Unsupervised Object Segmentation Based on Bi-Partitioning Image Model Integrated with Classification

The development of convolutional neural networks for deep learning has significantly contributed to image classification and segmentation areas. For high performance in supervised image segmentation, we need many ground-truth data. However, high costs are required to make these data, so unsupervised manners are actively being studied. The Mumford–Shah and Chan–Vese models are well-known unsupervised image segmentation models. However, the Mumford–Shah model and the Chan–Vese model cannot separate the foreground and background of the image because they are based on pixel intensities. In this paper, we propose a weakly supervised model for image segmentation based on the segmentation models (Mumford–Shah model and Chan–Vese model) and classification. The segmentation model (i.e., Mumford–Shah model or Chan–Vese model) is to find a base image mask for classification, and the classification network uses the mask from the segmentation models. With the classifcation network, the output mask of the segmentation model changes in the direction of increasing the performance of the classification network. In addition, the mask can distinguish the foreground and background of images naturally. Our experiment shows that our segmentation model, integrated with a classifier, can segment the input image to the foreground and the background only with the image’s class label, which is the image-level label.

Variety turn as the basis of an eductional concert

The purpose of the article is to analyze the creative process of the specifics of creating a variety of turns of different genres in an educational concert. The methodology consists of the use of the following methods: historical (art history), comparative, logical, and generalization, which allowed us to consider the issue of creative approaches as a basis for professional performance on stage. The scientific novelty of the obtained results lies in a qualitatively new approach to the issue of creating variety turns in educational concerts in the context of the formation of a modern specialist of variety art. Conclusions. Firstly, the analysis proved that for a variety of artists, namely in the genre of the compere’s comments, the proposed circumstances are the real circumstances of the concert. Secondly, a specific feature of communication between objects is the principle of interaction through the auditorium. Thirdly, the development of professional skills of improvisation on the stage is the most important condition for the training of future artists in higher art school. Fourthly, the main principle of work in an educational concert is to master a complex form of external and internal attention, which requires a constant «switching» of the way of existence of a variety of artists. Fifthly, when choosing, searching, and working on a variety of image-mask, the basic elements of the various artist's psychotechnics are crucial. Sixthly, various forms of educational concerts are the most important stage in the formation of professional skills of the future variety artist.

SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs. Recent deep neural network based FSS methods leverage high-dimensional feature similarity between the foreground features of the support images and the query image features. In this work, we demonstrate gaps in the utilization of this similarity information in existing methods, and present a framework - SimPropNet, to bridge those gaps. We propose to jointly predict the support and query masks to force the support features to share characteristics with the query features. We also propose to utilize similarities in the background regions of the query and support images using a novel foreground-background attentive fusion mechanism. Our method achieves state-of-the-art results for one-shot and five-shot segmentation on the PASCAL-5i dataset. The paper includes detailed analysis and ablation studies for the proposed improvements and quantitative comparisons with contemporary methods.

Target Image Mask Correction Based on Skeleton Divergence

Traditional approaches to modeling and processing discrete pixels are mainly based on image features or model optimization. These methods often result in excessive shrinkage or expansion of the restored pixel region, inhibiting accurate recovery of the target pixel region shape. This paper proposes a simultaneous source and mask-images optimization model based on skeleton divergence that overcomes these problems. In the proposed model, first, the edge of the entire discrete pixel region is extracted through bilateral filtering. Then, edge information and Delaunay triangulation are used to optimize the entire discrete pixel region. The skeleton is optimized with the skeleton as the local optimization center and the source and mask images are simultaneously optimized through edge guidance. The technique for order of preference by similarity to ideal solution (TOPSIS) and point-cloud regularization verification are subsequently employed to provide the optimal merging strategy and reduce cumulative error. In the regularization verification stage, the model is iteratively simplified via incremental and hierarchical clustering, so that point-cloud sampling is concentrated in the high-curvature region. The results of experiments conducted using the moving-target region in the RGB-depth (RGB-D) data (Technical University of Munich, Germany) indicate that the proposed algorithm is more accurate and suitable for image processing than existing high-performance algorithms.

Instance Segmentation on Real time Object Detection using Mask R-CNN

In the ever-advancing field of computer vision, image processing plays a prominent role. We can extend the applications of Image processing into solving real-world problems like substantially decreasing Human interaction over the art of driving. In the process of achieving this task, we face several challenges like Segmentation and Detection of objects. The proposed thesis overcomes the challenges effectively by introducing Instance segmentation and Binary masks along with Keras and Tensorflow. Instance segmentation is used to delineate and detect every unique object of interest according to their pixel characteristics in an image. Mask RCNN is the superior model over the existing CNN models and yields accurate detection of objects more efficiently. Unlike conventional Neural Networks which employs selective search algorithm to identify object of interest, Mask RCNN employs Regional Proposal Networks(RPN) to identify object of interest. For better results Image pre-processing techniques and morphological transformations are employed to reduce the noise and increase pixel clarity

Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

A central problem in biomedical imaging is the automated segmentation of images for further quantitative analysis. Recently, fully convolutional neural networks, such as the U-Net, were applied successfully in a variety of segmentation tasks. A downside of this approach is the requirement for a large amount of well-prepared training samples, consisting of image - ground truth mask pairs. Since training data must be created by hand for each experiment, this task can be very costly and time-consuming. Here, we present a segmentation method based on cycle consistent generative adversarial networks, which can be trained even in absence of prepared image - mask pairs. We show that it successfully performs image segmentation tasks on samples with substantial defects and even generalizes well to different tissue types.

IPI Noise Reduction by Image Mask Using DNA Coding Method in Holographic Data Storage System

A holographic data storage system (HDSS) is very important field in the storage system device. Many researchers study the HDSS about image processing algorithm for reduction of image noise. In this work, we proposed an intelligence virtual mask, parameter values of virtual image mask generated using DNA coding method, it is available to decrease the IPI noise in HDSS. In this paper, an intensity distribution of laser beam in our HDSS is controlled by the virtual mask with an intelligence algorithm. The virtual mask value is changed arbitrarily in real-time with suggested DNA coding method in the HDSS.