Most of the binarization techniques associate a certain intensity value called threshold which separate the pixel values of the concerned input grey scale image into two classes like background and foreground. Each and every pixel should be compared with the threshold and transformed to its respective class according to the threshold value. In this paper an automatic binarisation technique with local adaptation without any intensity value (threshold) of partition, is described. It creates a binarised image by transforming the input image to its respective binarised image automatically without using any threshold value. It uses local mean to adapt to local environment within a window of size w w. Local mean determination is time consuming one and to reduce the time consumption, integral sum image is used as prior process. The input grey scale image is self transformed to an integral sum image within itself and then transform to binary image from the integral sum image itself.
This paper presents a spatial domain threshold based adaptive power-law applications (TAPLA) in image enhancement technique in which adaptation is carried out with local thresholds. This is an improved version of Adaptive Power-law Transformations (APLT) [14] in which adaptation is carried out with local means. The computational time of APLT is windowsize dependent to find local mean while the TAPLA is independent of window-size to find local means, which are used to determine the local threshold values. Window-size independent of computational time is due to use of integral average image as prior process to find local mean. Like APLT, TAPLA can control the enhancement factors such as contrast, brightness and sharpness/smoothness with a proper choice of parameters through a single function. This method can be applied on both the grey scale and color images. In the case of color images, each channel is considered separately. TAPLA outperforms better than APLT in image quality as well as in computational time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.