earticle

논문검색

An Analysis of Contrast Enhancement using Activation Functions

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

Abstract
 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

저자정보

  • Gourav Garg Department of C.S.E. & I.T. Madhav Institute of Technology and Science, Gwalior, India
  • Poonam Sharma Department of C.S.E. & I.T. Madhav Institute of Technology and Science, Gwalior, India

참고문헌

자료제공 : 네이버학술정보

    ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

    0개의 논문이 장바구니에 담겼습니다.