Polarization image enhancement based on depth image segmentation in haze weather

Due to effects of the light by water and other particles, the quality of underwater image will degrade. The traditional underwater image segmentation methods based on intensity and spectrum have difficulty in determining boundary. Inspired by the visual system of mantis shrimps, this paper constructed a feedback neural network model, in which the parameters were optimized using machine learning method. Based on this model, we combine the polarization and intensity information to achieve the underwater polarization image segmentation. The results of experiment prove that the neural network model designed in this paper can improve the accuracy of underwater image segmentation.

Download Full-text

Depth image enhancement using local tangent plane approximations

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ◽

10.1109/cvpr.2015.7298980 ◽

2015 ◽

Cited By ~ 20

Author(s):

Kiyoshi Matsuo ◽

Yoshimitsu Aoki

Keyword(s):

Image Enhancement ◽

Tangent Plane ◽

Depth Image ◽

Local Tangent

Download Full-text

Development of Cable Inspection System Based on Image Processing

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.2199 ◽

2014 ◽

Vol 602-605 ◽

pp. 2199-2204

Author(s):

Huan Liu ◽

Chao Tao Liu

Keyword(s):

Image Processing ◽

Feature Extraction ◽

Image Segmentation ◽

Image Enhancement ◽

Image Recognition ◽

Host Computer ◽

Inspection System ◽

Energy Distributions ◽

Single Motor ◽

Image Acquisition System

A stayed cable inspection system was developed which consists of robot, host computer, cameras and image acquisition system. The robot was driven with single motor and could climb cables of various and variable diameters. Pictures of the cables’ were taken by the robot, and the defects and mars were identified automatically with image recognition. The steps of image recognition includes image de-noising, image enhancement, image segmentation, feature extraction, and recognition with the features of the images’ histogram grayscale distributions and energy distributions.

Download Full-text

FloW vision: Depth image enhancement by combining stereo RGB-depth sensor

2016 International Conference on Knowledge Creation and Intelligent Computing (KCIC) ◽

10.1109/kcic.2016.7883644 ◽

2016 ◽

Author(s):

Suryo Aji Waskitho ◽

Ardiansyah Alfarouq ◽

Sritrusta Sukaridhoto ◽

Dadet Pramadihanto

Keyword(s):

Image Enhancement ◽

Depth Image ◽

Depth Sensor

Download Full-text

An Extensive Review on Image Segmentation Techniques

Indian Journal of Image Processing and Recognition - regular ◽

10.35940/ijipr.b1002.061221 ◽

2021 ◽

Vol 1 (2) ◽

pp. 1-5

Author(s):

Kamlesh Sharma ◽

Nidhi Garg

Keyword(s):

Image Processing ◽

Image Segmentation ◽

Edge Detection ◽

Frequency Domain ◽

Image Enhancement ◽

Digital Images ◽

Extensive Review ◽

Current Image ◽

Segmentation Image

Image processing is the use of algorithms to perform various operations on digital images. The techniques that are explained further are image segmentation and image enhancement. Image Segmentation is a method to partition an image into multiple segments, to change the presentation of an image into something more meaningful and easier to analyze. The current image segmentation techniques include region-based segmentation and edge detection segmentation. Image Enhancement is the process of improving the quality of image. Under this section there are two broad divisions- Spatial Domain Technique and Frequency Domain Technique.

Download Full-text

Algorithmic Approaches For Image Edge Detection

International Journal of Advanced Trends in Computer Science and Engineering ◽

10.30534/ijatcse/2021/631032021 ◽

2021 ◽

Vol 10 (3) ◽

pp. 1942-1948

Keyword(s):

Image Processing ◽

Image Segmentation ◽

Edge Detection ◽

Image Enhancement ◽

Digital Image Processing ◽

Digital Image ◽

Image Edge Detection ◽

Image Edge ◽

Algorithmic Approaches

Edge detection is most important technique in digital image processing. It play an important role in image segmentation and many other applications. Edge detection providesfoundation to many medical and military applications.It difficult to generate a generic code for edge detection so many kinds ofalgorithms are available. In this article 4 different approaches Global image enhancement with addition (GIEA), Global image enhancement with Multiplication (GIEM),Without Global image enhancement with Addition (WOGIEA),and without Global image enhancement with Multiplication (WOGIEM)for edge detection is proposed. These algorithms are validatedon 9 different images. The results showthat GIEA give us more accurate results as compare to other techniques.

Download Full-text