Image Entropy Research Articles

An automatic entropy method to efficiently mask histology whole-slide images

Tissue segmentation of histology whole-slide images (WSI) remains a critical task in automated digital pathology workflows for both accurate disease diagnosis and deep phenotyping for research purposes. This is especially challenging when the tissue structure of biospecimens is relatively porous and heterogeneous, such as for atherosclerotic plaques. In this study, we developed a unique approach called ‘EntropyMasker’ based on image entropy to tackle the fore- and background segmentation (masking) task in histology WSI. We evaluated our method on 97 high-resolution WSI of human carotid atherosclerotic plaques in the Athero-Express Biobank Study, constituting hematoxylin and eosin and 8 other staining types. Using multiple benchmarking metrics, we compared our method with four widely used segmentation methods: Otsu’s method, Adaptive mean, Adaptive Gaussian and slideMask and observed that our method had the highest sensitivity and Jaccard similarity index. We envision EntropyMasker to fill an important gap in WSI preprocessing, machine learning image analysis pipelines, and enable disease phenotyping beyond the field of atherosclerosis.

Imaging breast malignancies with the Twente Photoacoustic Mammoscope 2.

Clinical measurements on breast cancer patients were performed with a three-dimensional tomographic photoacoustic prototype imager (PAM 2). Patients with a suspicious lesion, visiting the center for breast care of a local hospital, were included in the study. The acquired photoacoustic images were compared to conventional clinical images. Of 30 scanned patients, 19 were diagnosed with one or more malignancies, of which a subset of four patients was selected for detailed analysis. Reconstructed images were processed to enhance image quality and the visibility of blood vessels. Processed photoacoustic images were compared to contrast-enhanced magnetic resonance images where available, which aided in localizing the expected tumoral region. In two cases, spotty high-intensity photoacoustic signals could be seen in the tumoral region, attributable to the tumor. One of these cases also displayed a relatively high image entropy at the tumor site, likely related to the chaotic vascular networks associated with malignancies. For the other two cases, it was not possible to identify features indicative of malignancy, because of limitations in the illumination scheme and difficulties in locating the region of interest in the photoacoustic image.

Dual-kernel driven convolutional sparse learning for bearing transient feature enhancement

The transient structure feature of bearing reflects the dynamic response of vibration, which is of vital importance for rotating machinery fault diagnosis. However, the measured signals are complicated and non-stationary, where the transient impacts are always submerged in heavy background noise. In this study, a novel dual-kernel driven convolutional sparse learning (DKCSL) is proposed to enhance the transient feature with the intrinsic structure mined. Considering the benefits of data-driven representation with time–frequency manifold (TFM) learning and model-driven representation with wavelet analysis, two time–frequency kernels with different principles are constructed for 2-dimensional convolutional sparse learning (CSL) in a fusion way of both data-driven and model-driven. From the perspective of image processing, the representation of desired transient structure features can be well sensed from time-frequency distribution (TFD) by those two dual-driven time–frequency kernels. In this manner, the desired defective intrinsic features can be mined, which is consistent with the physical dynamic response. In addition, image entropy is introduced to output the optimal TFM kernel and a series of inverse transform are applied to obtain the enhanced signal waveform. Simulated and experimental data are tested here to verify the creativity and effectiveness of the proposed DKCSL method, and a comparison with the traditional single TFM kernel-based sparse result and wavelet kernel-based sparse result are further provided, which deeply indicates the originality of our method that its potential in intrinsic structure feature extraction with dual-kernel sensing for bearing fault diagnosis.

An optimal and efficient data security technique through crypto-stegano for E-commerce.

E-Commerce or Electronic commerce is the buying and selling of goods and services in which any commercial transactions through wireless electronic devices such as hand-held computers (tablets), mobile phones or laptops is conducted anytime & anywhere via Internet technology. But, E-Commerce transactions or services are suffered by many attacks such as Man in the Middle attack, eavesdropping attacks, and etc. due to the lack of secured security infrastructure. Here, data security is one of the ways to keep the confidential information secure through E-Commerce transactions. In this connection, we have proposed an optimal and efficient data security with the combination of Elgamal cryptosystem and LSB image steganography technique for E-Commerce. In our proposed work, at the merchant side, Elgamal encryption technique is used to protect sensitive information during E-Commerce transactions from intruders and LSB image steganography process is also applied to hide generated Elgamal encrypted data and produce a stego-image (steganography image). Then, DCT (Discrete Cosine Transform) technique through autoencoder is imposed on stego-image to make an optimal image to increase the throughput of the work. After that, the produced optimal image with cipher text is sent to the customer end. At the customer end, first, stego-image is extracted from the optimal image using LSB retrieval process. Then, Elgamal decryption process is used to retrieve the original data and secure the E-Commerce transactions in efficiently. Based on the experiment, we have plotted the performance metrics such as MSE, PSNR and SSIM on the work and entropy of the optimal image is also calculated with respect to the sample image. Thereby, a high level performance metrics is obtained in our proposed work.

