A Novel Gradient Vector Flow Snake Model Based on Convex Function for Infrared Image Segmentation.

Rui Zhang,Qin Zhou,Shiping Zhu

doi:10.3390/s16101756

Abstract

Infrared image segmentation is a challenging topic because infrared images are characterized by high noise, low contrast, and weak edges. Active contour models, especially gradient vector flow, have several advantages in terms of infrared image segmentation. However, the GVF (Gradient Vector Flow) model also has some drawbacks including a dilemma between noise smoothing and weak edge protection, which decrease the effect of infrared image segmentation significantly. In order to solve this problem, we propose a novel generalized gradient vector flow snakes model combining GGVF (Generic Gradient Vector Flow) and NBGVF (Normally Biased Gradient Vector Flow) models. We also adopt a new type of coefficients setting in the form of convex function to improve the ability of protecting weak edges while smoothing noises. Experimental results and comparisons against other methods indicate that our proposed snakes model owns better ability in terms of infrared image segmentation than other snakes models.

Highlights

Infrared radiation is an invisible type of electromagnetic wave, whose wavelength ranges between the radio wave and the visible light
The proposed gradient vector flow (GVF) model will be compared with GVF [18], generic gradient vector flow (GGVF) [19], normal gradient vector flow (NGVF) [20], normally biased gradient vector flow (NBGVF) [21], CN-GGVF [6], LIF [28] and SOAC [29] across different images
The infrared image segmentation technology is of great significance to real-world life and manufacturing

Summary

Introduction

Infrared radiation is an invisible type of electromagnetic wave, whose wavelength ranges between the radio wave and the visible light. Compared with the visible light, its light quantum energy is much lower, the heat effect is stronger, it is more likely to be absorbed by a substance, and is less sensitive to the human eye. The visible light between 0.4~0.75 μm can be sensed by human eyes. The light outside this range cannot be sensed without the aid of detectors. The advent and development of the infrared thermal imaging system indirectly broadens the visual sensing scope of the eyes. The most commonly used detector is the infrared thermal detector It can measure the infrared thermal radiation quantity in a non-contact manner, convert it into clearly visible images and display them on a screen

Results

Discussion

Conclusion