Feature Detection Using Curvature Maps and the Min-cut/Max-flow Algorithm

Abstract We propose a novel efficient seed-based method for the multi-object segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, with each node in the tree representing an object. Each tree node may contain different individual high-level priors of its corresponding object and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT, on medical, natural, and synthetic images, indicate promising results comparable to the related baseline methods that include structural information, but with lower computational complexity. Compared to the hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.

Download Full-text

Topology cuts: A novel min-cut/max-flow algorithm for topology preserving segmentation in N–D images

Computer Vision and Image Understanding ◽

10.1016/j.cviu.2008.07.008 ◽

2008 ◽

Vol 112 (1) ◽

pp. 81-90 ◽

Cited By ~ 55

Author(s):

Yun Zeng ◽

Dimitris Samaras ◽

Wei Chen ◽

Qunsheng Peng

Keyword(s):

Flow Algorithm ◽

Min Cut

Download Full-text

A Competitive Study of Graph Reduction Methods for Min S-T Cut Image Segmentation

Image Processing & Communications ◽

10.1515/ipc-2015-0014 ◽

2014 ◽

Vol 19 (2-3) ◽

pp. 97-105

Author(s):

Tomasz Węgliński ◽

Anna Fabijańska ◽

Jarosław Goclawski

Keyword(s):

Graph Cut ◽

Size Reduction ◽

Practical Application ◽

Graph Reduction ◽

Segmentation Algorithms ◽

Flow Algorithm ◽

Graph Size ◽

Reduction Methods ◽

Graph Cut Segmentation ◽

Min Cut

Abstract When applied to the segmentation of 3D medical images, graph-cut segmentation algorithms require an extreme amount of memory and time resources in order to represent the image graph and to perform the necessary processing on the graph. These requirements actually exclude the graph-cut based approaches from their practical application. Hence, there is a need to develop the dedicated graph size reduction methods. In this paper, several techniques for the graph size reduction are proposed. These apply the idea of superpixels. In particular, two methods for superpixel creation are introduced. The results of applying the proposed methods to the segmentation of CT datasets using min-cut/max-flow algorithm are presented, compared and discussed.

Download Full-text

Feature Detection Requires Spatial Attention

PsycEXTRA Dataset ◽

10.1037/e527342012-007 ◽

2007 ◽

Author(s):

Jan Theeuwes ◽

Erik van der Burg ◽

Artem V. Belopolsky

Keyword(s):

Spatial Attention ◽

Feature Detection

Download Full-text

Motion correction in PET/CT

Nuklearmedizin ◽

10.1055/s-0038-1625215 ◽

2005 ◽

Vol 44 (S 01) ◽

pp. S46-S50 ◽

Cited By ~ 5

Author(s):

M. Dawood ◽

N. Lang ◽

F. Büther ◽

M. Schäfers ◽

O. Schober ◽

...

Keyword(s):

Optical Flow ◽

Motion Correction ◽

Motion Vector ◽

Emission Tomography ◽

Cardiac Pet ◽

Novel Approach ◽

Positron Emission ◽

Pet Ct ◽

Flow Algorithm ◽

Motion Vector Field

Summary:Motion in PET/CT leads to artifacts in the reconstructed PET images due to the different acquisition times of positron emission tomography and computed tomography. The effect of motion on cardiac PET/CT images is evaluated in this study and a novel approach for motion correction based on optical flow methods is outlined. The Lukas-Kanade optical flow algorithm is used to calculate the motion vector field on both simulated phantom data as well as measured human PET data. The motion of the myocardium is corrected by non-linear registration techniques and results are compared to uncorrected images.

Download Full-text

Tidal Flow: A Fast and Teachable Maximum Flow Algorithm

OLYMPIADS IN INFORMATICS ◽

10.15388/ioi.2018.03 ◽

2018 ◽

Vol 12 ◽

pp. 25-41

Author(s):

Matthew C. FONTAINE

Keyword(s):

Computer Science ◽

Tidal Flow ◽

Maximum Flow ◽

Efficient Algorithms ◽

Science Students ◽

Flow Algorithm ◽

Maximum Flows

Among the most interesting problems in competitive programming involve maximum flows. However, efficient algorithms for solving these problems are often difficult for students to understand at an intuitive level. One reason for this difficulty may be a lack of suitable metaphors relating these algorithms to concepts that the students already understand. This paper introduces a novel maximum flow algorithm, Tidal Flow, that is designed to be intuitive to undergraduate andpre-university computer science students.