Decolorization based on the weighted combination of image entropy and canny edge retention ratio

Image decolorization is used to realize the color-to-gray conversion, which is widely used in black-and-white printing, digital-ink display, photo stylization, etc. Image contrast fidelity preservation is the key issue during this conversion process. We present a parametric model combining image entropy and the Canny edge retention ratio (CERR). Maximizing the image entropy keeps the global image contrast content, while maximizing the CERR enhances the local image contrast, mainly along the edges. The weighting parameter λ can be robustly estimated. Experimental results on Cadik’s and the COLOR250 datasets demonstrate that the model can achieve significant performance improvement over state-of-the-art methods both qualitatively and quantitatively.

Toward A No-reference Omnidirectional Image Quality Evaluation by Using Multi-perceptual Features

Compared to ordinary images, omnidirectional image (OI) usually has a broader view and a higher resolution, and image quality assessment (IQA) can help people to understand and improve their visual experience. However, the current IQA works cannot achieve good performance. To address this, we proposed a novel visual perception-based no-reference/blind omnidirectional image quality assessment (NR/B-OIQA) model. The gradient-based global structural features and gray-level co-occurrence matrix-based local structural features are combined together to highlight the rich quality-aware structural information. And a novel steganalysis real model-based color descriptor is extracted to reflect the color information that ignored in most IQA models. With a multi-scale visual perception, we take image entropy and the natural scene statistics features to convey the high-level semantics and quantify the unnaturalness of omnidirectional images. Finally, we apply support vector regression to predict the objective quality value based on the subjective scores and extracted all features. Experiments are conducted on OIQA and CVIQD2018 Databases, and the results illustrate that our model has more reliable performance and stronger competitiveness and receives better conformity with the subjective values.

A Hybrid Method of Frequency and Spatial Domain Techniques for TFT-LCD Circuits Defect Detection

Defect detection is a crucial but challenging task in thin film transistor liquid crystal display (TFT-LCD) manufacturing. Existing vision-based methods focus on either spatial domain or frequency domain with unsatisfactory detection. In view of that, this paper proposes a hybrid template matching method by drawing benefits from both frequency and spatial domain techniques. Under proposal, frequency domain template matching method and saliency detector method are firstly adopted separately to obtain two candidate frequency components associated with defects. In template matching process, a novel selection criterion is taken to improve identifying components associated with local spatial anomaly. Subsequently, the inverse Fourier transform is applied on the intersection of the two candidates to reconstruct the defect regions. In final steps, image entropy in the spatial domain is employed to filter out false detection regions to improve accuracy. To meet industry’s real-time inspection requirement, image partition and multi-threading calculation techniques are introduced into the proposed methodology. Experimental results have shown practical viability of the proposed approach to increase the yield rate of panels through robust defect detection in TFT-LCD manufacturing.

Optimized S-Curve Transformation and Wavelets-Based Fusion for Contrast Elevation of Breast Tomograms and Mammograms.

For the purpose of accuracy in detection and diagnosis, Computer-Aided Diagnosis (CAD) is preferred by radiologists for the analysis of Breast Cancer. However, the presence of noise, artifacts, and poor contrast in breast images during acquisition highlights the need for sophisticated enhancement techniques for the proper visualization of region-of-interest (ROI). In this work, contrast elevation of breast mammographic and tomographic images is performed with an improved S-Curve transform using the Particle Swarm Optimization (PSO) algorithm. The enhanced images are assessed using dedicated quality metrics such as the Enhancement Measure (EME) and Absolute Mean Brightness Error (AMBE) measurement. Although the enhancement techniques help in attaining better images, certain features relevant for diagnosis purposes are removed during the enhancement process, creating contradictions for radiological interpretation. Hence, to ensure the retention of diagnostic features from original breast tomograms and mammograms, a Discrete Wavelet Transform (DWT)-based fusion approach is incorporated, which fuses the original and contrast-enhanced images (with optimized s-curve transformation function) using the maximum fusion rule. The fusion performance is thereafter measured using the Image Quality Index (IQI), Standard Deviation (SD), and Entropy (E) as fusion metrics.

