Gender identification of the horsehair crab, Erimacrus isenbeckii (Brandt, 1848), by image recognition with a deep neural network.

Appearance-based gender identification of the horsehair crab [Erimacrus isenbeckii (Brandt, 1848)] is important for preventing indiscriminate fishing of female crabs. Although their gender is easily identified by visual observation of their abdomen because of a difference in the forms of their sex organs, most of the crabs settle with their shell side upward when placed on a floor, making visual gender identification difficult. Our objective is to use deep learning to identify the gender of the horsehair crab on the basis of images of their shell and abdomen sides. Deep learning was applied to a photograph of 60 males and 60 females captured in Funka Bay, Southern Hokkaido, Japan. The deep learning algorithms used the AlexNet, VGG-16, and ResNet-50 convolutional neural networks. The VGG-16 network achieved high accuracy. Heatmaps were enhanced near the forms of the sex organs in the abdomen side (F-1 measure: 98%). The bottom of the shell was enhanced in the heatmap of a male; by contrast, the upper part of the shell was enhanced in the heatmap of a female (F-1 measure: 95%). The image recognition of the shell side based on a deep learning algorithm enabled more precise gender identification than could be achieved by human-eye inspection.

Micro- and Nanoscale Imaging of Fluids in Water Using Refractive-Index-Matched Materials.

Three-dimensional (3D) visualization in water is a technique that, in addition to macroscale visualization, enables micro- and nanoscale visualization via a microfabrication technique, which is particularly important in the study of biological systems. This review paper introduces micro- and nanoscale 3D fluid visualization methods. First, we introduce a specific holographic fluid measurement method that can visualize three-dimensional fluid phenomena; we introduce the basic principles and survey both the initial and latest related research. We also present a method of combining this technique with refractive-index-matched materials. Second, we outline the TIRF method, which is a method for nanoscale fluid measurements, and introduce measurement examples in combination with imprinted materials. In particular, refractive-index-matched materials are unaffected by diffraction at the nanoscale, but the key is to create nanoscale shapes. The two visualization methods reviewed here can also be used for other fluid measurements; however, because these methods can used in combination with refractive-index-matched materials in water, they are expected to be applied to experimental measurements of biological systems.

Iterative blind deconvolution method for dwell-time adjustment.

Negative values occur in the calculation results when a fast Fourier transform is used in the algorithm to calculate the dwell time via the dwell-time adjustment algorithm for optical element grinding. In the present study, a processing method for negative values is used in the Fourier iterative Ayers-Dainty (AD) algorithm. The method in which the range of the unit removal shape was adopted in the AD algorithm resulted in a smaller error and enabled the error to be minimized using the quantized dwell-time distribution output.

Detection of microbubble position by a digital hologram.

This paper reports on a new technique of measurements of microbubble position in three dimensions with high time-resolution. The technique is based on micro digital holographic particle tracking velocimetry. In this technique, an intensity profile is constructed from a holographic image of a microbubble where the profile results in showing two peaks. The distance between the two peaks appears to relate to the size of the microbubble's diameter. The three-dimensional position of the bubble can be detected by the center of the two peaks and the center point of the bubble image focused by a digital hologram. We also theoretically obtained the intensity profile of a microbubble by considering a refraction of light on a bubble surface to a ring-shaped aperture model. The theoretically obtained distance between the two peaks is found to be in good agreement with the values obtained experimentally.

Special purpose computer system for flow visualization using holography technology.

We have designed a special purpose computer system for visualizing fluid flow using digital holographic particle tracking velocimetry (DHPTV). This computer contains an Field Programmble Gate Array (FPGA) chip in which a pipeline for calculating the intensity of an object from a hologram by fast Fourier transform is installed. This system can produce 100 reconstructed images from a 1024 x 1024-grid hologram in 3.3 sec. It is expected that this system will contribute to fluid flow analysis.

Parallel computing of a digital hologram and particle searching for microdigital-holographic particle-tracking velocimetry.

We have developed a parallel algorithm for microdigital-holographic particle-tracking velocimetry. The algorithm is used in (1) numerical reconstruction of a particle image computer using a digital hologram, and (2) searching for particles. The numerical reconstruction from the digital hologram makes use of the Fresnel diffraction equation and the FFT (fast Fourier transform), whereas the particle search algorithm looks for local maximum graduation in a reconstruction field represented by a 3D matrix. To achieve high performance computing for both calculations (reconstruction and particle search), two memory partitions are allocated to the 3D matrix. In this matrix, the reconstruction part consists of horizontally placed 2D memory partitions on the x-y plane for the FFT, whereas, the particle search part consists of vertically placed 2D memory partitions set along the z axes. Consequently, the scalability can be obtained for the proportion of processor elements, where the benchmarks are carried out for parallel computation by a SGI Altix machine.

Special purpose computer for digital holographic particle tracking velocimetry.

We have designed a special purpose computer system for digital holographic particle tracking velocimetry (DHPTV). We present the pipeline for calculating the intensity of an object from a hologram by fast Fourier transform in an FPGA chip. This system uses four FPGA chips and can make 100 reconstructed images from a 256x256-grid hologram in 266 msec. It is expected that this system will improve the efficiency of analysis in DHPTV.