“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Review of shape representation and description techniques

50 Years of Image Analysis

The authors show how large efficiencies can be achieved in model-based 3-D vision by combining the notions of discrete relaxation and bipartite matching. The computational approach presented is capable of pruning large segments of search space-an indispensable step when the number of objects in the model library is large and when recognition of complex objects with a large number of surfaces is called for. Bipartite matching is used for quick wholesale rejection of inapplicable models and for the determination of compatibility of a scene surface with a potential model surface taking into account relational considerations. The time complexity function associated with those aspects of the procedure that are implemented via bipartite matching is provided. The algorithms do not take more than a couple of iterations, even for objects with more than 30 surfaces. >

3-D object recognition using bipartite matching embedded in discrete relaxation

An ever increasing number of registered trademarks has created greater demand for an automatic trademark retrieval system. We present a method for such a system based on the image content using shape features. Zernike or pseudo-Zernike moments of the image are employed as a feature set. To retrieve similar shapes, we take into account visually salient features that dominantly affect the global shape of the trademarks and ignore their minor detail. Experimental results on a database of 3,000 trademark images demonstrate that the proposed method retrieves visually similar trademarks which agree well with human perception.

Content-based trademark retrieval system using visually salient features

A content-based image retrieval system retrieves an image based on an angular radial transform (ART) image descriptor. In the content-based image retrieval system, A method for retrieving an image includes the steps of: a) receiving a query image; b) extracting a query image descriptor from the query image based on at least an angular component and a radial component of the query image; c) comparing the query image descriptor with an image descriptor stored on the database; and d) determining a degree of a similarity between the query image descriptor and the image descriptor stored on the database.

Content-based image retrieval system and method for retrieving image using the same

The conventional method of estimating the rotation angle of a pattern using the principal axes is not suitable for circular symmetric patterns since their eigenvalues are similar in both directions. In the paper, a robust method of estimating a rotation angle using the phase information of Zernike moments is presented. The experimental results show that the proposed method estimates the rotation angle of the circular symmetric patterns more accurately than the principal axes method, even in the presence of noise.

Robust rotation angle estimator

Compression tests were performed in order to observe and investigate the rheological behavior of wrought aluminum alloys while varying the processing parameters such as liquid fraction, strain rate and materials. The results of an experimental investigation using Al2024, Al6061, Al7075 with a closed die are presented here. Specimens of each wrought aluminum alloy were characterized with their rheological behavior during partial melting and holding in the semi-solid state. The characteristics of flow between solid and liquid phases by considering liquid segregation are examined by restricting material (100% of packing rate in a closed die) during compression. The grain size was compared before and after the compression. Also, the strain–stress curves and microstructures of the rheological materials were investigated. Moreover, the tests allow the apparent viscosity of the alloys to be determined as a function of the liquid fraction and shear rate together with the densification behavior of the solid phase. Finally, the experimental results should be used in flow and solidification analyses and useful for manufacturing good SSM products through observing the microstructures according to changes solid fraction and compression rate.

Whoi-Yul Kim

Papers

3-D object recognition using bipartite matching embedded in discrete relaxation

Content-based trademark retrieval system using visually salient features

Content-based image retrieval system and method for retrieving image using the same

Robust rotation angle estimator

The effect of the solid fraction on rheological behavior of wrought aluminum alloys in incremental compression experiments with a closed die