For representation based image classification methods, it is very important to well represent the target image. As pixels at same positions of training samples and test samples of an object usually have different inte...For representation based image classification methods, it is very important to well represent the target image. As pixels at same positions of training samples and test samples of an object usually have different intensities, it brings difficulty in correctly classifying the object. In this paper, we proposed a novel method to reduce the effects of this issue for image classification. Our method first produces a new representation （i.e. virtual image） of original image, which can enhance the importance of moderate pixel intensities and reduce the effects of larger or smaller pixel intensities. Then virtual images and corresponding original images are respectively used to represent a test sample and obtain two rep- resentation results. Finally, this method fuses these two results to classify the test sample. The integration of original image and its virtual image is able to improve the accuracy of image classification. The experiments of image classification show that the proposed method can obtain a higher accuracy than the conventional classification methods.展开更多
A simple and effective approach is proposed to minimize the effect of unmodulated light and uneven intensity caused by the pixelated structure of the spatial light modulator in a holographic display. A more uniform im...A simple and effective approach is proposed to minimize the effect of unmodulated light and uneven intensity caused by the pixelated structure of the spatial light modulator in a holographic display. A more uniform image is produced by purposely shifting the holographic images of multiple reconstructed lights with different incident angles from the zero-diffraction-order and overlapping those selected different orders. The simulation and optical experimental results show that the influence of the zero-diffraction-order can be reduced, while keeping the good uniformity of the target images by this new approach.展开更多
文摘For representation based image classification methods, it is very important to well represent the target image. As pixels at same positions of training samples and test samples of an object usually have different intensities, it brings difficulty in correctly classifying the object. In this paper, we proposed a novel method to reduce the effects of this issue for image classification. Our method first produces a new representation （i.e. virtual image） of original image, which can enhance the importance of moderate pixel intensities and reduce the effects of larger or smaller pixel intensities. Then virtual images and corresponding original images are respectively used to represent a test sample and obtain two rep- resentation results. Finally, this method fuses these two results to classify the test sample. The integration of original image and its virtual image is able to improve the accuracy of image classification. The experiments of image classification show that the proposed method can obtain a higher accuracy than the conventional classification methods.
基金supported by the UK Engineering and Physical Sciences Research Council(EPSRC) for the support through the EPSRC Centre for Innovative Manufacturing in Ultra Precision(EP/I033491/1)
文摘A simple and effective approach is proposed to minimize the effect of unmodulated light and uneven intensity caused by the pixelated structure of the spatial light modulator in a holographic display. A more uniform image is produced by purposely shifting the holographic images of multiple reconstructed lights with different incident angles from the zero-diffraction-order and overlapping those selected different orders. The simulation and optical experimental results show that the influence of the zero-diffraction-order can be reduced, while keeping the good uniformity of the target images by this new approach.