Demystifying neuroblastoma malignancy through fractal dimension, entropy, and lacunarity.

Neuroblastoma is a pediatric solid tumor with a prognosis associated with histology and age of the patient, which are the parameters of the well-established current classification (Shimada classification). Despite the development of new treatment options, the prognosis of high-risk neuroblastoma patients is still poor. Therefore, there is a continuous need to stratify the children suffering from this tumor. A mathematical and computational approach is proposed to enable automatic and precise cancer diagnosis on the histological slide. We targeted the complexity of neuroblastoma by calculating its image entropy (S), fractal dimension (FD), and lacunarity (λ) in a combined mathematical code. First, we tested the proposed method for patient-derived glioma images. It allowed distinguishing between normal brain tissue, grade II, and grade III glioma, which harbor different outcomes. In neuroblastoma, our analysis of image's FD, S, and λ combined with a machine learning algorithm automatically predicted tumor malignancy with a receiver operating characteristic curve of 0.82. FD, S, and λ distinguish between neuroblastoma and ganglioneuroma, but they only partially differentiate between the normal samples and the other classes. Ganglioneuroma, the most differentiated form, and poorly-differentiated neuroblastoma display different values of FD, S, and λ. FD, S, and λ of imaging recognize groups in neuroblastic tumors. We suggest that future studies including these features may challenge the current Shimada classification of neuroblastoma with categories of favorable and unfavorable histology. It is expected that this methodology could trigger multicenter studies and potentially find practical use in the clinical setting of children's hospitals worldwide.

EspEn Graph for the Spatial Analysis of Entropy in Images.

The quantification of entropy in images is a topic of interest that has had different applications in the field of agronomy, product generation and medicine. Some algorithms have been proposed for the quantification of the irregularity present in an image; however, the challenges to overcome in the computational cost involved in large images and the reliable measurements in small images are still topics of discussion. In this research we propose an algorithm, EspEn Graph, which allows the quantification and graphic representation of the irregularity present in an image, revealing the location of the places where there are more or less irregular textures in the image. EspEn is used to calculate entropy because it presents reliable and stable measurements for small size images. This allows an image to be subdivided into small sections to calculate the entropy in each section and subsequently perform the conversion of values to graphically show the regularity present in an image. In conclusion, the EspEn Graph returns information on the spatial regularity that an image with different textures has and the average of these entropy values allows a reliable measure of the general entropy of the image.

On the Image Reconstruction of Capacitively Coupled Electrical Resistance Tomography (CCERT) with Entropy Priors.

Regularization with priors is an effective approach to solve the ill-posed inverse problem of electrical tomography. Entropy priors have been proven to be promising in radiation tomography but have received less attention in the literature of electrical tomography. This work aims to investigate the image reconstruction of capacitively coupled electrical resistance tomography (CCERT) with entropy priors. Four types of entropy priors are introduced, including the image entropy, the projection entropy, the image-projection joint entropy, and the cross-entropy between the measurement projection and the forward projection. Correspondingly, objective functions with the four entropy priors are developed, where the first three are implemented under the maximum entropy strategy and the last one is implemented under the minimum cross-entropy strategy. Linear back-projection is adopted to obtain the initial image. The steepest descent method is utilized to optimize the objective function and obtain the final image. Experimental results show that the four entropy priors are effective in regularization of the ill-posed inverse problem of CCERT to obtain a reasonable solution. Compared with the initial image obtained by linear back projection, all the four entropy priors make sense in improving the image quality. Results also indicate that cross-entropy has the best performance among the four entropy priors in the image reconstruction of CCERT.

