• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1721-1737
• /
• 2020

Human apparent age estimation has become a popular research topic and attracted great attention in recent years due to its wide applications, such as personal security and law enforcement. To achieve the goal of age estimation, a large number of methods have been pro-posed, where the models derived through the cumulative attribute coding achieve promised performance by preserving the neighbor-similarity of ages. However, these methods afore-mentioned ignore the geometric structure of extracted facial features. Indeed, the geometric structure of data greatly affects the accuracy of prediction. To this end, we propose an age estimation algorithm through joint feature selection and manifold learning paradigms, so-called Feature-selected and Geometry-preserved Least Square Regression (FGLSR). Based on this, our proposed method, compared with the others, not only preserves the geometry structures within facial representations, but also selects the discriminative features. Moreover, a deep learning extension based FGLSR is proposed later, namely Feature selected and Geometry preserved Neural Network (FGNN). Finally, related experiments are conducted on Morph2 and FG-Net datasets for FGLSR and on Morph2 datasets for FGNN. Experimental results testify our method achieve the best performances.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.141-150
• /
• 2011

Precise image-to-image registration is required to process multi-sensor data together. The purpose of this paper is to develop an algorithm that register between high-resolution optical and SAR images using linear features. As a pre-processing step, initial alignment was fulfilled using manually selected tie points to remove any dislocations caused by scale difference, rotation, and translation of images. Canny edge operator was applied to both images to extract linear features. These features were used to design a cost function that finds matching points based on their similarity. Outliers having larger geometric differences than general matching points were eliminated. The remaining points were used to construct a new transformation model, which was combined the piecewise linear function with the global affine transformation, and applied to increase the accuracy of geometric correction.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.269-277
• /
• 2006

We propose a new expert system for recovering the broken fragments of relics into an original form using computer graphics and image processing. This paper presents a system with an application to tombstones objects of flat plane with letters carved in for assembling the fragments by placing their respective fragments in the right position. The matching process contains three sub-processes: aligning the front and letters of an object, identifying the matching directions, and determining the detailed matching positions. We apply least squares fitting, vector inner product, and geometric and RGB errors to the matching process. It turned out that 2-D translations via fragments-alignment enable us to save the computational load significantly. Based on experimental results from the damaged cultural fragments, the performance of the proposed method is illustrated.

• KSBB Journal
• /
• v.11 no.4
• /
• pp.405-410
• /
• 1996

This paper discussed the dispersion effect according to the geometrical variation of an internal-loop spparatus by the method of pulse injection of a tracer. The Bodenstein number, which is the dimensionless group characterizing the effect of dispersion, was decreased with increasing the superficial gas velocity in the 50L and the 500L apparatus. But, in the 5L apparatus, the Bodenstein number was increased with increasing the superficial gas velocity in the range of 0 to 2cm/sec but above that range the rate of increase was dropped down to give a constant value because of the phenomenon of gas disengagement. The principle of similarity based on dimensional analysis was applied to design a pilot scale internal-loop apparatus. The effect of dispersion was examined in three different internal-loop apparatus to give the following correlation with major geometric and fluid dynamic properties as variables. B0=4.4014ReG0.117 ReL-0.0065(Hr/Dr)0.76(Dd/Dr)-0.76

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.67-75
• /
• 2011

This paper presents a scale and rotation-invariant gait recognition method using R-transform, which is computed by projecting squared coefficients of Radon transform. Since R-transform is invariant to translation, rotation, and scaling, it particularly suitable for extracting object poses without camera calibration. Coefficients of R-transform are used to compute correlation, and the maximum correlation value determines the similarity between two gait images. The proposed method requires neither camera calibration nor geometric compensation, and as a result, it makes robust gait recognition possible without additional compensation for translation, rotation, and scaling.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.3
• /
• pp.183-190
• /
• 2007

