Automatic segmentation algorithm for breast cell image based on multi-scale CNN and CSS corner detection

2020 ◽  
Vol 24 (3) ◽  
pp. 195-203
Author(s):  
Haoyang Tang ◽  
Cong Song ◽  
Meng Qian
Keyword(s):  
Automatic Segmentation ◽  
Scale Space ◽  
Segmentation Algorithm ◽  
Corner Detection ◽  
Adherent Cells ◽  
Multi Scale ◽  
Cell Image ◽  
Curvature Scale Space ◽  
Segmentation Accuracy ◽  
Initial Segmentation

As the shapes of breast cell are diverse and there is adherent between cells, fast and accurate segmentation for breast cell remains a challenging task. In this paper, an automatic segmentation algorithm for breast cell image is proposed, which focuses on the segmentation of adherent cells. First of all, breast cell image enhancement is carried out by the staining regularization. Then, the cells and background are separated by Multi-scale Convolutional Neural Network (CNN) to obtain the initial segmentation results. Finally, the Curvature Scale Space (CSS) corner detection is used to segment adherent cells. Experimental results show that the proposed algorithm can achieve 93.01% accuracy, 93.93% sensitivity and 95.69% specificity. Compared with other segmentation algorithms of breast cell, the proposed algorithm can not only solve the difficulty of segmenting adherent cells, but also improve the segmentation accuracy of adherent cells.

Multi-scale curvature product for robust image corner detection in curvature scale space

2007 ◽  
Vol 28 (5) ◽  
pp. 545-554 ◽  
Author(s):  
Xiaohong Zhang ◽  
Ming Lei ◽  
Dan Yang ◽  
Yuzhu Wang ◽  
Litao Ma
Keyword(s):  
Scale Space ◽  
Corner Detection ◽  
Multi Scale ◽  
Curvature Scale Space ◽  
Robust Image

Adaptive Corner Detection Based on Direct Curvature Scale Space

2013 ◽  
Vol 391 ◽  
pp. 488-492
Author(s):  
Bin Liao ◽  
Hui Ying Sun ◽  
Jun Gang Xu
Keyword(s):  
Real Time ◽  
Scale Space ◽  
Corner Detection ◽  
Local Curvature ◽  
Advanced Method ◽  
Multi Scale ◽  
Curvature Scale Space ◽  
Real Time Applications ◽  
Global And Local ◽  
Initial List

Corner detection based on global and local curvature properties is an advanced method for detecting corners in images, which is a fundamental composition of many algorithms. However, we find that it is time-consuming for real-time applications and might detect wrong corners or lose some important corners. To alleviate these problems, we propose an improved curvature product corner detector with dynamic region of support based on Direct Curvature Scale Space (DCSS). Firstly, we use direct curvature scale space to reduce the complexity of computation instead of curvature scale space. Secondly, multi-scale curvature product with certain threshold is used to strengthen the corner detection. Finally, we check the angles of corner candidates in the dynamic region of support in order to eliminate falsely detected corners and use an adaptive curvature threshold to remove round corners from the initial list. The experimental results show that our proposed method improves the performance of corner detection both on accuracy and efficiency, and gain more stable corners at the same time.

Robust Image Corner Detection Using Curvature Product in Direct Curvature Scale Space

2010 ◽  
Vol 20-23 ◽  
pp. 725-730 ◽  
Author(s):  
Bao Jiang Zhong ◽  
Chang Li
Keyword(s):  
Gaussian Function ◽  
Computational Cost ◽  
Local Maximum ◽  
Scale Space ◽  
Corner Detection ◽  
Absolute Value ◽  
Multi Scale ◽  
Curvature Scale Space ◽  
Robust Image ◽  
World Image

In this paper we propose an image corner detector based on the direct curvature scale space (DCSS) technique, referred to as the curvature product DCSS (CP-DCSS) corner detector. After the contours of interested objects are extracted from a real-world image, their curvature functions are respectively convolved with the Gaussian function as its standard deviation gradually increases. By measuring the product of the curvature values computed at several given scales, true corners on the contours can be easily detected since false or insignificant corners have been effectively suppressed. A point is declared as a corner when the absolute value of the curvature product exceeds a given threshold and is a local maximum at the mentioned point. CP-DCSS combines the advantages of two recently proposed corner detectors, namely, the DCSS corner detector and the multi-scale curvature product (MSCP) corner detector. Compared to DCSS, CP-DCSS omits a parsing process of the DCSS map, and hence it has a simpler structure. Compared to MSCP, CP-DCSS works equally well, however, at less computational cost.

Robust Corner Detection Based on Multi-scale Curvature Product in B-spline Scale Space

2007 ◽  
Vol 33 (4) ◽  
pp. 414-417 ◽  
Author(s):  
Yu-Zhu WANG ◽  
Dan YANG ◽  
Xiao-Hong ZHANG
Keyword(s):  
Scale Space ◽  
Corner Detection ◽  
B Spline ◽  
Multi Scale

Improved Multi-Scale Segmentation Algorithm for High Spatial Resolution Remote Sensing Images

2012 ◽  
Vol 500 ◽  
pp. 780-784
Author(s):  
Rui Liu ◽  
Shi Xin Wang ◽  
Yi Zhou ◽  
Zhen Feng Shao
Keyword(s):  
Remote Sensing ◽  
High Spatial Resolution ◽  
Scale Parameter ◽  
Segmentation Algorithm ◽  
Region Merging ◽  
Remote Sensing Images ◽  
Multi Scale ◽  
Initial Segmentation ◽  
Large Heterogeneity ◽  
Heterogeneity Parameter

An improved multi-scale segmentation algorithm is proposed in this paper. In order to get segmentation result more efficiently and accurately, watershed transformation is used as an initial segmentation algorithm, and then the objects of regions are merged based on the improved merge rule. The improved regulation for region merging is mainly based on the scale parameter of area-based while the heterogeneity parameter is considered as well. In this way, the failure of considering that some regions with large heterogeneity with their neighborhood are not suitable for merging will be prevented. Experimental results show that the quality and efficiency of remote sensing image segmentation can be greatly improved by the improved multi-scale segmentation algorithm.

Sign in / Sign up

Export Citation Format

Share Document