An unsupervised hyperspectral hierarchical representation (HHR) framework is proposed by estimating density peak index (DPI). To accelerate our proposed algorithm, we first aggregate adjacent homogenous pixels into extended-pixels as basic initial units. Next, to rank the importance of initial units, both local density and interunit distance of each extended-pixel are taken into account to calculate the DPI. Then, a local–global merging procedure is conducted to construct the hierarchical structure. Selecting the extended-pixels with high DPI values as centers, the related adjacent extended-pixels are merged into local-regions. To generate final HHR, the local-regions are grouped globally based on their updated DPI rank. Considering the representative property of HHR, we also explore a hyperspectral classification strategy. Different from traditional segmentation-based classification methods, our classification scheme only focuses on the classification of the representative subregions, then the labels of other subregions directly refer to the results of representative subregions in the same HHR group. Thus, the computational load for classification can be significantly decreased than for pixel-wise classification. The experiments on three hyperspectral subsets show that the proposed HHR framework can yield remarkable performance in unsupervised clustering, and the classification scheme can obtain equivalent classification accuracy with distinctly limited calculation.
In the field of image processing, it has been a challenging task to obtain a complete foreground that is not uniform in color or texture. Unlike other methods, which segment the image by only using low-level features, we present a segmentation framework, in which high-level visual features, such as semantic information, are used. First, the initial semantic labels were obtained by using the nonparametric method. Then, a subset of the training images, with a similar foreground to the input image, was selected. Consequently, the semantic labels could be further refined according to the subset. Finally, the input image was segmented by integrating the object affinity and refined semantic labels. State-of-the-art performance was achieved in experiments with the challenging MSRC 21 dataset.
Traditional laser scanning microscopes require complex control systems to synchronize and control image acquisition. The control system is especially cumbersome in the multimodal laser scanning microscope. We have developed a novel multimodal laser scanning microscope control system based on a National Instruments multifunction data acquisition device (DAQ), which serves as both a data acquisition device and a programmable signal generator. The novel control system is low-cost and easy-to-build, with all components off-the-shelf. We have applied the control system in a multimodal laser scanning microscope. The control system has not only significantly decreased the complexity of the microscope, but also increased the system flexibility. We have demonstrated that the system can be easily customized for various applications.
Melanin is regarded as the most enigmatic pigments/biopolymers found in most organisms. We have shown previously that melanin goes through a step-wise multi-photon absorption process after the fluorescence has been activated with high laser intensity. No melanin step-wise multi-photon activation fluorescence (SMPAF) can be obtained without the activation process. The step-wise multi-photon activation fluorescence has been observed to require less laser power than what would be expected from a non–linear optical process. In this paper, we examined the power dependence of the activation process of melanin SMPAF at 830nm and 920nm wavelengths. We have conducted research using varying the laser power to activate the melanin in a point-scanning mode for multi-photon microscopy. We recorded the fluorescence signals and position. A sequence of experiments indicates the relationship of activation to power, energy and time so that we can optimize the power level. Also we explored regional analysis of melanin to study the spatial relationship in SMPAF and define three types of regions which exhibit differences in the activation process.