Adaptive contrast enhancement and de-enhancement

https://doi.org/10.1016/0031-3203(91)90072-DGet rights and content

Abstract

Two different interpolative schemes for adaptive contrast enhancement have been presented for speeding up the contrast enhancement algorithm proposed by Beghdadi and Negrate. To reduce the enhancement of noise in relatively flat regions present in the image, an adaptive power variation technique is used in which the degree of contrast enhancement is varied depending on the severity of brightness change in a region. A contrast transformation function is proposed which can be used for adaptive enhancement as well as de-enhancement of images.

References (21)

There are more references available in the full text version of this article.

Cited by (55)

  • COVID-RDNet: A novel coronavirus pneumonia classification model using the mixed dataset by CT and X-rays images

    2022, Biocybernetics and Biomedical Engineering
    Citation Excerpt :

    Besides, there is no clear boundary between the lesion region and normal lung tissue, where it is in a gradual transition state. To improve the negative and positive COVID-19 classification accuracy, the proposed algorithm enhances the contrast between the COVID-19 region and the normal region by an adaptive enhancement algorithm [46–49]. To overcome the problems in traditional deep learning, the proposed COVID-RDNet model is shown in Fig. 9 and its innovations are as follows:

  • Multichannel image contrast enhancement based on linguistic rule-based intensificators

    2019, Applied Soft Computing Journal
    Citation Excerpt :

    Many other techniques for image enhancement are exploited, e.g. global histogram equalisation [39], logarithmic transform histogram shifting and histogram-based image enhancement [40], dynamic histogram equalisation technique [41], multi-histogram normalisation method [42], and discrete cosine transform [43]. However, only few studies follow the direct approach that modify the image contrast at each pixel of the image, e.g. [21,22,38,44,45]. In [38,44], it is proved that the direct method offers techniques that can produce more effective results.

View all citing articles on Scopus
View full text