Background and objective: During the initial stages, skin lesions may not have sufficient intensity difference or contrast from the background region on dermatological macro-images. The lack of proper light exposure at the time of capturing the image also reduces the contrast. Low contrast between lesion and background regions adversely impacts segmentation. Enhancement techniques for improving the contrast between lesion and background skin on dermatological macro-images are limited in the literature. An EfficientNet-based modified sigmoid transform for enhancing the contrast on dermatological macroimages is proposed to address this issue. Methods: A modified sigmoid transform is applied in the HSV color space. The crossover point in the modified sigmoid transform that divides the macro-image into lesion and background is predicted using a modified EfficientNet regressor to exclude manual intervention and subjectivity. The Modified EfficientNet regressor is constructed by replacing the classifier layer in the conventional EfficientNet with a regression layer. Transfer learning is employed to reduce the training time and size of the dataset required to train the modified EfficientNet regressor. For training the modified EfficientNet regressor, a set of value components extracted from the HSV color space representation of the macro-images in the training dataset is fed as input. The corresponding set of ideal crossover points at which the values of Dice similarity coefficient (DSC) between the ground-truth images and the segmented output images obtained from Otsu’s thresholding are maximum is defined as the target. Results: On images enhanced with the proposed framework, the DSC of segmented results obtained by Otsu’s thresholding increased from 0.68 ± 0.34 to 0.81 ± 0.17. Conclusions: The proposed algorithm could consistently improve the contrast between lesion and background on a comprehensive set of test images, justifying its applications in automated analysis of dermatological macro-images.
Image processing algorithms are finding various applications in manufacturing and materials industries such as identification of cracks in the fabricated samples, calculating the geometrical properties of the given microstructure, presence of surface defects, etc. The present work deals with the application of Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm for improving the quality of the microstructure images of the Friction Stir Welded joints. The obtained results showed that the obtained value of quantitative metric features such as Entropy value and RMS Contrast value were high which resulted in enhanced microstructure images.
The relevance and impact of probability distributions on image processing are the subject of this study.It may be characterized as a probability distribution function of brightness for a certain area, which might be a whole picture. To generate a histogram, the probability density function of the brightness is frequently calculated by counting how many times each brightness occurs in the picture region. The brightness average is defined as the sample mean of the brightness of pixels in a certain region. The frequency is shown by the histogram. The histogram has a wide range of uses in image processing. It could, for starters, be used for picture analysis. Second, the functions of an image's brightness and contrast, as well as the final two uses of equalizing and thresholding. Normalizing a histogram is one technique to convert the intensities of discrete distributions to the probability of discrete distribution functions. The technique to equalize the histogram is to control the image's contrast by altering their intensity distribution functions. The major goal of this procedure is to give the cumulative probability function a linear trend (CDF).A method of segmentation is to divide a section of the picture into constituent areas or objects.
This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep reinforcement learning (RL) for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied. Besides, it is possible to visualize what kind of operation is employed for each pixel at each iteration, which would help us understand why and how such an operation is chosen. We also believe that our technology can enhance the explainability and interpretability of the deep neural networks. In addition, because the operations executed at each pixels are visualized, we can change or modify the operations if necessary. We apply the proposed method to a variety of image processing tasks: image denoising, image restoration, local color enhancement, and saliency-driven image editing. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning. The source code is available on https://github.com/rfuruta/pixelRL.
This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep RL for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied. We apply the proposed method to three image processing tasks: image denoising, image restoration, and local color enhancement. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning.