Edge Dissimilarity Research Articles

Weighting the transitivity of undirected weighted social networks with triadic edge dissimilarity scores

When an individual is socially connected to two others, the resulting triplet can be closed (if the two social partners are themselves connected) or open (if they are not connected). The proportion of closed triplets, referred to as the binary network transitivity, is a classic measure of the level of interconnectedness of a social network. However, in any given triplet, if the closing link is weak, or indeed if any of the links in the triplet is weak, then the triplet should not contribute as much to network transitivity as if all three links were equally strong. I propose two ways to weight the contribution of each triplet according to the dissimilarity between the three links in the triplet. Empirically, the resulting new metrics conveyed information not picked up by any other network-level metric. I envision that this approach could prove useful in studies of triadic mechanisms, i.e., situations where pre-existing social ties influence the interactions with third parties. These metrics could also serve as repeatable synthetic variables that summarize information about the variability of the strength of social connections.

United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI

Simultaneous segmentation and detection of liver tumors (hemangioma and hepatocellular carcinoma (HCC)) by using multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for the clinical diagnosis. However, it is still a challenging task due to: (1) the HCC information on NCMRI is insufficient makes extraction of liver tumors feature difficult; (2) diverse imaging characteristics in multi-modality NCMRI causes feature fusion and selection difficult; (3) no specific information between hemangioma and HCC on NCMRI cause liver tumors detection difficult. In this study, we propose a united adversarial learning framework (UAL) for simultaneous liver tumors segmentation and detection using multi-modality NCMRI. The UAL first utilizes a multi-view aware encoder to extract multi-modality NCMRI information for liver tumor segmentation and detection. In this encoder, a novel edge dissimilarity feature pyramid module is designed to facilitate the complementary multi-modality feature extraction. Secondly, the newly designed fusion and selection channel is used to fuse the multi-modality feature and make the decision of the feature selection. Then, the proposed mechanism of coordinate sharing with padding integrates the multi-task of segmentation and detection so that it enables multi-task to perform united adversarial learning in one discriminator. Lastly, an innovative multi-phase radiomics guided discriminator exploits the clear and specific tumor information to improve the multi-task performance via the adversarial learning strategy. The UAL is validated in corresponding multi-modality NCMRI (i.e. T1FS pre-contrast MRI, T2FS MRI, and DWI) and three phases contrast-enhanced MRI of 255 clinical subjects. The experiments show that UAL gains high performance with the dice similarity coefficient of 83.63%, the pixel accuracy of 97.75%, the intersection-over-union of 81.30%, the sensitivity of 92.13%, the specificity of 93.75%, and the detection accuracy of 92.94%, which demonstrate that UAL has great potential in the clinical diagnosis of liver tumors.

Unsupervised Edge Detector based on Evolved Cellular Automata

Abstract Extensive research has been performed in image processing to find the best edge detector, from the gradient-based operators to evolved Cellular Automata (CA). Some of these detectors have weak points, such as disconnected edges, the incapacity of detecting the branching edges or the need of a ground truth that is not always available. To overcome these issues, we propose a CA-based edge detector adapted to the particularities of the image. The adaption means to identify the best CA rule, which is an optimization problem solved by a Genetic Algorithm (GA). The GA requires a fitness function and we propose to use an unsupervised fitness based on edge dissimilarity. The performed numerical experiments are meant to evaluate the proposed approach and to emphasize that some of the weak points of a well-known detector (Canny) can be overcome by our method.

Reduced-Reference Video Quality Metric Using Spatial Information in Salient Regions

In multimedia transmission, it is important to rely on an objective quality metric which accurately represents the subjective quality of processed images and video sequences. Maintaining acceptable Quality of Experience in video transmission requires the ability to measure the quality of the video seen at the receiver end. Reduced-reference metrics make use of side-information that is transmitted to the receiver for estimating the quality of the received sequence with low complexity. This attribute enables real-time assessment and visual degradation detection caused by transmission and compression errors. A novel reduced-reference video quality known as the Spatial Information in Salient Regions Reduced Reference Metric is proposed. The approach proposed makes use of spatial activity to estimate the received sequence distortion after concealment. The statistical elements analysed in this work are based on extracted edges and their luminance distributions. Results highlight that the proposed edge dissimilarity measure has a good correlation with DMOS scores from the LIVE Video Database.

