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

Generative adversarial network in medical imaging: A review.

Nuclear segmentation in digital microscopic tissue images can enable extraction of high-quality features for nuclear morphometrics and other analysis in computational pathology. Conventional image processing techniques, such as Otsu thresholding and watershed segmentation, do not work effectively on challenging cases, such as chromatin-sparse and crowded nuclei. In contrast, machine learning-based segmentation can generalize across various nuclear appearances. However, training machine learning algorithms requires data sets of images, in which a vast number of nuclei have been annotated. Publicly accessible and annotated data sets, along with widely agreed upon metrics to compare techniques, have catalyzed tremendous innovation and progress on other image classification problems, particularly in object recognition. Inspired by their success, we introduce a large publicly accessible data set of hematoxylin and eosin (H&E)-stained tissue images with more than 21000 painstakingly annotated nuclear boundaries, whose quality was validated by a medical doctor. Because our data set is taken from multiple hospitals and includes a diversity of nuclear appearances from several patients, disease states, and organs, techniques trained on it are likely to generalize well and work right out-of-the-box on other H&E-stained images. We also propose a new metric to evaluate nuclear segmentation results that penalizes object- and pixel-level errors in a unified manner, unlike previous metrics that penalize only one type of error. We also propose a segmentation technique based on deep learning that lays a special emphasis on identifying the nuclear boundaries, including those between the touching or overlapping nuclei, and works well on a diverse set of test images.

A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology

This paper presents a new supervised method for vessel segmentation in retinal images. This method remolds the task of segmentation as a problem of cross-modality data transformation from retinal image to vessel map. A wide and deep neural network with strong induction ability is proposed to model the transformation, and an efficient training strategy is presented. Instead of a single label of the center pixel, the network can output the label map of all pixels for a given image patch. Our approach outperforms reported state-of-the-art methods in terms of sensitivity, specificity and accuracy. The result of cross-training evaluation indicates its robustness to the training set. The approach needs no artificially designed feature and no preprocessing step, reducing the impact of subjective factors. The proposed method has the potential for application in image diagnosis of ophthalmologic diseases, and it may provide a new, general, high-performance computing framework for image segmentation.

A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images

Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels’ local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired by the recently introduced deformable convolutional networks, we integrate the deformable convolution into the proposed network. The DUNet, with upsampling operators to increase the output resolution, is designed to extract context information and enable precise localization by combining low-level features with high-level ones. Furthermore, DUNet captures the retinal vessels at various shapes and scales by adaptively adjusting the receptive fields according to vessels’ scales and shapes. Public datasets: DRIVE, STARE, CHASE_DB1 and HRF are used to test our models. Detailed comparisons between the proposed network and the deformable neural network, U-Net are provided in our study. Results show that more detailed vessels can be extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0.9566/0.9641/0.9610/0.9651 and AUC of 0.9802/0.9832/0.9804/0.9831 on DRIVE, STARE, CHASE_DB1 and HRF respectively. Moreover, to show the generalization ability of the DUNet, we use another two retinal vessel data sets, i.e., WIDE and SYNTHE, to qualitatively and quantitatively analyze and compare with other methods. Extensive cross-training evaluations are used to further assess the extendibility of DUNet. The proposed method has the potential to be applied to the early diagnosis of diseases.

DUNet: A deformable network for retinal vessel segmentation

Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-ipr.2012.0455

Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database

Fundus imaging is the most commonly used modality to collect information about the human eye background. Objective and quantitative assessment of quality for the acquired images is essential for manual, computer-aided and fully automatic diagnosis. In this paper, we present a no-reference quality metric to quantify image noise and blur and its application to fundus image quality assessment. The proposed metric takes the vessel tree visible on the retina as guidance to determine an image quality score. In our experiments, the performance of this approach is demonstrated by correlation analysis with the established full-reference metrics peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM). We found a Spearman rank correlation for PSNR and SSIM of 0.89 and 0.91. For real data, our metric correlates reasonable to a human observer, indicating high agreement to human visual perception.

/pdf/automatic-no-reference-quality-assessment-for-retinal-fundus-56n45d6y6e.pdf

Automatic no-reference quality assessment for retinal fundus images using vessel segmentation

This paper deals with registration of retinal images, which were taken by high-resolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps — global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1·13 and 0·93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus p...

Hybrid retinal image registration using phase correlation

A method for segmentation of vessel structure in colour retinal fundus images is presented, based on 2D matched filtering correlating the local image areas with 2D masks obtained via averaging of brightness profiles of vessels for several different vessel widths.Each of the basic masks is rotated in twelve different directions; this way, 60 masks for 5 different widths, each with 12 orientations are produced and used as 2D convolution kernels of the matched filters. The maximum response of all the filter responses for a concrete local area thus carries - if there is a vessel present - the information both on the width and orientation of the vessel segment. Compared to the previously published results [6], the segmentation has been improved primarily in two directions: the width resolution has been increased from 3 to 5 classes with a better approximation of the brightness profiles, and the orientation information is now utilized to provide vessel direction maps that are further used in the following phase of complementing the missing vessel segments. The parametric maps representing the maximum responses of the filters are then combined and finally tresholded thus obtaining binary vessel maps to be morphologically cleaned in order to remove the artefacts due to noise and also to complement the obviously missing parts of vessels. The method was designed and tested using the high-resolution fundus camera images provided by a cooperating ophthalmological clinic, and also statistically tested based on the standard public image database DRIVE.

Jan Odstrcilik

Papers

Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database

Automatic no-reference quality assessment for retinal fundus images using vessel segmentation

Hybrid retinal image registration using phase correlation

Improvement of Vessel Segmentation by Matched Filtering in Colour Retinal Images

Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration.