Search

Low-light images have faded color, low color rates, and unclear image details. It significantly affects the performance of computer vision applications. Low-light image processing systems increase the color rate to restore the original image, and the color balance must be maintained for the image to be of high quality. In this paper, adaptive gamma and color correction (AGCC) is proposed as a method to enhance low-light images. The proposed model aims to enhance the color rates and balance of images to restore the original color in the image. It consists of three basic steps: calculate the adaptive gamma suitable for the lighting in the image, correct color, and starch color intensity over the histogram. Eight datasets containing images with diverse lighting conditions were employed to evaluate the proposed model's performance. The experimental results show that the proposed model archives outperform the state-of-the-art regarding computational simplicity, time complexity, and enhancement efficiency of the restored images. The model significantly improves processing time, retrieving images in an average of 0.09 Sec. from the evaluated datasets. Furthermore, it demonstrates a performance advantage exceeding 85% compared to methods in state-of-theart. [ABSTRACT FROM AUTHOR]

Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14 % increase), compared to working with the original images. [ABSTRACT FROM AUTHOR]

Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14% increase), compared to working with the original images.

Hematoxylin and eosin (H&E) stained colors is a critical step in the digitized pathological diagnosis of cancer. However, differences in section preparations, staining protocols and scanner specifications may result in the variations of stain colors in pathological images, which can potentially hamper the effectiveness of pathologist's diagnosis and the robustness. To alleviate this problem, several color normalization methods have been proposed. Most previous approaches map color information between images highly dependent on a reference template. However, due to the problem that pathological images are usually unpaired, these methods cannot produce satisfactory results. In this work, we propose an unsupervised color normalization method based on channel attention and long-range residual, using a technology called invertible neural networks (INN) to transfer the stain style while preserving the tissue semantics between different hospitals or centers, resulting in a virtual stained sample in the sense that no actual stains are used. In our method, the expert does not need to choose a template image. More specifically, we have developed a new unsupervised stain style transfer framework based on INN that is different from state-of-the-art methods. Meanwhile, we propose a new generator and a discriminator to further improve the performance. Our approach outperforms state-of-the-art methods both in objective metrics and subjective evaluations, yielding an improvement of 1.0 dB in terms of PSNR. Moreover, the amount of computation of the proposed network has been reduced by 33 %. This indicates that the inference speed is almost one third faster while the performance is better.

Outdoor images in sand-dust environments play an adverse role in various remote-based computer vision tasks because captured sand-dust images have severe color casts, low contrast, and poor visibility. However, although sand-dust image restoration is as important as haze removal and underwater image enhancement, it has not been sufficiently studied. In this paper, we present a novel color balance algorithm for sand-dust image enhancement. The aim of the proposed enhancement method is to obtain a coincident chromatic histogram. First, we introduce a pixel-adaptive color correction method using the mean and standard deviation of chromatic histograms. Pixels of each color component are adjusted based on the statistical characteristics of the green component. Second, a green-mean-preserving color normalization technique is presented. However, using the mean of red and blue components as the mean of the green can result in an undesirable output because the red or blue components of many sand-dust images have a narrow histogram with a high peak. To address this problem, we propose a histogram shifting algorithm that makes the red and blue histograms overlap the green histogram as much as possible. Based on this algorithm, bluish or reddish artifacts of the enhanced image can be reduced. Finally, image adjustment is exploited to improve the brightness of the sand-dust image. We performed intensive experiments for various sand-dust images and compared the performance of the proposed method with those of state-of-the-art enhancement methods. The simulation results indicate that the proposed enhancement scheme outperforms the existing approaches in terms of both subjective and objective qualities.

