원문정보
초록
영어
The contrast of an image is a feature which determines how image looks better visually. In this paper, we are analysing the capability of activation functions for contrast enhancement. Activation functions are classically used in neural network. In this paper, Activation function creates a mask which is operated on the image on pixel by pixel basis. On the basis of activation function the pixel value of image is changed which improves the contrast of image. We have used various activation functions such as sigmoid function, bipolar sigmoid function, RAMP function, hyperbolic tangent function. Contrast enhancement using these activation functions has been successfully applied on several dark and bright images. For performance assessment we have used Peak Signal to Noise Ratio (PSNR), absolute mean brightness error (AMBE), and Structure Similarity Index (SSIM). From experimental result, it is observed that RAMP function and hyperbolic tangent function have better image enhancement capability.
목차
1. Introduction
2. Histogram Equalization (HE)
3. Activation Function
3.1. Uni Sigmoid Function
3.2. Bi-polar Sigmoid
3.3. Hyperbolic Tangent Function
3.4. Ramp Function
4. Activation function based algorithm
5. Performance Evaluation
5.1. Peak Signal to Noise Ratio (PSNR)
5.2. Absolute Mean Brightness Error(AMBE)
5.3. Structure Similarity Index (SSIM)
6. Results and Discussion
7. Conclusion
References