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

“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

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

Deep learning models for plant disease detection and diagnosis

License Plate Detection (LPD) is a key component in automatic license plate recognition system. Despite the success of License Plate Recognition (LPR) methods in the past decades, the problem is quite a challenge due to the diversity of plate formats and multiform outdoor illumination conditions during image acquisition. This paper aims at automatical detection of car license plates via image processing techniques. In this paper, we proposed a real-time and robust method for license plate detection using Heuristic Energy Map(HEM). In the vehicle image, the region of license plate contains many components or edges. We obtain the edge energy values of an image by using the box filter and search for the license plate region with high energy values. Using this energy value information or Heuristic Energy Map(HEM), we can easily detect the license plate region from vehicle image with a very high possibilities. The proposed method consists two main steps: Region of Interest (ROI) Detection and License Plate Detection. This method has better performance in speed and accuracy than the most of existing methods used for license plate detection. The proposed method can detect a license plate within 130 milliseconds and its detection rate is 99.2% on a 3.10-GHz Intel Core i3-2100(with 4.00 GB of RAM) personal computer.

/pdf/novel-license-plate-detection-method-based-on-heuristic-2tyv64wxr6.pdf

Novel License Plate Detection Method Based on Heuristic Energy Map

The discrete Frechet distance basically measures the similarity of two curves considering their paths as well as distances of all discrete points on two curves. The present algorithms to compute the discrete Frechet distance between two curves have very high computational complexity. In order to reduce its computational burden, we propose a CNN architecture to compute the discrete Frechet Distance, employing the parallel processing capability of CNN consisting of an array of locally-coupled cells and each cell as a dynamical system. This paper presents the proposed CNN structure and its required cell coupling laws. The performance of the proposed system is verified through simulations.

Computation of discrete Fréchet distance using CNN

A comparing study for detection microcalcifications in digital mammogram using wavelets is proposed. Microcalcifications are early sign of breast cancer appeared as isolated bright spots in mammograms, however, they are difficult to detect due to their small size (0.05 to 1 mm of diameter). From a signal processing point of view, microcalcifications are high frequency components in mammograms. To enhance the detection performance of the microcalcifications in the mammograms we use the wavelet transform. Due to the multi-resolution decomposition capacity of the wavelet transform, we can decompose the image into different resolution levels which are sensitive to different frequency bands. By choosing an appropriate wavelet with a right resolution level, we can effectively detect the microcalcifications in digital mammogram. In this paper, several normal wavelet family functions are studied comparably, and for each wavelet function, different resolution levels are explored for detecting the microcalcifications. Experimental results show that the Daubechies wavelet with 4th level decomposition achieves the best detecting result of 95% TP rate with FP rate of 0.3 clusters per image.

Comparing study for detecting microcalcifications in digital mammogram using wavelets

Automatic online multiple pedestrian tracking is a rather important and challenging task in the field of machine vision. A new multiple pedestrian tracking system is proposed in this paper, which combines pedestrian detection, motion prediction, target matching and adaptive location adjustment methods. The clip-split strategy was adopted for optimization of the detected pedestrian candidates, which resulted in great improvement of the tracking accuracies, especially when the marginal areas of the detected target candidates contained background scenes. For each frame, the proposed adaptive location adjustment method was used to adjust the location and scale of the targets to deal with drifting problems where necessary, especially after severe occlusions. Experimental results on three challenging real-world datasets demonstrated that the proposed tracker has excellent performance over other state-of-the-art trackers based on MOT metrics.

Online adaptive multiple pedestrian tracking in monocular surveillance video

Instance-level image translation aims to only translate instance of interest and can be operated more finely and flexibly than object-level and holistic-level image translation. However, current algorithms are not suitable to do it since they employ a holistic or object level’s discriminator that tends to change the whole image or all instances. To address the issue, we propose a simple yet effective local discriminator, in which the input image is split into two parts, region of interest (ROI) and background. Instance mask is employed to align the ROI and the background is design to be random in a prior distribution to mitigate a divergence between the ROI and the background. In this way, we obtain translated instance with decent margins without artifacts as current algorithms get. Moreover we propose a new architecture to simultaneously realize versatile instance-level image translation. Experimental results prove that our proposed algorithm outperforms the state-of-the-art in position accuracy and background retainment by a clear margin.

/pdf/instance-level-image-translation-with-a-local-discriminator-52n5vgon6t.pdf

Dong Sun Park

Papers

Novel License Plate Detection Method Based on Heuristic Energy Map

Computation of discrete Fréchet distance using CNN

Comparing study for detecting microcalcifications in digital mammogram using wavelets

Online adaptive multiple pedestrian tracking in monocular surveillance video

Instance-Level Image Translation With a Local Discriminator