Search

Showing total 2 results
2 results

1. Digitization of natural objects with micro CT and photographs

Author

Kenji Kohiyama, Takashi Ijiri, Akira Hirabayashi, Hideki Todo, and Yoshinori Dobashi

Subjects
0106 biological sciences, business.product_category, Computer science, Physiology, lcsh:Medicine, Digital Cameras, Computed tomography, Plant Science, 01 natural sciences, Diagnostic Radiology, Image Processing, Computer-Assisted, Photography, Medicine and Health Sciences, Computer vision, lcsh:Science, Tomography, Digitization, Digital camera, Multidisciplinary, medicine.diagnostic_test, Ecology, Radiology and Imaging, Plant Anatomy, Eukaryota, Cameras, Climbing, Bone Imaging, Insects, Optical Equipment, Plant-Insect Interactions, Engineering and Technology, Algorithms, Research Article, Arthropoda, Imaging Techniques, 010607 zoology, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Equipment, Neuroimaging, Flowers, Research and Analysis Methods, 010603 evolutionary biology, Texture (geology), Imaging, Three-Dimensional, Diagnostic Medicine, Plant-Animal Interactions, medicine, Humans, Animals, Micro ct, ComputingMethodologies_COMPUTERGRAPHICS, business.industry, Biological Locomotion, Plant Ecology, lcsh:R, Ecology and Environmental Sciences, Organisms, Reproducibility of Results, Biology and Life Sciences, Invertebrates, Computed Axial Tomography, X-Ray Radiography, lcsh:Q, Artificial intelligence, business, Tomography, X-Ray Computed, Volume (compression), Neuroscience
Abstract

In this paper, we present a three-dimensional (3D) digitization technique for natural objects, such as insects and plants. The key idea is to combine X-ray computed tomography (CT) and photographs to obtain both complicated 3D shapes and surface textures of target specimens. We measure a specimen by using an X-ray CT device and a digital camera to obtain a CT volumetric image (volume) and multiple photographs. We then reconstruct a 3D model by segmenting the CT volume and generate a texture by projecting the photographs onto the model. To achieve this reconstruction, we introduce a technique for estimating a camera position for each photograph. We also present techniques for merging multiple textures generated from multiple photographs and recovering missing texture areas caused by occlusion. We illustrate the feasibility of our 3D digitization technique by digitizing 3D textured models of insects and flowers. The combination of X-ray CT and a digital camera makes it possible to successfully digitize specimens with complicated 3D structures accurately and allows us to browse both surface colors and internal structures.

Published
2018

2. Emotion computing and Word Mover's Distance

Author

Ning Liu and Fuji Ren

Subjects
Computer science, Emotions, lcsh:Medicine, Social Sciences, 02 engineering and technology, Anxiety, computer.software_genre, Infographics, Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Feature (machine learning), Psychology, lcsh:Science, Language, Multidisciplinary, Applied Mathematics, Simulation and Modeling, Semantics, Physical Sciences, 020201 artificial intelligence & image processing, Graphs, Natural language processing, Word (computer architecture), Algorithms, Research Article, Computer and Information Sciences, Feature vector, Emotion classification, Research and Analysis Methods, Machine Learning Algorithms, Dimension (vector space), Artificial Intelligence, Humans, Computer Simulation, business.industry, Dimensionality reduction, Data Visualization, lcsh:R, Cognitive Psychology, Biology and Life Sciences, 020207 software engineering, Linguistics, Models, Theoretical, Visualization, Cognitive Science, lcsh:Q, Artificial intelligence, business, computer, Mathematics, Neuroscience
Abstract

In this paper, we propose an emotion separated method(SeTF·IDF) to assign the emotion labels of sentences with different values, which has a better visual effect compared with the values represented by TF·IDF in the visualization of a multi-label Chinese emotional corpus Ren_CECps. Inspired by the enormous improvement of the visualization map propelled by the changed distances among the sentences, we being the first group utilizes the Word Mover's Distance(WMD) algorithm as a way of feature representation in Chinese text emotion classification. Our experiments show that both in 80% for training, 20% for testing and 50% for training, 50% for testing experiments of Ren_CECps, WMD features get the best f1 scores and have a greater increase compared with the same dimension feature vectors obtained by dimension reduction TF·IDF method. Compared experiments in English corpus also show the efficiency of WMD features in the cross-language field.

Published
2018