TY - GEN
T1 - An Effective Image Enhancement Algorithm for Single Image Haze Removal Based on Daubechies Wavelet Filter Bank
AU - Samantaray, Aswini Kumar
AU - Asritha, D.
AU - Lakshmi Prasanna, N.
AU - Vijaya Lakshmi, T.
AU - Sree Jaitha, P.
AU - Sai, Siva
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
PY - 2024
Y1 - 2024
N2 - The primary issues in producing natural images are low contrast and poor quality. A novel approach for image enhancement is proposed in this work employing the discrete wavelet transform, adaptive thresholding, and morphology-based method. To start, pre-processing procedures are used to preserve the fine features of an image. After that, Daubechies-2 (tap-4) wavelet filter bank is used to split the image into high-pass and low-pass subband images. Images from the high-pass subband are improved using an adaptive thresholding technique. The morphology-based top-hat transform is used to improve low-pass subband images. Once the high-frequency and low-frequency subimages have been processed, the enhanced image can be obtained by utilizing the inverse DWT approach. PSNR and RMSE are used to assess the extent to which the suggested method performs. Experiments revealed that this technique is excellent at both enhancing an image’s details and effectively preserving its edge features.
AB - The primary issues in producing natural images are low contrast and poor quality. A novel approach for image enhancement is proposed in this work employing the discrete wavelet transform, adaptive thresholding, and morphology-based method. To start, pre-processing procedures are used to preserve the fine features of an image. After that, Daubechies-2 (tap-4) wavelet filter bank is used to split the image into high-pass and low-pass subband images. Images from the high-pass subband are improved using an adaptive thresholding technique. The morphology-based top-hat transform is used to improve low-pass subband images. Once the high-frequency and low-frequency subimages have been processed, the enhanced image can be obtained by utilizing the inverse DWT approach. PSNR and RMSE are used to assess the extent to which the suggested method performs. Experiments revealed that this technique is excellent at both enhancing an image’s details and effectively preserving its edge features.
UR - https://www.scopus.com/pages/publications/85192218669
UR - https://www.scopus.com/pages/publications/85192218669#tab=citedBy
U2 - 10.1007/978-981-99-9531-8_20
DO - 10.1007/978-981-99-9531-8_20
M3 - Conference contribution
AN - SCOPUS:85192218669
SN - 9789819995301
T3 - Lecture Notes in Networks and Systems
SP - 251
EP - 259
BT - Advances in Data-Driven Computing and Intelligent Systems - Selected Papers from ADCIS 2023
A2 - Das, Swagatam
A2 - Saha, Snehanshu
A2 - Coello, Carlos A. Coello
A2 - Rathore, Hemant
A2 - Bansal, Jagdish Chand
PB - Springer Science and Business Media Deutschland GmbH
T2 - 2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, ADCIS 2023
Y2 - 21 September 2023 through 23 September 2023
ER -