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

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2296
Author(s):  
Hyun-Tae Choi ◽  
Byung-Woo Hong
Keyword(s):  
Image Segmentation ◽  
High Performance ◽  
Ground Truth ◽  
Input Image ◽  
Image Model ◽  
Ground Truth Data ◽  
Weakly Supervised ◽  
Unsupervised Image Segmentation ◽  
Segmentation Models ◽  
Image Mask

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.

A Learning-Based Framework for Supervised and Unsupervised Image Segmentation Evaluation

2014 ◽  
Vol 14 (03) ◽  
pp. 1450014 ◽  
Author(s):  
Jian Lin ◽  
Bo Peng ◽  
Tianrui Li
Keyword(s):  
Image Segmentation ◽  
Ground Truth ◽  
Evaluation Framework ◽  
Segmentation Evaluation ◽  
Machine Learning Methods ◽  
Effectiveness Measure ◽  
Human Evaluation ◽  
Segmentation Quality ◽  
Image Segmentation Evaluation ◽  
Unsupervised Image Segmentation

Image segmentation is a fundamental task in automatic image analysis. However, there is still no generally accepted effectiveness measure which is suitable for evaluating the segmentation quality in every application. In this paper, we propose an evaluation framework which benefits from multiple stand-alone measures. To this end, different segmentation evaluation measures are chosen to evaluate segmentation separately, and the results are effectively combined using machine learning methods. We train and implement this framework in our brand-new segmentation dataset which contains images of different contents with segmentation ground truth and Weizmann segmentation database (WSD). In addition, we provide human evaluation of image segmentation pairs to benchmark the evaluation results of the measures. Experimental results show a better performance than the stand-alone methods.

scholarly journals Efficient ancestry and mutation simulation with msprime 1.0

Genetics ◽  
2021 ◽  
Author(s):  
Franz Baumdicker ◽  
Gertjan Bisschop ◽  
Daniel Goldstein ◽  
Graham Gower ◽  
Aaron P Ragsdale ◽  
...  
Keyword(s):  
Population Genetics ◽  
Data Structure ◽  
Software Quality ◽  
High Performance ◽  
Sequence Data ◽  
Ground Truth ◽  
Development Model ◽  
Ground Truth Data ◽  
Open Source Development ◽  
Memory Efficient

Abstract Stochastic simulation is a key tool in population genetics, since the models involved are often analytically intractable and simulation is usually the only way of obtaining ground-truth data to evaluate inferences. Because of this, a large number of specialized simulation programs have been developed, each filling a particular niche, but with largely overlapping functionality and a substantial duplication of effort. Here, we introduce msprime version 1.0, which efficiently implements ancestry and mutation simulations based on the succinct tree sequence data structure and the tskit library. We summarize msprime’s many features, and show that its performance is excellent, often many times faster and more memory efficient than specialized alternatives. These high-performance features have been thoroughly tested and validated, and built using a collaborative, open source development model, which reduces duplication of effort and promotes software quality via community engagement.

scholarly journals Long-Term Land Deformation Monitoring Using Quasi-Persistent Scatterer (Q-PS) Technique Observed by Sentinel-1A: Case Study Kelok Sembilan

2019 ◽  
Author(s):  
Pakhrur Razi
Keyword(s):  
High Performance ◽  
Ground Truth ◽  
Deformation Monitoring ◽  
Acquisition Time ◽  
Satellite Orbits ◽  
Mountainous Area ◽  
Ground Truth Data ◽  
Persistent Scatterer ◽  
Land Deformation ◽  
The Impact

Located on the mountainous area, Kelok Sembilan flyover area in West Sumatra, Indonesia has a long history of land deformation, therefore monitoring and analyzing as continuously is a necessity to minimize the impact. Notably, in the rainy season, the land deformation occurs along this area. The zone is crucial as the center of transportation connection in the middle of Sumatra. Quasi-Persistent Scatterer (Q-PS) Interferometry technique was applied for extracting information of land deformation on the field from time to time. Not only does the method have high performance for detecting land deformation but also improve the number of PS point, especially in a non-urban area. This research supported by 90 scenes of Sentinel-1A (C-band) taken from October 2014 to November 2017 for ascending and descending orbit with VV and VH polarization in 5 × 20 m (range × azimuth) resolution. Both satellite orbits detected two critical locations of land deformation namely as zone A and Zone B, which located in positive steep slope where there is more than 500 mm movement in the Line of Sight (LOS) during acquisition time. Deformations in the vertical and horizontal direction for both zone, are 778.9 mm, 795.7 mm and 730.5 mm, 751.7 mm, respectively. Finally, the results were confirmed by ground truth data using Unmanned Aerial Vehicle (UAV) observation.

