CARNet: Cascade attentive RefineNet for multi-lesion segmentation of diabetic retinopathy images

Diabetic retinopathy is the leading cause of blindness in working population. Lesion segmentation from fundus images helps ophthalmologists accurately diagnose and grade of diabetic retinopathy. However, the task of lesion segmentation is full of challenges due to the complex structure, the various sizes and the interclass similarity with other fundus tissues. To address the issue, this paper proposes a cascade attentive RefineNet (CARNet) for automatic and accurate multi-lesion segmentation of diabetic retinopathy. It can make full use of the fine local details and coarse global information from the fundus image. CARNet is composed of global image encoder, local image encoder and attention refinement decoder. We take the whole image and the patch image as the dual input, and feed them to ResNet50 and ResNet101, respectively, for downsampling to extract lesion features. The high-level refinement decoder uses dual attention mechanism to integrate the same-level features in the two encoders with the output of the low-level attention refinement module for multiscale information fusion, which focus the model on the lesion area to generate accurate predictions. We evaluated the segmentation performance of the proposed CARNet on the IDRiD, E-ophtha and DDR data sets. Extensive comparison experiments and ablation studies on various data sets demonstrate the proposed framework outperforms the state-of-the-art approaches and has better accuracy and robustness. It not only overcomes the interference of similar tissues and noises to achieve accurate multi-lesion segmentation, but also preserves the contour details and shape features of small lesions without overloading GPU memory usage.

Development of methods for generation of digital watermarks resistant to distortion

Active attacks and natural impacts can lead to two types of image-container distortions: noise-like and geometric. There are also image processing operations, e.g. scaling, rotation, truncation, pixel permutation which are much more detrimental to digital watermarks (DWM). While ensuring resistance to removal and geometric attacks is a more or less resolved problem, the provision of resistance to local image changes and partial image deletion is still poorly understood. The methods discussed in this paper are aimed at ensuring resistance to attacks resulting in partial image loss or local changes in the image. This study's objective is to develop methods for generating a distortion-resistant digital watermark using the chaos theory. This will improve the resistance of methods of embedding the digital watermark to a particular class of attacks which in turn will allow developers of DWM embedding methods to focus on ensuring the method resistance to other types of attacks. An experimental study of proposed methods was conducted. Histograms of DWMs have shown that the proposed methods provide for the generation of DWM of a random obscure form. However, the method based on a combination of Arnold’s cat maps and Henon maps has noticeable peaks unlike the method based on shuffling the pixels and their bits only with Arnold’s cat maps. This suggests that the method based only on Arnold’s cat maps is more chaotic. This is also evidenced by the value of the coefficient of correlation between adjacent pixels close to zero (0.0109) for color DWMs and 0.030 for black and white images.

Search for identical regions in images using invariant moments

One of the ways to describe objects on images is to identify some of their characteristic points or points of attention. Areas of neighborhoods of attention points are described by descriptors (lots of signs) in such way that they can be identified and compared. These signs are used to search for identical points in other images. The article investigates and establishes the possibility of searching for arbitrary local image regions by descriptors constructed with using invariant moments. A feature of the proposed method is that the calculation of the invariant moments of local areas is carried out with using the integral representation of the geometric moments of the image. Integral representation is a matrix with the same size as the image. The elements of the matrix is the sums of the geometric moments of individual pixels, which are located above and to the left with respect to the coordinates of this element. The number of matrices depends on the order of the geometric moments. For moments up to the second order (inclusively), there will be six such matrices. Calculation of one of six geometric moments of an arbitrary rectangular area of the image comes down up to 3 operations such as summation or subtraction of elements of the corresponding matrix located in the corners of this area. The invariant moments are calculated on base of six geometric moments. The search is performed by scanning the image coordinate grid with a window of a given size. In this case, the invariant moments and additional parameters are calculated and compared with similar parameters of the neighborhoods of the reference point of different size (taking into account the possible change in the image scale). The best option is selected according to a given condition. Almost all mass operations of the procedures for calculating the parameters of standards and searching of identical points make it possible explicitly perform parallel computations in the SIMD mode. As a result, the integral representation of geometric moments and the possibility of using parallel computations at all stages will significantly speed up the calculations and allow you to get good indicators of the search efficiency for identical points and the speed of work

Developing and Validating a Venue Stimuli-Local Image Fit Scale

Few studies in sport marketing have examined the formative role of venue stimuli in affecting sport spectators. As such, the fi eld currently lacks methodological direction for dealing with venue stimuli as a means to understand the sport spectator experience. Research is needed to inform academics and practitioners about the appropriate use and potential outcomes of venue stimuli, particularly as they relate to destination image and local place. Given the notable lack of investigation on this topic, this study was exploratory in nature, with the purposes of developing and validating a sport venue stimuli and local image fi t (SIF) scale. The development process of the SIF scale comprised the six stages of scale development recommended by previous scholars. Th e scale developed in this study provides a reliable and valid instrument designed to assess the extent to which sensory stimuli in the sport venue are congruent with local image, thus offering practitioners and academics a means to understand how inimitable elements of the local culture enrich the venue experience when they become intertwined with spectators’ sensory experience.

A geometric calibration approach for industrial cone-beam CT system based on low-rank phantom

Precise alignment of the system scan geometry is crucial to ensure the reconstructed image quality in the cone-beam CT system. A calibration method that depends on the local feature of ball bearings phantom and point-like markers is probably affected by local image variations. Besides, multiple projections with circular scanning are usually required by this type of method to derive misaligned parameters. In contrast to previous works, this paper proposes a method that depends on the global symmetric low-rank feature of a novel phantom, which can accurately represent the system geometrical misalignment. All the misaligned parameters of the cone-beam CT system can be estimated from a single perspective direction without circular scanning. Meanwhile, since the global low-rank feature of the phantom is utilized, the proposed method is robust to the noise. Extensive simulations and real experiments validate the accuracy and robustness of our method, which achieves better performance compared to an existing phantom-based method.

Automated Classification of High-resolution Rock Image Based on Residual Neural Network

The identification and classification of high-resolution rock images are significant for oil and gas exploration. In recent years, deep learning has been applied in various fields and achieved satisfactory results. This paper presents a rock classification method based on deep learning. Firstly, the high-resolution rock images are randomly divided into several small images as a training set. According to the characteristics of the datasets, the ResNet (Residual Neural Network) is optimized and trained. The local images obtained by random segmentation are predicted by using the model obtained by training. Finally, all probability values corresponding to each category of the local image are combined for statistics and voting. The maximum probability value and the corresponding category are taken as the final classification result of the classified image. Experimental results show that the classification accuracy of this method is 99.6%, which proves the algorithm’s effectiveness in high-resolution rock images classification.

Image Deblurring using Wiener Filtering and Siamese Neural Network

Blurred images are difficult to avoid in situations when minor Atmospheric turbulence or camera movement results in low-quality images. We propose a system that takes a blurred image as input and produces a deblurred image by utilizing various filtering techniques. Additionally, we utilize the Siamese Network to match local image segments. A Siamese Neural Network model is used that is trained to account for image matching in the spatial domain. The best-matched image returned by the model is then further used for Signal-to-Noise ratio and Point Spread Function estimation. The Wiener filter is then used to deblur the image. Finally, the results of the deblurring techniques with existing algorithms are compared and it is shown that the error in deblurring an image using the techniques presented in this paper is considerably lesser than other techniques.