Download Full-text

Novel Voltage Choice and Min-Cut Based Assignment for Dual-VDD System

IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences ◽

10.1587/transfun.e95.a.2208 ◽

2012 ◽

Vol E95.A (12) ◽

pp. 2208-2219 ◽

Cited By ~ 1

Author(s):

Haiqi WANG ◽

Sheqin DONG ◽

Tao LIN ◽

Song CHEN ◽

Satoshi GOTO

Keyword(s):

Min Cut

Download Full-text

Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentation

Journal of Imaging Science and Technology ◽

10.2352/j.imagingsci.technol.2020.64.4.040412 ◽

2020 ◽

Vol 64 (4) ◽

pp. 40412-1-40412-11

Author(s):

Kexin Bai ◽

Qiang Li ◽

Ching-Hsin Wang

Keyword(s):

Brain Tumor ◽

Data Augmentation ◽

A Priori ◽

Class Imbalance ◽

Maximum Flow ◽

Magnetic Resonance Images ◽

Tumor Segmentation ◽

Similarity Coefficients ◽

Segmentation Algorithms ◽

Flow Algorithm

Abstract To address the issues of the relatively small size of brain tumor image datasets, severe class imbalance, and low precision in existing segmentation algorithms for brain tumor images, this study proposes a two-stage segmentation algorithm integrating convolutional neural networks (CNNs) and conventional methods. Four modalities of the original magnetic resonance images were first preprocessed separately. Next, preliminary segmentation was performed using an improved U-Net CNN containing deep monitoring, residual structures, dense connection structures, and dense skip connections. The authors adopted a multiclass Dice loss function to deal with class imbalance and successfully prevented overfitting using data augmentation. The preliminary segmentation results subsequently served as the a priori knowledge for a continuous maximum flow algorithm for fine segmentation of target edges. Experiments revealed that the mean Dice similarity coefficients of the proposed algorithm in whole tumor, tumor core, and enhancing tumor segmentation were 0.9072, 0.8578, and 0.7837, respectively. The proposed algorithm presents higher accuracy and better stability in comparison with some of the more advanced segmentation algorithms for brain tumor images.

Download Full-text

ON METHODS OF OBJECT DETECTION IN VIDEO STREAMS

Computer systems and network ◽

10.23939/csn2020.01.080 ◽

2017 ◽

Vol 2 (1) ◽

pp. 80-87

Author(s):

Puyda V. ◽

◽

Stoian. A.

Keyword(s):

Computer Vision ◽

Object Detection ◽

Open Source ◽

Feature Detection ◽

Video Stream ◽

Object Identification ◽

Vision Systems ◽

Modern Computer ◽

Computer Vision Systems ◽

Open Source Hardware

Detecting objects in a video stream is a typical problem in modern computer vision systems that are used in multiple areas. Object detection can be done on both static images and on frames of a video stream. Essentially, object detection means finding color and intensity non-uniformities which can be treated as physical objects. Beside that, the operations of finding coordinates, size and other characteristics of these non-uniformities that can be used to solve other computer vision related problems like object identification can be executed. In this paper, we study three algorithms which can be used to detect objects of different nature and are based on different approaches: detection of color non-uniformities, frame difference and feature detection. As the input data, we use a video stream which is obtained from a video camera or from an mp4 video file. Simulations and testing of the algoritms were done on a universal computer based on an open-source hardware, built on the Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC processor with frequency 1,5GHz. The software was created in Visual Studio 2019 using OpenCV 4 on Windows 10 and on a universal computer operated under Linux (Raspbian Buster OS) for an open-source hardware. In the paper, the methods under consideration are compared. The results of the paper can be used in research and development of modern computer vision systems used for different purposes. Keywords: object detection, feature points, keypoints, ORB detector, computer vision, motion detection, HSV model color

Download Full-text