scholarly journals MeshLifter: Weakly Supervised Approach for 3D Human Mesh Reconstruction from a Single 2D Pose Based on Loop Structure

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4257
Author(s):  
Sunwon Jeong ◽  
Ju Yong Chang
Keyword(s):  
Ground Truth ◽  
Reconstruction Error ◽  
Loop Structure ◽  
Ground Truth Data ◽  
3D Data ◽  
Reconstruction Performance ◽  
Human Pose ◽  
Mesh Reconstruction ◽  
Weakly Supervised ◽  
2D And 3D

In this paper, we address the problem of 3D human mesh reconstruction from a single 2D human pose based on deep learning. We propose MeshLifter, a network that estimates a 3D human mesh from an input 2D human pose. Unlike most existing 3D human mesh reconstruction studies that train models using paired 2D and 3D data, we propose a weakly supervised learning method based on a loop structure to train the MeshLifter. The proposed method alleviates the difficulty of obtaining ground-truth 3D data to ensure that the MeshLifter can be trained successfully from a 2D human pose dataset and an unpaired 3D motion capture dataset. We compare the proposed method with recent state-of-the-art studies through various experiments and show that the proposed method achieves effective 3D human mesh reconstruction performance. Notably, our proposed method achieves a reconstruction error of 59.1 mm without using the 3D ground-truth data of Human3.6M, the standard dataset for 3D human mesh reconstruction.

scholarly journals Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

2020 ◽  
Vol 12 (2) ◽  
pp. 207 ◽  
Author(s):  
Sherrie Wang ◽  
William Chen ◽  
Sang Michael Xie ◽  
George Azzari ◽  
David B. Lobell
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Damage Assessment ◽  
High Performance ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Classification Performance ◽  
Support Vector ◽  
Weak Supervision ◽  
Weakly Supervised

Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful translation to remote sensing tasks has been limited by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain. In this work, we perform cropland segmentation using two types of labels commonly found in remote sensing datasets that can be considered sources of “weak supervision”: (1) labels comprised of single geotagged points and (2) image-level labels. We demonstrate that (1) a U-Net trained on a single labeled pixel per image and (2) a U-Net image classifier transferred to segmentation can outperform pixel-level algorithms such as logistic regression, support vector machine, and random forest. While the high performance of neural networks is well-established for large datasets, our experiments indicate that U-Nets trained on weak labels outperform baseline methods with as few as 100 labels. Neural networks, therefore, can combine superior classification performance with efficient label usage, and allow pixel-level labels to be obtained from image labels.

scholarly journals Semi-automated Root Image Analysis (saRIA)

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Narendra Narisetti ◽  
Michael Henke ◽  
Christiane Seiler ◽  
Rongli Shi ◽  
Astrid Junker ◽  
...  
Keyword(s):  
Image Analysis ◽  
Image Segmentation ◽  
Root System ◽  
System Architecture ◽  
Ground Truth ◽  
Automated Analysis ◽  
Root System Architecture ◽  
Automated Image Analysis ◽  
Projection Area ◽  
Ground Truth Data

AbstractQuantitative characterization of root system architecture and its development is important for the assessment of a complete plant phenotype. To enable high-throughput phenotyping of plant roots efficient solutions for automated image analysis are required. Since plants naturally grow in an opaque soil environment, automated analysis of optically heterogeneous and noisy soil-root images represents a challenging task. Here, we present a user-friendly GUI-based tool for semi-automated analysis of soil-root images which allows to perform an efficient image segmentation using a combination of adaptive thresholding and morphological filtering and to derive various quantitative descriptors of the root system architecture including total length, local width, projection area, volume, spatial distribution and orientation. The results of our semi-automated root image segmentation are in good conformity with the reference ground-truth data (mean dice coefficient = 0.82) compared to IJ_Rhizo and GiAroots. Root biomass values calculated with our tool within a few seconds show a high correlation (Pearson coefficient = 0.8) with the results obtained using conventional, pure manual segmentation approaches. Equipped with a number of adjustable parameters and optional correction tools our software is capable of significantly accelerating quantitative analysis and phenotyping of soil-, agar- and washed root images.