The color variation of hematoxylin and eosin (H&E)‐stained tissues has presented a challenge for applications of artificial intelligence (AI) in digital pathology. Many color normalization algorithms have been developed in recent years in order to reduce the color variation between H&E images. However, previous efforts in benchmarking these algorithms have produced conflicting results and none have sufficiently assessed the efficacy of the various color normalization methods for improving diagnostic performance of AI systems. In this study, we systematically investigated eight color normalization algorithms for AI‐based classification of H&E‐stained histopathology slides, in the context of using images both from one center and from multiple centers. Our results show that color normalization does not consistently improve classification performance when both training and testing data are from a single center. However, using four multi‐center datasets of two cancer types (ovarian and pleural) and objective functions, we show that color normalization can significantly improve the classification accuracy of images from external datasets (ovarian cancer: 0.25 AUC increase, p = 1.6 e‐05; pleural cancer: 0.21 AUC increase, p = 1.4 e‐10). Furthermore, we introduce a novel augmentation strategy by mixing color‐normalized images using three easily accessible algorithms that consistently improves the diagnosis of test images from external centers, even when the individual normalization methods had varied results. We anticipate our study to be a starting point for reliable use of color normalization to improve AI‐based, digital pathology‐empowered diagnosis of cancers sourced from multiple centers. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Many diseases are accompanied by changes in certain biochemical indicators called biomarkers in cells or tissues. A variety of biomarkers, including proteins, nucleic acids, antibodies, and peptides, have been identified. Tumor biomarkers have been widely used in cancer risk assessment, early screening, diagnosis, prognosis, treatment, and progression monitoring. For example, the number of circulating tumor cell (CTC) is a prognostic indicator of breast cancer overall survival, and tumor mutation burden (TMB) can be used to predict the efficacy of immune checkpoint inhibitors. Currently, clinical methods such as polymerase chain reaction (PCR) and next generation sequencing (NGS) are mainly adopted to evaluate these biomarkers, which are time-consuming and expansive. Pathological image analysis is an essential tool in medical research, disease diagnosis and treatment, functioning by extracting important physiological and pathological information or knowledge from medical images. Recently, deep learning-based analysis on pathological images and morphology to predict tumor biomarkers has attracted great attention from both medical image and machine learning communities, as this combination not only reduces the burden on pathologists but also saves high costs and time. Therefore, it is necessary to summarize the current process of processing pathological images and key steps and methods used in each process, including: (1) pre-processing of pathological images, (2) image segmentation, (3) feature extraction, and (4) feature model construction. This will help people choose better and more appropriate medical image processing methods when predicting tumor biomarkers. [ABSTRACT FROM AUTHOR]

The popularity of digital histopathology is growing rapidly in the development of computer aided disease diagnosis systems. However, the color variations due to manual cell sectioning and stain concentration make the process challenging in various digital pathological image analysis such as histopathological image segmentation and classification. Hence, the normalization of these variations are needed to obtain the promising results. The proposed research intends to introduce a reliable and robust new complete color normalization method, addressing the problems of color and stain variability. The new complete color normalization involves three phases, namely enhanced fuzzy illuminant normalization, fuzzy-based stain normalization, and modified spectral normalization. The extensive simulations are performed and validated on histopathological images. The presented algorithm outperforms the existing conventional normalization methods by overcoming the certain limitations and challenges. As per the experimental quality metrics and comparative analysis, the proposed algorithm performs efficiently and provides promising results. [ABSTRACT FROM AUTHOR]

Many diseases are accompanied by changes in certain biochemical indicators called biomarkers in cells or tissues. A variety of biomarkers, including proteins, nucleic acids, antibodies, and peptides, have been identified. Tumor biomarkers have been widely used in cancer risk assessment, early screening, diagnosis, prognosis, treatment, and progression monitoring. For example, the number of circulating tumor cell (CTC) is a prognostic indicator of breast cancer overall survival, and tumor mutation burden (TMB) can be used to predict the efficacy of immune checkpoint inhibitors. Currently, clinical methods such as polymerase chain reaction (PCR) and next generation sequencing (NGS) are mainly adopted to evaluate these biomarkers, which are time-consuming and expansive. Pathological image analysis is an essential tool in medical research, disease diagnosis and treatment, functioning by extracting important physiological and pathological information or knowledge from medical images. Recently, deep learning-based analysis on pathological images and morphology to predict tumor biomarkers has attracted great attention from both medical image and machine learning communities, as this combination not only reduces the burden on pathologists but also saves high costs and time. Therefore, it is necessary to summarize the current process of processing pathological images and key steps and methods used in each process, including: (1) pre-processing of pathological images, (2) image segmentation, (3) feature extraction, and (4) feature model construction. This will help people choose better and more appropriate medical image processing methods when predicting tumor biomarkers.

