Image contrast enhancement in automatic mode by nonlinear stretching

Yelmanov, Sergei; Romanyshyn, Yuriy

doi:10.1109/memstech.2018.8365712

Cited by 15 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome this issue, IAGC [3] suggests using an inverse enhancement to decrease luminance when the input is too bright. On the other hand, ANS [4] uses an adaptive piecewise linear function of the brightness scale and suggests finding an optimal adaptive level using the Otsu thresholding [46]. These concepts are widely used in several study fields, such as dehazed tasks [31] [47] or image fusion framework 0, which extracts the strong and weak features from the input after using the relative total variation and enhances the vital feature by a specially-designed AGC algorithm.…”

Section: A Adaptive Gamma Correction Methodsmentioning

confidence: 99%

“…Low-cost enhancement methods were preferred in the pre-processing because high-level applications usually demanded more computational power; meanwhile, the computational capacity of some devices was quite limited. Gamma correction (Gamma) was time-saving and very efficient for adjusting the distribution of dark and bright pixels in images but needed to assign a gamma value manually; therefore, many adaptive methods were instrumental in selecting the suitable gamma values rapidly, including adaptive gamma correction (AGC) 0, adaptive gamma correction with weighted distribution (AGCWD) [2], improved adaptive gamma correction (IAGC) [3], and adaptive non-linear stretching (ANS) [4]. Histogram equalization (HE) was a popular method, too.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast, deep-learning-based dehazing algorithms were weak to restore the contrast of images in the HazeRD dataset (HRD) [28] (see Figs. 4(a) and 4(b), respectively). The research in [29] also mentioned dissatisfaction regarding visual appearance and time complexity burden, so they suggested preserving the fine texture effectively.…”

Section: Introductionmentioning

confidence: 99%

“…We obtained dehazed images with state-of-the-art dehazing algorithms. After that, the dehazed images were treated as raw images and enhanced using adaptive gamma correction methods 0- [2], luminance compensation for the fog-removal layer (LCFL) [36], and CLAHE [4]. When the enhancement method did not support color image, enhancements were applied to the luminance channel of the LAB color space.…”

mentioning

confidence: 99%

“…When the enhancement method did not support color image, enhancements were applied to the luminance channel of the LAB color space. We also evaluated the performance of the proposed framework based on three gamma-related enhancement methods, including Gamma, AGCWD [2], IAGC [3], and ANS [4]. The three adaptive gamma correction methods used histogram values of input images (0 to 255) to build gamma tables; however, some of the 2 * values exceeded 1.0, hindering normalization to [0, 255].…”

mentioning

confidence: 99%

See 4 more Smart Citations

Enhance Dehazed Images Rapidly Without Losing Restoration Accuracy

Liu

2024

IEEE Access

View full text Add to dashboard Cite

We proposed a novel image-enhancing framework to ensure consolidated restoration accuracy when remedying the visual quality of dehazed images, such as over-saturation, color deviation, or luminance issues. Conventionally, the dehazing process was usually considered image restoration; however, enhancement methods only aimed to improve dehazed images' contrast, brightness, and detail. Therefore, the conventional enhancing framework tended to degrade consolidated restoration accuracy due to focusing on low-level image features rather than controlling errors associated with the dehazing process. Our method aimed to improve the consolidated restoration accuracy of the dehazing-and-enhancing process. In experiments, the proposed framework improved the visual quality and preserved restoration accuracy (despite enhancements) with high computational efficiency and resolved quality issues generated by conventional dehazing algorithms. Moreover, the minimal time complexity of the proposed framework is O(n), ensuring practical applicability when implemented in conjunction with state-of-the-art dehazing algorithms.INDEX TERMS dehazing, haze, defogging, fog, haze removal, dark channel, image enhancement, error propagation, edge redundancy.

show abstract