We have studied shape with a particular focus on the zebrafish model system. The shape is an essential appearance of the phenotype of a biological specimen and it can be used to read out a... Show moreWe have studied shape with a particular focus on the zebrafish model system. The shape is an essential appearance of the phenotype of a biological specimen and it can be used to read out a current state or response or to study gene expression. So accurate shape analysis requires a precise shape description. Moreover, a sufficiently large sampling size of the specimens is necessary to ensure a justified and unbiased shape analysis. The latter is very important for high-throughput in compound screening. Therefore, top performance in zebrafish analysis requires high-throughput imaging (HTI). To deal with HTI, we aim to design an elaborate and well-performing HTI architecture. For the essential operations we need computational approaches to obtain the 2D/3D shape representations that are precise and yet can be acquired fast. The quality of the obtained shape descriptions will be validated in a straightforward manner with scalar primitives, i.e., the volume and surface area of a 3D shape. These primitives serve as 3D measurements for a robust primary shape assessment in the phenotype characterisation. Using only shape description is not sufficient, e.g., for high-resolution imaging on tissue and cellular level, so texture should be considered to complement and enhance the shape analysis. Show less
With the dramatic growth of the image data on the web, there is an increasing demand of the algorithms capable of understanding the visual information automatically. Deep learning, served as one of... Show moreWith the dramatic growth of the image data on the web, there is an increasing demand of the algorithms capable of understanding the visual information automatically. Deep learning, served as one of the most significant breakthroughs, has brought revolutionary success in diverse visual applications, including image classification, object detection, image segmentation, image captioning and etc. The purpose of this thesis is to explore and design new deep learning algorithms for better visual understanding. The main purpose of the thesis is to develop new algorithms which can improve the understanding of images. To fulfill this, it focuses on two visual applications: image classification and image captioning. Image classification aims to classify images into pre-defined categories, and helps people to know what objects the images contain. Image captioning attempts to generate a sentence to describe the images. In addition to the object, the generated sentence should also contain the action, relation and etc. Show less
