In this paper, we conduct research on the natural image classification and segmentation algorithm based on GPU and neural network. The application of image segmentation is very broad, almost appeared in all areas rela...In this paper, we conduct research on the natural image classification and segmentation algorithm based on GPU and neural network. The application of image segmentation is very broad, almost appeared in all areas related to image processing, and involved in various types. With the fast development of computing technology and integrated circuit technology, the renewal speed of graphics hardware. Our method combines the GPU with network to optimize the traditional image segmentation and classification methods which will be meaningful. In the future, we will focus our attention on the hardware deployment of the GPU to modify the current approach.展开更多
Integral imaging is a 3D display technology without any additional equipment. A new system is proposed in this paper, which uses a lenticular lens array to replace the lens array in the conventional integral imaging s...Integral imaging is a 3D display technology without any additional equipment. A new system is proposed in this paper, which uses a lenticular lens array to replace the lens array in the conventional integral imaging system. The lenticular integral imaging system reduces the complexity and the price of integral imaging system. The positive characteristics of conventional integral imaging system, such as full parallax and quasi-continuous view points, are still kept on the proposed system in horizontal direction. Optical results show that the time for calculating the elemental images is reduced by 25% compared with the conventional one. The resolution of integrated image in vertical direction is 4 times higher than that of conventional system. This proposed system opens a new way on application of integral imaging.展开更多
文摘In this paper, we conduct research on the natural image classification and segmentation algorithm based on GPU and neural network. The application of image segmentation is very broad, almost appeared in all areas related to image processing, and involved in various types. With the fast development of computing technology and integrated circuit technology, the renewal speed of graphics hardware. Our method combines the GPU with network to optimize the traditional image segmentation and classification methods which will be meaningful. In the future, we will focus our attention on the hardware deployment of the GPU to modify the current approach.
基金supported by the National Natural Science Foundation of China(No.11474169)
文摘Integral imaging is a 3D display technology without any additional equipment. A new system is proposed in this paper, which uses a lenticular lens array to replace the lens array in the conventional integral imaging system. The lenticular integral imaging system reduces the complexity and the price of integral imaging system. The positive characteristics of conventional integral imaging system, such as full parallax and quasi-continuous view points, are still kept on the proposed system in horizontal direction. Optical results show that the time for calculating the elemental images is reduced by 25% compared with the conventional one. The resolution of integrated image in vertical direction is 4 times higher than that of conventional system. This proposed system opens a new way on application of integral imaging.
