• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.2
• /
• pp.130-135
• /
• 2016

Gait recognition has advantage of non-contact type recognition. But It has disadvantage of low recognition rate when the pedestrian silhouette is changed due to bag or coat. In this paper, we proposed new method using combination of gait energy image feature and thermal face image feature. First, we extracted a face image which has optimal focusing value using human body rate and Tenengrad algorithm. Second step, we extracted features from gait energy image and thermal face image using linear discriminant analysis. Third, calculate euclidean distance between train data and test data, and optimize weights using genetic algorithm. Finally, we compute classification using nearest neighbor classification algorithm. So the proposed method shows a better result than the conventional method.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.935-938
• /
• 1998

In this paper, we propose a new auto focus algorithm using variance which estimate spread characteristic of image. In the proposed algorithm, the focus value is calculated via variance of difference between two adjacent pixels. This algorithm, we propose, show much more sharp focus curve than any other algorithms. It is shown experimentally that the proposed auto focus algorithm can be a efficient alternative to existing Tenengrad-based auto focusing algorithms.

• Journal of the Optical Society of Korea
• /
• v.15 no.3
• /
• pp.252-263
• /
• 2011

In this work, for the first time, the quality of restoration in wide-field microscopy images after deconvolution was analyzed as a function of different Point Spread Functions using one deconvolution method, on a specimen of known size and on a biological specimen. The empirical Point Spread Function determination can significantly depend on the numerical aperture, refractive index of the embedding medium, refractive index of the immersion oil and cover slip thickness. The influence of all of these factors is shown in the same article and using the same microscope. We have found that the best deconvolution results are obtained when the empirical PSF utilized is obtained under the same conditions as the specimen. We also demonstrated that it is very important to quantitatively check the process' outcome using several quality indicators: Full-Width at Half-Maximum, Contrast-to-Noise Ratio, Signal-to-Noise Ratio and a Tenengrad-based function. We detected a significant improvement when using an indicator to measure the focus of the whole stack. Therefore, to qualitatively determinate the best deconvolved image between different conditions, one approach that we are pursuing is to use Tenengrad-based function indicators in images obtained using a wide-field microscope.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.26-31
• /
• 2018

In this paper, surface defects and typical illumination mechanisms for steel plates are analyzed, and then optimum illumination mechanism is selected using discrete wavelet transform (DWT) synthetic images and discriminant measure (DM). The DWT synthetic images are generated using component images decomposed by Haar wavelet transform filter. The best synthetic image according to surface defects is determined using signal to noise ratio (SNR). The optimum illumination mechanism is selected by applying discriminant measure (DM) to the best synthetic images. The DM is applied using the tenengrad-euclidian function. The DM is evaluated as the degree of contrast using the defect boundary information. The performance of the optimum illumination mechanism is verified by quantitative data and intuitive image looks.