Efficient image structural similarity quality assessment method using image regularised feature

Abstract

Image regularised features play a critical role in image processing domain, by integrating regularised feature and structural similarity, a new full-reference image assessment method (IRF_SSIM) is proposed in this study. As well known, the gradient operator always be used to capture the edge information of the image, while the total variational regularised features can be adopted to calculate the detailed change information of image contrast and texture, as well as noise removal and edge retention. Therefore, the IRF_SSIM method extends the gradient features into the image regularised features to measure the structural changes in the image. In addition, image quality is also affected by variations of luminance and contrast. For a more comprehensive image quality assessment, the IRF_SSIM method considers the changes in structure, luminance and contrast simultaneously. In other words, the total image quality is estimated by structural similarity calculated by integrating the effects of image structure, luminance and contrast changes. Comparing with the representative methods, the experimental results illustrate that the IRF_SSIM method is highly consistent with the subjective assessment results.

Breast cancer diagnosis through an optimization‐driven multispectral gamma correction (ODMGC)

“…Lower DSSIM values suggest a more significant similarity between the images. [29][30][31][32] Tables 1 through 4 compare malignant and normal cases after applying BBHE, DSIHE, RETINEX, ODMGC 1 , and ODMGC 2 enhancement methods. This work also thoroughly analysed IQA metrics like PSNR, ASME, SSIM, and DSSIM.…”

“…The degree to which an image meets the viewer's information demands determines how much impact noise and image quality reduction have on one another 28 . The four IQA metrics, such as Peak Signal to Noise Ratio (PSNR), Absolute Mean Brightness Error (AMBE), Structural Similarity Index Measure (SSIM), and Structural Dissimilarity (DSSIM) for both normal and malignant images are compared in this study 29–32 . This assessment is accomplished by comparing the enhanced images to their original inputs.…”

“…It measures the structure, luminance, and contrast changes between the processed and reference images. Lower DSSIM values suggest a more significant similarity between the images 29–32 …”

CHIME: Causal Human-in-the-Loop Model Explanations

“…The authors manually validated the quality of the generated pair by visually inspecting 45 subsets of image pairs. Indeed, subjective similarity has been used as ground truth for automated similarity techniques (Li et al 2020). In addition to colour similarity, we evaluated object similarity based on the concepts provided by crowd workers, e.g., given two images, if both of them contain "Spoon" then we consider those two images as similar.…”