Search

The usage of full-color imaging in digital pathology produces significant results. Compared with a grayscale image or a pseudocolor image containing contrast information, a full-color image can identify and detect the target object better with color texture information. Fourier ptychographic microscopy (FPM) is a high-throughput computational imaging technique that breaks the tradeoff between high resolution (HR) and a large field of view. It also eliminates the artifacts of scanning and stitching in digital pathology and improves its imaging efficiency. However, the conventional full-color digital pathology based on FPM is still time-consuming because of the repeated experiments with tri-wavelengths. A color transfer FPM approach termed "CFPM" was reported. The color texture information of a low-resolution full-color pathologic image is directly transferred to the HR grayscale FPM image captured by only a single wavelength. Both of the color space of FPM based on the standard CIE-XYZ color model and the display based on the standard RGB color space were established. Different FPM colorization schemes were analyzed and compared with 30 biological samples. Three types of evaluation approaches were provided, including the root-mean-square error (RMSE), the difference maps, and the image histogram cosine similarity. The average RMSE values of the conventional method and CFPM compared with the ground truth were 5.3% and 5.7%, respectively. Therefore, the reconstruction time is significantly reduced by 2/3 with the sacrifice of precision of only 0.4%. The CFPM method is also compatible with advanced fast FPM approaches to further reduce computation time. [ABSTRACT FROM AUTHOR]

3D feature descriptors provide essential information to find given models in captured scenes. In practical applications, these scenes often contain clutter. This imposes severe challenges on the 3D object recognition leading to feature mismatches between scenes and models. As such errors are not fully addressed by the existing methods, 3D feature matching still remains a largely unsolved problem. We therefore propose our Histograms of Gaussian Normal Distribution (HGND) for capturing salient feature information on a local reference frame (LRF) that enables us to solve this problem. We define a LRF on each local surface patch by using the eigenvectors of the scatter matrix. Different from the traditional local LRF-based methods, our HGND descriptor is based on the combination of geometrical and spatial information without calculating the distribution of every point and its geometrical information in a local domain. This makes it both simple and efficient. We encode the HGND descriptors in a histogram by the geometrical projected distribution of the normal vectors. These vectors are based on the spatial distribution of the points. We use three public benchmarks, the Bologna, the UWA and the Ca' Foscari Venezia dataset, to evaluate the speed, robustness, and descriptiveness of our approach. Our experiments demonstrate that the HGND is fast and obtains a more reliable matching rate than state-of-the-art approaches in cluttered situations. [ABSTRACT FROM AUTHOR]

Classification is a hot topic in hyperspectral remote sensing community. In the last decades, numerous effort has been concentrate on the classification problem. However, most of the methods accuracy is not high enough due to the fact that they do not extract features in a deep manner. In this paper, a new hyperspectral data classification skeleton based on exponential flexible momentum deep convolution neural network (EFM-CNN) is proposed. First, the fitness of convolution neural network is substantiated by following classical spectral information-based classification. Then, a novel deep architecture is proposed, which is a hybrid of principle component analysis (PCA), improved convolution neural network based on exponential flexible momentum and support vector machine (SVM). Experimental results indicate that the classifier can effectively improve the accuracy with the state-of-the-art algorithms. And compared with homologous parameters momentum updating methods such as adaptive momentum method, standard momentum gradient method and elastic momentum method, on LeNet5 net and multiple neural network, the accuracy obtained of proposed algorithm increases by 2.6% and 6.5% on average respectively. [ABSTRACT FROM AUTHOR]

Copyright of SCIENCE CHINA Information Sciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)