs, it is very difficult to recognize faces rotated more than 15 degrees from original feature points extracted from the photographs. As such, it is difficult to create an algorithm to recognize faces in multiple angles. In this paper, it is proposed a new algorithm to recognize three-dimensional face recognition based on feature points extracted from a flat photograph. This method divides into six feature point vector zones on the face. Then, the vector value is compressed and expanded according to the rotation angle of the face to recognize the feature points of the face in a three-dimensional form. For this purpose, the average of the compressibility and the expansion rate of the face data of 100 persons by angle and face zone were obtained, and the face angle was estimated by calculating the distance between the middle of the forehead and the tail of the eye. As a result, very improved recognition performance was obtained at 30 degrees of rotated face angle.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.40-48
• /
• 1996

In this paper, a 40 dimensional segment vector with 4 frame and 7 frame width in every monosyllable interval was compressed into a 10, 14, 20 dimensional vector using K-L expansion and neural networks, and these was used to speech recognition feature parameter for CHMM. And we also compared them with CHMM added as feature parameter to the discrete duration time, the regression coefficients and the mixture distribution. In recognition test at 100 monosyllable, recognition rates of CHMM +${\bigtriangleup}$MCEP, CHMM +MIX and CHMM +DD respectively improve 1.4%, 2.36% and 2.78% over 85.19% of CHMM. And those using vector compressed by K-L expansion are less than MCEP + ${\bigtriangleup}$MCEP but those using K-L + MCEP, K-L + ${\bigtriangleup}$MCEP are almost same. Neural networks reflect more the speech dynamic variety than K-L expansion because they use the sigmoid function for the non-linear transform. Recognition rates using vector compressed by neural networks are higher than those using of K-L expansion and other methods.

• Earthquakes and Structures
• /
• v.18 no.4
• /
• pp.437-449
• /
• 2020

It is quite apparent that engineering concerns related to the influence of masonry infills on seismic behavior of reinforced concrete (RC) structures is likely to remain relevant in the long term, as infill walls maintain their functionalities in construction practice. Within this framework, the present paper mainly deals with the issue in terms of modal expansion of effective earthquake forces and the resultant modal responses. An adequate determination of spatial distribution of effective earthquake forces over the height of the building is highly essential for both seismic analysis and design. The possible influence of infill walls is investigated by means of modal analyses of two-, three-, and four-bay RC frames with a number of stories ranging from 3 to 8. Both uniformly and non-uniformly infilled frames are considered in numerical analyses, where infill walls are simulated by adopting the model of equivalent compression strut. Consequently, spatial distribution of effective earthquake forces, modal static base shear force response of frames, modal responses of story shears from external excitation vector and lateral floor displacements are obtained. It is found that, infill walls and their arrangement over the height of the frame structure affect the spatial distribution of modal inertia forces, as well as the considered response quantities. Moreover, the amount of influence varies in stories, but is not very dependent to bay number of frames.