There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

“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

In recent years, many deep architectures have been proposed for handwritten text recognition. However, most of the previous deep models need large scale training data and a long training time to obtain good results. In this paper, we propose a novel deep learning method based on “stretching” the projection matrices of stacked feature learning models. We call the proposed method “stretching deep architectures” (or SDA). In the implementation of SDA, stacked feature learning models are first learned layer by layer, and then the stretching technique is applied on the weight matrices between successive layers. As the feature learning models can be efficiently optimized and the stretching results can be easily computed, the training of SDA is very fast and no back propagation is needed. We have tested SDA on handwritten digits recognition, Arabic subword recognition and English letter recognition tasks. Extensive experiments demonstrate that SDA performs not only better than shallow feature learning models, but also state-of-the-art deep learning models.

Stretching deep architectures for text recognition

Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. Lightweight neural network is one practical and effective way to accomplish the single-image segmentation task. This work focuses on the single-image segmentation problem only with some seeds such as scribbles. Inspired by the dynamic receptive field in the human being’s visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Determining the relative ubiety between the camera and the laser projector in a line-structured light vision sensor is a classical yet important task. Typical calibration methods often confront problems, such as difficulty of producing the target precisely and introduction of perspective projection errors. In this work, a new calibration method based on a concentric circle feature is introduced. The proposed method is based on geometrical properties and can reduce the perspective projection error. In our method, the vanishing line of the light plane is firstly deduced from the imaged concentric circles. Then the normal vector of the light plane is determined. Consequently, the complete expression can be confirmed from the principle of the intersecting planes. The proposed method is simple and robustness as the basic theory is geometrical properties. Accuracy evaluation experiment shows that the accuracy of the calibration method can reach 0.07 mm within the view field of about 200 × 200 mm. This accuracy is comparable to the commonly used calibration method with a checkerboard planar target, whereas our target is simple to produce.

/pdf/a-new-calibration-method-for-line-structured-light-vision-1psamgxooj.pdf

A new calibration method for line-structured light vision sensors based on concentric circle feature

NormAttention-PSN: A High-frequency Region Enhanced Photometric Stereo Network with Normalized Attention

Different wavelengths of light may undergo changes in underwater environment resulting in altered images. For example, the presence of floating particles causes underwater images to appear bluish and blurred. In this study, the authors propose a method called the deep sparse non-negative matrix factorisation (DSNMF) to estimate the illumination of an underwater image. The image under observation is divided into patches and each channel of a single patch is reshaped as an [ R, G, B ] matrix. The DSNMF method deeply factorises each input matrix into multiple layers with a sparseness constraint. The last layer of the factorised matrix is used as the illumination of the patch. The sparseness constraint adjusts the appearance of the final image. After factorisation, the estimated illumination is applied to each patch of the original image to obtain the final image. Compared with state-of-the-art underwater image enhancement methods using no reference image quality assessment, not only does the proposed method outperforms current techniques in terms of its visual effect and IQA, but is also simpler to implement.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-ipr.2016.0543

Junyu Dong

Papers

Stretching deep architectures for text recognition

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

A new calibration method for line-structured light vision sensors based on concentric circle feature

NormAttention-PSN: A High-frequency Region Enhanced Photometric Stereo Network with Normalized Attention

Underwater image colour constancy based on DSNMF