Improved Method Based on Retinex and Gabor for the Surface Defect Enhancement of Aluminum Strips

Aiming at the problems of the blurred image defect contour and the surface texture of the aluminum strip suppressing defect feature extraction when collecting photos online in the air cushion furnace production line, we propose an algorithm for the surface defect enhancement and detection of aluminum strips based on the Retinex theory and Gobar filter. The Retinex algorithm can enhance the information and detail part of the image, while the Gobar algorithm can maintain the integrity of the defect edges well. The method first improves the high-frequency information of the image using a multi-scale Retinex based on a Laplacian filter, scales the original image and the enhanced image, and enhances the contrast of the image by adaptive histogram equalization. Then, the image is denoised, and texture suppressed using median filtering and morphological operations. Finally, Gobar edge detection is performed on the obtained sample images by convolving the sinusoidal plane wave and the Gaussian kernel function in the null domain and performing double-threshold segmentation to extract and refine the edges. The algorithm in this paper is compared with histogram equalization and the Gaussian filter-based MSR algorithm, and the surface defects of aluminum strips are significantly enhanced for the background. The experimental results show that the information entropy of the aluminum strip material defect image is improved from 5.03 to 7.85 in the original image, the average gradient of the image is improved from 3.51 to 9.51 in the original image, the contrast between the foreground and background is improved from 16.66 to 117.53 in the original image, the peak signal-to-noise ratio index is improved to 24.50 dB, and the integrity of the edges is well maintained while denoising. This paper’s algorithm effectively enhances and detects the surface defects of aluminum strips, and the edges of defect contours are clearer and more complete.

A visual effect enhancement method of print advertisement based on Sobel operator filtering

Aiming at the problems of long enhancement time, low image entropy and poor visual effects of traditional methods, a method for enhancing the visual effects of plane advertisements based on Sobel operator filtering is proposed. Through DCT coefficient and target contour extraction algorithm, the edge contour of the flat advertisement image is accurately extracted, and the hyperspectral sensor is used to sparse the contour extraction result to achieve the image denoising effect. Finally, the Sobel operator filter is used to remove part of the interference in the image background, highlight the small targets in the image, and supplement the missing points in the image to achieve the enhancement of the visual effect of the print advertisement. Experimental results show that the proposed method can achieve image enhancement in a shorter time, and the image entropy value is relatively high, indicating that the method can retain a large amount of image detail information, and the subjective visual effect is better, in line with human visual standards, and sufficient verify the effectiveness of the method.

Detection of Meditation-Induced HRV Dynamics Using Averaging Technique-Based Oversampled Feature Set and Machine Learning Classifiers

In this paper, we propose a textural information-based analysis of scalogram image obtained from continuous wavelet transform of heart rate variability (HRV) signal to study its dynamics during meditation. In addition to features from scalogram image, visibility graph-based complexity measures and multiscale permutation entropies (MPEs) from HRV signal are used to elucidate the modulation in autonomic activity of heart during meditative and non-meditative state. Significant changes in the probability distribution of pixel intensities of scalogram image and undiminished permutation entropy at higher scales are observed during the meditative state. From the extracted features, we have selected the top-ranked features based on ReliefF algorithm and minimum threshold weight of importance set at 0.04. Considering the small sample size (12 subjects) of meditation dataset, we have employed a novel data augmentation technique based on averaging of feature sets to overcome the issue of overfitting. To examine the efficacy of the proposed technique, both the non-augmented and augmented data are applied to four different types of classifiers, namely k-nearest neighbor, support vector machine (SVM), logistic regression and random forest classifiers. Experimental results demonstrate that performance of classifiers in distinguishing meditative and pre-meditative state are much superior with the augmented data as compared to that with regular non-augmented data. Out of these classifiers, radial basis function (RBF)-based SVM results in the best performance with an average accuracy of 96.67%, sensitivity of 95.83% and specificity of 97.5%.

Asynchronous Generative Adversarial Network for Asymmetric Unpaired Image-to-Image Translation

The unpaired image-to-image translation aims to translate input images from one source domain to some desired outputs in a target domain by learning from unpaired training data. Cycle-consistency constraint provides a general principle to estimate and measure forward and backward mapping functions between two domains. In many cases, the information entropy of images from the two domains is not equal, resulting in an information-rich domain and an information-poor domain. However, existing solutions based on cycle-consistency either completely discard the information asymmetry between the two domains (a common choice), which leads to inferior translation performance for the asymmetric unpaired image-to-image translation, or have to rely on special task-specific designs and introduce extra loss components. These elaborative designs especially for the relatively harder translation direction from the information-poor domain to the information-rich domain (poor-to-rich translation) require extra labor and are limited to some specific tasks. In this paper, we propose a novel asynchronous generative adversarial network named Async-GAN, which provides a model-agnostic framework for easily turning symmetrical models into powerful asymmetric counterparts that can handle asymmetric unpaired image-to-image translation much better. The key innovation is to iteratively build gradually improving intermediate domains for generating pseudo paired training samples, which provide stronger full supervision for assisting the poor-to-rich translation. Extensive experiments on various asymmetric unpaired translation tasks demonstrate the superiority of the proposal. Furthermore, the proposed training framework could be extended to various Cycle-GAN solutions and achieve a performance gain.