With the advent of computer-assisted diagnosis (CAD), the accuracy of cancer detection from histopathology images is significantly increased. However, color variation in the CAD system is inevitable due to the variability of stain concentration and manual tissue sectioning. The small variation in color may lead to the misclassification of cancer cells. Therefore, color normalization is a very much essential step prior to segmentation and classification in order to reduce the inter-variability of background color among a set of source images. In this paper, a novel color normalization method is proposed for Hematoxylin and Eosin stained histopathology images. Conventional Reinhard algorithm is modified in our proposed method by incorporating fuzzy logic. Moreover, mathematically, it is proved that our proposed method satisfies all three hypotheses of color normalization. Furthermore, several quality metrics are estimated locally for evaluating the performance of various color normalization methods. The experimental result reveals that our proposed method has outperformed all other benchmark methods.

In this paper, a five phase model is proposed for early detection of communicable and non-communicable diseases like Haemoprotozoan and breast cancer using pathology images. At first, color normalization technique is utilized to improve the visual quality of the collected histology images. Next, edge boost curve transform is employed to segment nuclei and non-nuclei cells from the enhanced images. The developed segmentation methodology delivers good results in overlapped database. Further, the segmented image is converted into one dimensional vectors and then modified reliefF algorithm is applied to choose the active feature vectors to achieve better classification. Finally, deep neural network is accomplished to classify the Haemoprotozoan images as anaplasmosis, babesiosis and theileriosis, and breast images as malignant or benign. From the experimental result, the proposed model; modified reliefF-deep neural network obtained maximum classification accuracy of 97.6% in Haemoprotozoan disease detection and 95.94% in breast cancer detection, which are better related to other comparative techniques like Random Forest, Multi Support Vector Machine and K-Nearest Neighbor. [ABSTRACT FROM AUTHOR]

One of the foremost and challenging tasks in hematoxylin and eosin stained histological image analysis is to reduce color variation present among images, which may significantly affect the performance of computer-aided histological image analysis. In this regard, the paper introduces a new rough-fuzzy circular clustering algorithm for stain color normalization. It judiciously integrates the merits of both fuzzy and rough sets. While the theory of rough sets deals with uncertainty, vagueness, and incompleteness in stain class definition, fuzzy set handles the overlapping nature of histochemical stains. The proposed circular clustering algorithm works on a weighted hue histogram, which considers both saturation and local neighborhood information of the given image. A new dissimilarity measure is introduced to deal with the circular nature of hue values. Some new quantitative measures are also proposed to evaluate the color constancy after normalization. The performance of the proposed method, along with a comparison with other state-of-the-art methods, is demonstrated on several publicly available standard data sets consisting of hematoxylin and eosin stained histological images. [ABSTRACT FROM AUTHOR]

The advent of whole slide imaging has brought advanced computer-aided diagnosis via medical imaging and artificial intelligence technologies in digital pathology. The examination of tissue samples through whole slide imaging is commonly used to diagnose cancerous diseases, but the analysis of histopathology images through a decision support system is not always accurate due to variations in color caused by different scanning equipment, staining methods, and tissue reactivity. These variabilities decrease the accuracy of computer-aided diagnosis and affect the diagnosis of pathologists. In this context, an effective stain normalization method has proved as a powerful tool to standardize different color appearances and minimize color variations in histopathology images. This study reviews different stain normalization methods highlighting the main methodologies, contributions, advantages, and limitations of correlated works. The state-of-the-art methods are grouped into four distinct categories. Next, we select ten representative methods from the groups and conduct an experimental comparison to investigate the strengths and weaknesses of different methods and rank them according to selected performance accuracy measures. The quality performances of selected methods are compared in terms of quaternion structure similarity index metric, structural similarity index metric, and Pearson correlation coefficient conducting experiments on three histopathological image datasets. Our findings conclude that the structure-preserving unified transformation-based methods consistently outperform the state-of-the-art methods by improving robustness against variability and reproducibility. The comparative analysis we conducted in this paper will serve as the basis for future research, which will help to refine existing techniques and develop new approaches to address the complexities of stain normalization in complex histopathology images. • A comprehensive review of stain color normalization techniques for whole slide image analysis. • A detailed study about strengths and limitations of published works indicating possible future research. • Quantitative and comparative analysis of ten selected methods and their effectiveness in digital pathology. [ABSTRACT FROM AUTHOR]