To make use of surveying data obtained from different sensors and different techniques, it is a pre-requite step that register them in a common coordinate system. For this purpose, we developed methodologies to register IKONOS-2 Satellite Imagery using LiDAR(Light Detection And Ranging) data. To achieve this, conjugate features from these data should be extracted in advance. In this study, linear features are chosen as conjugate features. Then, to register them, observation equations are established from similarity measurements of the extracted features and the results was evaluated statistically. The results clearly demonstrate that the proposed algorithms are appropriate to register these data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.116-122
• /
• 2010

This paper proposes a method for classifying targets robust to geometric transformations of targets such as rotation, scale change, translation, and pose change. Targets which have rotation, scale change, and shift is firstly classified based on CM(Confidence Map) which is generated by similarity, scale ratio, and range of orientation for SIFT(Scale-Invariant Feature Transform) feature vectors. On the other hand, DB(DataBase) which is acquired in various angles is used to deal with pose variation of targets. Range of the angle is determined by comparing and analyzing the execution time and performance for sampling intervals. We experiment on various images which is geometrically changed to evaluate performance of proposed target classification method. Experimental results show that the proposed algorithm has a good classification performance.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.5
• /
• pp.899-908
• /
• 2022

In this study, a study was conducted to localize a large aluminum turbo fan used for tank powerpack. The turbo fan was scanned with a 3D scanner and then 3D modeling was performed. Computational fluid dynamics (CFD) were performed from the performance conditions of the fan, and structural analysis was performed using the pressure data obtained from CFD. The fan was reduced to 1/5 size by applying the geometric similarity. A 1/5 size fan has a honeycomb structure inserted into the front shroud and back shroud to reduce the weight by 5.3%. A 1/5 size fan was printed using a PBF 3D printer, and a 1/5 size fan with honeycombs was also printed. The pressure drop of 8.67 kPa and the required power of 138.19 kW, which satisfies the performance conditions of the fan, were confirmed from the results of CFD. The values of the maximum deformation amount of 0.000788 mm and the maximum effective stress of 0.241 MPa were confirmed from the structural analysis results. The fan printed by the PBF 3D printer had the same shape as the modeling, and the shape was perfect. There are no defects anywhere in appearance. However, the condition of the outer surface of the fan's back shroud is rough compared to other locations. The fan in which the honeycomb was inserted was also perfectly output, and the shape of the honeycomb was the same as the modeling.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.3
• /
• pp.245-253
• /
• 2011

We investigate the flow characteristics of elementary-flow paths with $90^{\circ}$ bends; a velocity-control trim consists of such paths. For geometric similarity, the width and length of each path are selected, and the number of bends is 0, 4, or 8. The flow tests are conducted with the same flow-path elements. The numerical results are in good agreement with the experimental data. In elements without bends, the volume flow rate decreases with the length of the flow path, with a constant pressure drop between the inlet and the outlet. However, in flow paths with $90^{\circ}$ bends, it increases and then decreases with the length of the flow path. For a fixed number of $90^{\circ}$ bends, better pressure-drop characteristics are observed as the length of the flow path increases. For a fixed flow-path length, a flow-path element with more bends has a smoother pressure drop along the path.

• School Mathematics
• /
• v.9 no.4
• /
• pp.523-533
• /
• 2007

This article focused the meaning of Pythagoras' and Euclid's proof about the Pythagorean theorem in a historical and mathematical perspective. Pythagoras' proof using similarity is based on the arithmetic assumption about commensurability. However, Euclid proved the Pythagorean theorem again only using the concept of dissection-rearrangement that is purely geometric so that it does not need commensurability. Pythagoras' and Euclid's different approaches to geometry have to do with Birkhoff's axiom system and Hilbert's axiom system in the school geometry Birkhoff proposed the new axioms for plane geometry accepting real number that is strictly defined. Thus Birkhoff's metrical approach can be defined as a Pythagorean approach that developed geometry based on number. On the other hand, Hilbert succeeded Euclid who had pursued pure geometry that did not depend on number. The difference between the proof using similarity and dissection-rearrangement is related to the unsolved problem in the geometry curriculum that is conflict of Euclid's conventional synthetical approach and modern mathematical approach to geometry.