Recently, object recognition is improved accuracy by Convolutional Neural Network(CNN) and growing object recognition demand for automatic driving system and security and so on. However, one of the problem of object recognition is to extract object region which have various size, scale and form. This paper propose moving object proposal for object recognition. Using region grouping and scoring with optical flow, we can propose object proposal for moving objects. The object proposal experiments show effective results compared with previous method on the UCF crowd dataset.
In this paper, we present a proposal of material discrimination method based on the spectral reflectance properties in the near-infrered (NIR) wavelength range and informative wavelengths selection to discriminate multiple target materials such as the human skin, plant and asphalt. A material is detected from its image by using only two or three wavelengths corresponding to the absorption wavelength and the other wavelength based on the spectral reflectance property of the material. However discrimination between more than two materials are not always made by using only absorption wavelengths of each material. Even if the materials were discriminated, whether or not the wavelength was informative is not known. Here we discriminated three material regions by using multiple NIR wavelengths. In this proposed method, binary classifiers are generated from each material by Partial Least Squares (PLS) regression analysis, and three materials are discriminated by predicted values obtained by the classifiers. Also, the informative wavelengths are selected by Variable Influence Projection (VIP) obtained by PLS regression analysis. As a result of the experiment, three materials were discriminated with high accuracy by using only five wavelengths.
This paper focuses on the thermal cleavage of a laminated wafer on which the borosilicate glass substrate is bonded on the silicon wafer. The semiconductor laser beam with an elliptical shape is applied to generate the thermal distribution inside the laminated wafer. The carbon dioxide laser is also used to improve the cleavage quality at the final edge of laminated wafer. The crack propagation during laser beam irradiation is observed by acoustic emission sensor, and the influence of physical and thermal property in each material on the crack propagation is evaluated. As results, the crack propagation in laminated wafer was achieved by the absorption to the silicon of semiconductor laser and the thermal conduction to the borosilicate glass by the generated heat inside the silicon. At the start edge in laminated wafer, the crack propagated only inside the silicon due to the difference of the absorption coefficient and the thermal properties in silicon and borosilicate glass. At the final edge in laminated wafer, the cleavage characteristic was improved by applying the CO2 laser beam for the purpose of adding the input energy to the borosilicate glass.
Chemical mechanical polishing (CMP) is used in a wide range of processes in semiconductor production; however, the polishing mechanism of CMP is not yet completely understood. One reason that aggravates satisfactory understanding is that the polishing action in the fine gap between the semiconductor wafer and polishing pad cannot be directly observed. The behavior of the abrasive particles and chemical species in the slurry is believed to play a critical role in the polishing mechanism. Although the macroscale slurry flow has been studied by many researchers, the microscale slurry flow in the fine gap, especially in polishing pad asperities, has been largely unstudied. In this study, therefore, we attempted to visualize the slurry flow taking place in the asperities experimentally. Because the in-situ observation of the slurry flow is extremely difficult, a larger model of the pad asperities was built, based on the scaling laws of fluid dynamics. A refractive index matching technique and particle suspension method were applied in order to visualize the scaled-up slurry flow. As a result, the flows toward and away from the wafer surface have also been observed as suggested by previous studies.
The present paper describes load capacity evaluations of PA66 gears which were performed against gear running test results on the basis of JIS B 1759. Unreinforced PA66 was evaluated to have a permissible bending strength of 44.9 MPa. This value could be valid, so that JIS B 1759 would be suitable for evaluations of PA66 gears. However, PA66 has a large friction coefficient on PA66, and PA66 gear pairs showed severe wear. As a result, their failure modes did not a tooth breakage, so that a mating gear factor of PA66 on PA66 cannot be determined. Meanwhile, failure modes of glass-fiber-reinforced PA66 gear pairs were tooth breakage, so that their running test results were evaluated on the basis of JIS B 1759. However, their permissible bending strength was evaluated to be much smaller than the bending strength published by material manufactures. This is because fiber orientations in test gears could not be effective in enhancing their load capacity although those in test pieces for bending tests must be appropriate for the tests. In addition, accuracy of plastic gears could slightly affect their load capacity, so that restrictions on test gear accuracy may be eased. Furthermore, a regulation on a variation in an applied torque to a test gear should be revised, because it would be impossible to follow it exactly.