Image analysis tools for cancer, such as automatic nuclei segmentation, are impacted by the inherent variation contained in pathology image data. Convolutional neural networks (CNN), demonstrate success in generalizing to variable data, illustrating great potential as a solution to the problem of data variability. In some CNN-based segmentation works for digital pathology, authors apply color normalization (CN) to reduce color variability of data as a preprocessing step prior to prediction, while others do not. Both approaches achieve reasonable performance and yet, the reasoning for utilizing this step has not been justified. It is therefore important to evaluate the necessity and impact of CN for deep learning frameworks, and its effect on downstream processes. In this paper, we evaluate the effect of popular CN methods on CNN-based nuclei segmentation frameworks.

One of the main obstacles for the implementation of deep convolutional neural networks (DCNNs) in the clinical pathology workflow is their low capability to overcome variability in slide preparation and scanner configuration, that leads to changes in tissue appearance. Some of these variations may not be not included in the training data, which means that the models have a risk to not generalize well. Addressing such variations and evaluating them in reproducible scenarios allows understanding of when the models generalize better, which is crucial for performance improvements and better DCNN models. Staining normalization techniques (often based on color deconvolution and deep learning) and color augmentation approaches have shown improvements in the generalization of the classification tasks for several tissue types. Domain-invariant training of DCNN's is also a promising technique to address the problem of training a single model for different domains, since it includes the source domain information to guide the training toward domain-invariant features, achieving state-of-the-art results in classification tasks. In this article, deep domain adaptation in convolutional networks (DANN) is applied to computational pathology and compared with widely used staining normalization and color augmentation methods in two challenging classification tasks. The classification tasks rely on two openly accessible datasets, targeting Gleason grading in prostate cancer, and mitosis classification in breast tissue. The benchmark of the different techniques and their combination in two DCNN architectures allows us to assess the generalization abilities and advantages of each method in the considered classification tasks. The code for reproducing our experiments and preprocessing the data is publicly available1. Quantitative and qualitative results show that the use of DANN helps model generalization to external datasets. The combination of several techniques to manage color heterogeneity suggests that several methods together, such as color augmentation methods with DANN training, can generalize even further. The results do not show a single best technique among the considered methods, even when combining them. However, color augmentation and DANN training obtain most often the best results (alone or combined with color normalization and color augmentation). The statistical significance of the results and the embeddings visualizations provide useful insights to design DCNN that generalizes to unseen staining appearances. Furthermore, in this work, we release for the first time code for DANN evaluation in open access datasets for computational pathology. This work opens the possibility for further research on using DANN models together with techniques that can overcome the tissue preparation differences across datasets to tackle limited generalization.

Computational image analysis is one means for evaluating digitized histopathology specimens that can increase the reproducibility and reliability with which cancer diagnoses are rendered while simultaneously providing insight as to the underlying mechanisms of disease onset and progression. A major challenge that is confronted when analyzing samples that have been prepared at disparate laboratories and institutions is that the algorithms used to assess the digitized specimens often exhibit heterogeneous staining characteristics because of slight differences in incubation times and the protocols used to prepare the samples. Unfortunately, such variations can render a prediction model learned from one batch of specimens ineffective for characterizing an ensemble originating from another site. In this work, we propose to adopt unsupervised domain adaptation to effectively transfer the discriminative knowledge obtained from any given source domain to the target domain without requiring any additional labeling or annotation of images at the target site. In this paper, our team investigates the use of two approaches for performing the adaptation: (1) color normalization and (2) adversarial training. The adversarial training strategy is implemented through the use of convolutional neural networks to find an invariant feature space and Siamese architecture within the target domain to add a regularization that is appropriate for the entire set of whole-slide images. The adversarial adaptation results in significant classification improvement compared with the baseline models under a wide range of experimental settings.