Multislice Time-Frequency Image Entropy as a Feature for Railway Wheel Fault Diagnosis

Multislice Time-Frequency Image Entropy as a Feature for Railway Wheel Fault Diagnosis

Multiple Objects Automatic Detection of GPR Data Based on the AC-EWV and Genetic Algorithm

The automatic detection of multiple objects in ground penetrating radar (GPR) data is investigated by searching for the reflected hyperbolas of buried objects, which can reduce the subjectivity of operators and improve identification accuracy. Based on Frequency-wavenumber (F-K) migration, the accurate calculation of electromagnetic wave velocity (AC-EWV) is proposed by searching for the minimum image entropy of migrated radargrams. To avoid global searching, potential positions of object hyperbolas are selected from the binarized radargram through the vertical gray gradient searching, then the sub_window is extracted with the potential position as the center. The best fitting hyperbola is detected with the genetic algorithm (GA) in the sub_window, and objects are finally determined with five hyperbolic matching criteria and the auto-categorization. This technique is verified with the simulated and measured GPR data about rebars, pipelines, and voids, and results demonstrate that it achieves the average correct rate, average missed rate, and the average misjudged rate is 98.46%, 1.33%, and 0.36%, respectively, and the average correct rate for GPR data of the double-layer rebars is 91.67%.

ISAR Imaging for Maneuvering Targets via Fast Rotation Parameter Estimation

In inverse synthetic aperture radar (ISAR) imaging of maneuvering targets, traditional high-order phase compensation methods are usually limited by the heavy computational burden of parameter estimation, making it hard to apply in real-time cases. In this letter, an efficient ISAR motion compensation method is proposed based on fast parameter estimation. A novel analytic expression of the image entropy is derived with the help of a compensation matrix based on sinc function interpolation, which can eliminate the high-order phase term. Hence, the parameter estimation is transformed to an optimization problem where the gradient descent algorithm can be adopted to accelerate the computation speed. Compared with other recently proposed methods, our method is superior in high robustness and low computing cost. Experiments with simulated and real data have verified that without affecting the image quality, the computing time of our method can be reduced to about 1/4 of the traditional search algorithm.

Weak illumination image enhancement algorithm based on cyclic generation countermeasure network

To solve the problem of missing or distorted detail texture when manually adjusting image parameters, a weak illumination image enhancement algorithm based on cyclic generation game network is proposed. The image features are normalized by Gaussian distribution. Combined with homomorphic filtering theory and defogging operation, the image is generated and denoised according to the network brightness to enhance the weak illumination image. The experimental results show that after using this method to process the image, the image entropy increases by 6.8%, the contrast increases by 27.5%, and the noise content decreases by 24.1%. It has better contrast. It can not only meet the enhancement effect of weak light, but also ensure the details of the image, so that the image has richer details and good visual appearance.

Luminosity rectified blind Richardson-Lucy deconvolution for single retinal image restoration

Background and objectiveDue to imperfect imaging conditions, retinal images can be degraded by uneven/insufficient illumination, blurriness caused by optical aberrations and unintentional motions. Degraded images reduce the effectiveness of diagnosis by an ophthalmologist. To restore the image quality, in this research we propose the luminosity rectified Richardson-Lucy (LRRL) blind deconvolution framework for single retinal image restoration. MethodsWe established an image formation model based on the double-pass fundus reflection feature and developed a differentiable non-convex cost function that jointly achieves illumination correction and blind deconvolution. To solve this non-convex optimization problem, we derived the closed-form expression of the gradients and used gradient descent with Nesterov-accelerated adaptive momentum estimation to accelerate the optimization, which is more efficient than the traditional half quadratic splitting method. ResultsThe LRRL was tested on 1719 images from three public databases. Four image quality matrixes including image definition, image sharpness, image entropy, and image multiscale contrast were used for objective assessments. The LRRL was compared against the state-of-the-art retinal image blind deconvolution methods. ConclusionsOur LRRL corrects the problematic illumination and improves the clarity of the retinal image simultaneously, showing its superiority in terms of restoration quality and implementation efficiency. The MATLAB code is available on Github.