Edge Dissimilarity Reduced-Reference Quality Metric with Low Overhead Bitrate

In multimedia transmission, it is important to rely on an objective quality metric which accurately represents the subjective quality of processed images and video sequences. Reduced-reference metrics make use of side-information that is transmitted to the receiver for estimating the quality of the received sequence with low complexity. In this paper, an Edge-based Dissimilarity Reduced-Reference video quality metric with low overhead bitrate is proposed. The metric is evaluated by finding the dissimilarity between the edge information of original and distorted sequences. The edge degradation can be detected in this manner as perceived video quality is highly associated with edge structural. Due to the high overhead using the Soergel distance, it is pertinent to find a way to reduce the overhead while maintaining the edge information that can convey the quality measure of the sequences. The effects of different edge detection operator, video resolution and file compressor are investigated. The aim of this paper is to significantly reduce the bitrate required in order to transmit the side information overhead as the reduced reference video quality metric. From the results obtained, the side information extracted using Sobel edge detector maintained consistency throughout the reduction of spatial and temporal down-sample.

Edge Dissimilarity Reduced-Reference Quality Metric with Low Overhead Bitrate

In multimedia transmission, it is important to rely on an objective quality metric which accurately represents the subjective quality of processed images and video sequences. Reduced-reference metrics make use of side-information that is transmitted to the receiver for estimating the quality of the received sequence with low complexity. In this paper, an Edge-based Dissimilarity Reduced-Reference video quality metric with low overhead bitrate is proposed. The metric is evaluated by finding the dissimilarity between the edge information of original and distorted sequences. The edge degradation can be detected in this manner as perceived video quality is highly associated with edge structural. Due to the high overhead using the Soergel distance, it is pertinent to find a way to reduce the overhead while maintaining the edge information that can convey the quality measure of the sequences. The effects of different edge detection operator, video resolution and file compressor are investigated. The aim of this paper is to significantly reduce the bitrate required in order to transmit the side information overhead as the reduced reference video quality metric. From the results obtained, the side information extracted using Sobel edge detector maintained consistency throughout the reduction of spatial and temporal down-sample.

Discriminative measures for comparison of phylogenetic trees

In this paper we introduce and study three new measures for efficient discriminative comparison of phylogenetic trees. The NNI navigation dissimilaritydnav counts the steps along a “combing” of the Nearest Neighbor Interchange (NNI) graph of binary hierarchies, providing an efficient approximation to the (NP-hard) NNI distance in terms of “edit length”. At the same time, a closed form formula for dnav presents it as a weighted count of pairwise incompatibilities between clusters, lending it the character of an edge dissimilarity measure as well. A relaxation of this formula to a simple count yields another measure on all trees — the crossing dissimilaritydCM. Both dissimilarities are symmetric and positive definite (vanish only between identical trees) on binary hierarchies but they fail to satisfy the triangle inequality. Nevertheless, both are bounded below by the widely used Robinson–Foulds metric and bounded above by a closely related true metric, the cluster-cardinality metricdCC. We show that each of the three proposed new dissimilarities is computable in time O(n2) in the number of leaves n, and conclude the paper with a brief numerical exploration of the distribution over tree space of these dissimilarities in comparison with the Robinson–Foulds metric and the more recently introduced matching-split distance.

Almond Dispersion Detector for a New Almond Picker Apparatus using Coupled Image Segmentation and Genetic Algorithm

The objective of this study was to develop a machine vision system for detecting almond drop from trees on the ground during the harvesting stage. To attach this goal, in the machine vision system, the segmentation technique was coupled by genetic algorithm technique. The proposed method consists of three steps; Preprocessing included conversion images to gray level, noise reduction and edge dissimilarity enhancement; Image segmentation included K-means clustering algorithm, connected components labeling and remove small region; Region merge procedure using GA. The developed method was compared with usual image segmentation, thresholding and color segmentation. The results of fruit detection in the images showed that the developed method could detect 93% of all fruits in the images. While fruit detections using segmentation-thresholding and color segmentation in the images were 80% and 78%, respectively. The results confirmed that our method is found to be suitable, and effective for detecting almonds.

Towards Rapid Citywide Damage Mapping Using Neighborhood Edge Dissimilarities in Very High-Resolution Optical Satellite Imagery—Application to the 2003 Bam, Iran, Earthquake

Remote sensing technology is increasingly recognized as a valuable post-earthquake damage assessment tool. Recent studies performed by research teams in the United States, Japan, and Europe have demonstrated that building damage sustained in urban environments can be identified through analysis of optical imagery and synthetic aperture radar (SAR) data. Damage detection using automated change detection algorithms will soon facilitate the scaling and prioritization of relief efforts, as well as the monitoring of the recovery operations. This paper introduces the use of an edge dissimilarity algorithm to quantify the extent of building damage.