• We propose an approach that associates color normalization with percolation features. • The method was applied in colorectal and breast histological images. • Relevant AUC rates were obtained for classifying malignant and benign tumor images. • Color normalization improved the results obtained for colorectal images. • We evaluate the effect of local and global percolation features on each dataset. Percolation is a fractal descriptor that has been applied recently on computer vision problems. We applied this descriptor on 58 colored histological breast images, and 165 colored histological colorectal images, both stained with Hematoxylin and Eosin, in order to extract features to differentiate between benign and malignant cases. The experiments were also performed over normalized images, aiming to analyze the influence of different color normalization techniques on percolation-based features and whether they can provide better classification results. The feature sets obtained from the application of the method on the original images and on the normalized images with three different techniques were tested using 12 different classifiers. We compared the obtained results with other relevant methods in the area and observed significant contributions, with AUC rates above 0.900 in both normalized and non-normalized images. We also verified that color normalization does not contribute to the classification of breast tumors when associated with percolation features. However, color normalized images from the colorectal tumor's dataset provided better results than the original images. [ABSTRACT FROM AUTHOR]

Highlights • A novel color normalization method for H&E-stained WSIs is proposed. • The color appearance of the normalization is very consistent. • Both structure and color artifacts can be effectively avoided. • The method only involves pixel-wise operation and can be solved in 3 second. Abstract Background and Objective Color consistency of histological images is significant for developing reliable computer-aided diagnosis (CAD) systems. However, the color appearance of digital histological images varies across different specimen preparations, staining, and scanning situations. This variability affects the diagnosis and decreases the accuracy of CAD approaches. It is important and challenging to develop effective color normalization methods for digital histological images. Methods We proposed a novel adaptive color deconvolution (ACD) algorithm for stain separation and color normalization of hematoxylin-eosin-stained whole slide images (WSIs). To avoid artifacts and reduce the failure rate of normalization, multiple prior knowledges of staining are considered and embedded in the ACD model. To improve the capacity of color normalization for various WSIs, an integrated optimization is designed to simultaneously estimate the parameters of the stain separation and color normalization. The solving of ACD model and application of the proposed method involves only pixel-wise operation, which makes it very efficient and applicable to WSIs. Results The proposed method was evaluated on four WSI-datasets including breast, lung and cervix cancers and was compared with 6 state-of-the-art methods. The proposed method achieved the most consistent performance in color normalization according to the quantitative metrics. Through a qualitative assessment for 500 WSIs, the failure rate of normalization was 0.4% and the structure and color artifacts were effectively avoided. Applied to CAD methods, the area under receiver operating characteristic curve for cancer image classification was improved from 0.842 to 0.914. The average time of solving the ACD model is 2.97 s. Conclusions The proposed ACD model has prone effective for color normalization of hematoxylin-eosin-stained WSIs in various color appearances. The model is robust and can be applied to WSIs containing different lesions. The proposed model can be efficiently solved and is effective to improve the performance of cancer image recognition, which is adequate for developing automatic CAD programs and systems based on WSIs. [ABSTRACT FROM AUTHOR]

Color disagreement among histological images may affect the performance of computeraided histological image analysis. So, one of the most important and challenging tasks in histological image analysis is to diminish the color variation among the images, maintaining the histological information contained in them. In this regard, the paper proposes a new circular clustering algorithm, termed as rough-fuzzy circular clustering. It integrates judiciously the merits of rough-fuzzy clustering and cosine distance. The rough-fuzzy circular clustering addresses the uncertainty due to vagueness and incompleteness in stain class definition, as well as overlapping nature of multiple contrasting histochemical stains. The proposed circular clustering algorithm incorporates saturation-weighted hue histogram, which considers both saturation and hue information of the given histological image. The efficacy of the proposed method, along with a comparison with other state-of-the-art methods, is demonstrated on publicly available hematoxylin and eosin stained fifty-eight benchmark histological images. [ABSTRACT FROM AUTHOR]