scholarly journals Robust A*-Search Image Segmentation Algorithm for Mine-like Objects Segmentation in SONAR Images

2020 ◽  
Vol 11 (2) ◽  
pp. 53-66
Author(s):  
Ivan Aleksi ◽  
Tomislav Matić ◽  
Benjamin Lehmann ◽  
Dieter Kraus
Keyword(s):  
Image Segmentation ◽  
Success Rate ◽  
Mobile Robotics ◽  
Ground Truth ◽  
Ground Truth Data ◽  
Side Scan Sonar ◽  
Search Image ◽  
Sonar Image ◽  
Sonar Images ◽  
The Cost

This paper addresses a sonar image segmentation method employing a Robust A*-Search Image Segmentation (RASIS) algorithm. RASIS is applied on Mine-Like Objects (MLO) in sonar images, where an object is defined by highlight and shadow regions, i.e. regions of high and low pixel intensities in a side-scan sonar image. RASIS uses a modified A*-Search method, which is usually used in mobile robotics for finding the shortest path where the environment map is predefined, and the start/goal locations are known. RASIS algorithm represents the image segmentation problem as a path-finding problem. Main modification concerning the original A*-Search is in the cost function that takes pixel intensities and contour curvature in order to navigate the 2D segmentation contour. The proposed method is implemented in Matlab and tested on real MLO images. MLO image dataset consist of 70 MLO images with manta mine present, and 70 MLO images with cylinder mine present. Segmentation success rate is obtained by comparing the ground truth data given by the human technician who is detecting MLOs. Measured overall success rate (highlight and shadow regions) is 91% for manta mines and 81% for cylinder mines.

scholarly journals Image Segmentation Techniques Using K-Means Clustering to Identify the Land Use Change Detection

2021 ◽  
Vol 10 (2) ◽  
pp. 1200-1206
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Image Segmentation ◽  
Land Use Change ◽  
Change Detection ◽  
Ground Truth ◽  
Important Application ◽  
Major Objective ◽  
Ground Truth Data ◽  
Point Of Interest

The change detection of the agriculture land and other land useis one of the important application of remote sensing imagery.The major objective of this paper tomeasure the different boundary regionsof the land classes using an image segmentation techniques. The initial categorizing of different land use classes is experimented by using k-means clustering, which basically clusters the point of interest with the pixel similarity. The measurement of the different pixel region represent the different classes of agriculture area is a challenging task with the real and synthetic images. The important characteristics of the algorithm preserves the cluster pixel details at most of the iterations, however for the similar canopy values the cluster effeminacy varies and the identification of the land clusters also deviates as compared with the ground truth data.

scholarly journals Efficient ancestry and mutation simulation with msprime 1.0

2021 ◽  
Author(s):  
Franz Baumdicker ◽  
Gertjan Bisschop ◽  
Daniel Goldstein ◽  
Graham Gower ◽  
Aaron P Ragsdale ◽  
...  
Keyword(s):  
Population Genetics ◽  
Data Structure ◽  
Software Quality ◽  
High Performance ◽  
Sequence Data ◽  
Ground Truth ◽  
Development Model ◽  
Ground Truth Data ◽  
Open Source Development ◽  
Memory Efficient

Stochastic simulation is a key tool in population genetics, since the models involved are often analytically intractable and simulation is usually the only way of obtaining ground-truth data to evaluate inferences. Because of this necessity, a large number of specialised simulation programs have been developed, each filling a particular niche, but with largely overlapping functionality and a substantial duplication of effort. Here, we introduce msprime version 1.0, which efficiently implements ancestry and mutation simulations based on the succinct tree sequence data structure and tskit library. We summarise msprime's many features, and show that its performance is excellent, often many times faster and more memory efficient than specialised alternatives. These high-performance features have been thoroughly tested and validated, and built using a collaborative, open source development model, which reduces duplication of effort and promotes software quality via community engagement.

Sign in / Sign up

Export Citation Format

Share Document