A portable video-rate confocal laser scanning microscope (CLSM) is implemented with polygon mirror and
galvanometric mirror employed as the fast and slow axis scanner, respectively. The system can be applied for
noninvasively imaging skin and other tissue. The dimension of this real-time CLSM is only 33×20×12cm<sup>3</sup> with weigh of
1.780 kg. Here we used a single Complex Programmable Logic Device (CPLD) to generate the control and
synchronization signals for real time confocal microscopy. Utilizing NI image acquisition card, the CLSM system can
acquire and store the real-time images. So that high resolution confocal microscopy is achieved simultaneously.
Natural scene classification is a challenging open problem in computer vision. We present a novel spatial pyramid representation scheme for recognizing scene category. Initially, each image is partitioned into sub-blocks, applying the technology of superpixel lattices segmentation according to a boosted edge learning boundary map, which makes the objects in each sub-block have the integrity-that is, the features in each sub-block are relatively consistent. Then, we extract the dense scale-invariant feature transform features of the images and form the contextual visual feature description. Finally, the image representations are performed by following the methodology of spatial pyramid. The feature descriptions we present include both local structural information and global spatial structural information; therefore, they are more discriminative for scene classification. Experiments demonstrate that the classification rate can achieve about 87.13% on a set of 15 categories of complex scenes.
Matching points between two or multiple images of a scene is a vital component in many computer vision and pattern recognition tasks. The key step of point matching is how to construct a distinctive and robust descriptor. A state-of-the-art scale-invariant feature transform (SIFT) descriptor has proven that it outperforms other local descriptors on the distinctiveness and robustness. However, the SIFT descriptor neglects the global context of the feature points, as thus it fails to resolve the ambiguities that occur in local similar regions in an image. In this paper, a spatial distribution (SD) descriptor is constructed for each feature point detected by the SIFT method. It uses a log-polar histogram to build the global component according to the difference-of-Gaussian convolution image information. The spatial distribution descriptor has rotation, zoom invariance and partial skewness invariance due to that it integrates the local and global information of feature points. Points matching are performed on various images by the proposed framework. Experimental results show that the SD method outperforms the method using only SIFT.
Recently, a category of watermarking techniques based on binary phase-only filter (BPOF) has been proposed for image authentication. In such techniques, the authentication is implemented by evaluating the correlation between Fourier phase information and the hidden watermark bitplane. In this paper, we reveal the security flaws of BPOF-based watermarking algorithms and propose sophisticated tampering attacks against them. We show how the attacker can easily tamper with a watermarked image without being detected. Experimental results demonstrate that our attacks are successful in tampering watermarked images. The watermarking schemes are proven to be fundamentally flawed.
In traditional fractal image coding schemes, domain blocks are constrained to be twice as large as range blocks in order to ensure the convergence of the iterative decoding stage. However, this constraint has limited the fractal encoder to exploit the self-similarity of the original image. In order to overcome the shortcoming, a novel scheme using same sized range and domain blocks is proposed in the letter. Experimental results show the remarkable improvement in compression ratio and image quality.