scholarly journals Heuristic threshold for Histogram-based Binarization of Grayscale Images

2014 ◽  
Vol 17 (1) ◽  
pp. 97
Author(s):  
Javier Montenegro Joo
Keyword(s):  
Grayscale Images

Se reporta el desarrollo de un laboratorio Virtual basado en histograma para llevar a cabo experimentos sobre binarizacion de imágenes en niveles de gris. A fin de automatizar el proceso de binarizacion, se introduce un Umbral Heurístico de Binarizacion. Después de obtener el histograma de una imagen en niveles de gris el modulo calcula el umbral heurístico, extrayendo el promedio ponderado de los niveles de gris de primer plano de la imagen. A continuación se resaltan los niveles de gris en la imagen que están por encima del umbral heurístico. Aunque aún no experimentalmente óptimo, el umbral heurístico proporciona una primera aproximación hacia la binarizacion automática de imágenes en niveles de gris.

Spatio-Temporal LED Driving for Subjective Super-Resolution of Grayscale Images

2019 ◽  
pp. 1243
Author(s):  
Kojiro Matsushita ◽  
Toyotaro Tokimoto ◽  
Kengo Fujii ◽  
Hirotsugu Yamamoto
Keyword(s):  
Super Resolution ◽  
Spatio Temporal ◽  
Grayscale Images

scholarly journals Data Augmentation Methods Applying Grayscale Images for Convolutional Neural Networks in Machine Vision

2021 ◽  
Vol 11 (15) ◽  
pp. 6721
Author(s):  
Jinyeong Wang ◽  
Sanghwan Lee
Keyword(s):  
Neural Networks ◽  
Machine Vision ◽  
Object Detection ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Image Data ◽  
Manufacturing Productivity ◽  
Smart Factories ◽  
Grayscale Images

In increasing manufacturing productivity with automated surface inspection in smart factories, the demand for machine vision is rising. Recently, convolutional neural networks (CNNs) have demonstrated outstanding performance and solved many problems in the field of computer vision. With that, many machine vision systems adopt CNNs to surface defect inspection. In this study, we developed an effective data augmentation method for grayscale images in CNN-based machine vision with mono cameras. Our method can apply to grayscale industrial images, and we demonstrated outstanding performance in the image classification and the object detection tasks. The main contributions of this study are as follows: (1) We propose a data augmentation method that can be performed when training CNNs with industrial images taken with mono cameras. (2) We demonstrate that image classification or object detection performance is better when training with the industrial image data augmented by the proposed method. Through the proposed method, many machine-vision-related problems using mono cameras can be effectively solved by using CNNs.

scholarly journals Contrast Enhancement of Digital Images Using an Improved Type-II Fuzzy Set-Based Algorithm

2021 ◽  
Vol 38 (1) ◽  
pp. 39-50
Author(s):  
Zohair Al-Ameen
Keyword(s):  
Fuzzy Set ◽  
Quality Evaluation ◽  
Low Complexity ◽  
Correction Method ◽  
Image Feature ◽  
Type Ii ◽  
Gamma Correction ◽  
Low Contrast ◽  
High Resolution Images ◽  
Grayscale Images

Contrast is a distinctive image feature that tells if it has adequate visual quality or not. On many occasions, images are captured with low-contrast due to inevitable obstacles. Therefore, an improved type-II fuzzy set-based algorithm is developed to enhance the contrast of various color and grayscale images properly while preserving the brightness and providing natural colors. The proposed algorithm utilizes new upper and lower ranges, amended Hamacher t-conorm, and a transform-based gamma correction method to provide the enhanced images. The proposed algorithm is assessed with artificial and real contrast distorted images, compared with twelve specialized methods, and the outcomes are evaluated using four advanced metrics. From the obtained results of experiments and comparisons, the developed algorithm demonstrated the ability to process various color and grayscale images, performed the best among the comparative methods, and scored the best in all four quality evaluation metrics. The findings of this study are significant because the proposed algorithm has low-complexity and can adjust the contrast of different images expeditiously, which enables it to be used with different imaging modalities especially those with limited hardware resources or produce high-resolution images.

Sign in / Sign up

Export Citation Format

Share Document