Outdoor images are often degraded by aerosols suspending in atmosphere in bad weather conditions like haze. To cope with this phenomenon, researchers have proposed many approaches and single image based techniques draw attention mostly. Recently, a fusion-based strategy achieves good results, which derives two enhanced images from single image and blends them to recover haze-free image. However, there are still some deficiencies in the fusion-input images and weight maps, which leads their restoration less natural. In this paper, we propose a multi-scale fusion scheme for single image dehazing. We first use an adaptive color normalization to eliminate a common phenomenon, color distortion, in haze condition. Then two enhanced images, including our newly presented local detail enhanced image, are derived to be blended. Thereafter, five haze-relevant features of dark channel, clarity, saliency, luminance and chromatic are investigated since those can serve as weight maps for fusion. Dark channel, clarity and saliency features are finally selected due to their expression abilities and less interconnection. The fusion is processed with a pyramid strategy layer-by-layer. The multi-scale blended images are combined in a bottom-up manner. At last quantitative experiments demonstrate that our approach is effectiveness and yields better results than other methods. [ABSTRACT FROM AUTHOR]

Microscopic analyses of tissue samples are crucial for confirming the diagnosis of breast cancer. The digitization of these samples has led to the development of computational systems that can assist pathologists. However, these systems may face limitations owing to color variations in the images. Normalization studies have been widely conducted to address these issues, but there is still a need for new proposals that take into account the biological properties of dyes and tissues. This study presents a novel method for normalizing hematoxylin and eosin-stained histological images by estimating the color appearance matrices and density maps of the stain. The proposed method offers contributions in terms of pixel selection and weight definition to improve the color estimation of histological images. Besides, to the best of our knowledge, no previous studies have evaluated normalized images considering both handcrafted and learning features. Breast cancer images with significant color variations were used to evaluate this approach and the results demonstrated its effectiveness and efficiency. The average values of FSIM, NIQE, and QSSIM were up to 0.9866, 3.4298, and 0.9655, respectively. Compared with other normalization techniques, the proposed method showed an increase of up to 5.9261, with the largest difference observed in the amount of noise added, as indicated by the NIQE metric. To determine the impact of normalization on feature extraction, the evaluations included an analysis of both color and deep-learned features. These experiments showed that all evaluated methods harmed the separation of breast cancer samples by color features. In contrast, the deep-learned features resulted in less complex classification problems, especially with the proposed normalization. This technique also reached one of the lowest processing times, nearly 6 s with the largest image from the databases. • We present a normalization method of H&E breast cancer histological images. • The proposed spectral matching is based on biological and stain properties. • The stain estimation used region selection, sparsity estimation and preprocessing. • Public breast cancer images were evaluated by their colors and features. • The performed analyses demonstrate the contribution of the proposed normalization. • Future works are necessary for a better representation of eosin. [ABSTRACT FROM AUTHOR]

The estimation of nutrient content of plants is considerably important in agricultural practices, especially in enabling the application of precision farming. A plethora of methods has been used to estimate nitrogen amount in plants, including the utilization of computer vision. However, most of the image-based nitrogen estimation methods are conducted in controlled environments. These methods are not so practical, time consuming, and require many equipment. Therefore, there is a crucial need to develop a method to estimate nitrogen content of plants based on leaves images captured on field. It is a very challenging task since the intensity of sunlight is always changing and this leads to an inconsistent image capturing problem. In this paper, we develop a low-cost, simple, and accurate approach image-based nitrogen amount estimation. Plant images are captured directly under sunlight by using a conventional digital camera and are subject to a variation in lighting conditions. We propose a color constancy method using neural networks fusion and a genetic algorithm to normalize various plant images due to different sunlight intensities. A Macbeth color checker is utilized as the reference to normalize the color of the images. We also develop a combination of neural networks using a committee machine to estimate the nitrogen content in wheat leaves. Twelve statistical RGB color features are used as the input parameters for the nutrient estimation. The obtained result shows considerable better performance than the conventional gray-world and scale-by-max approaches, as well as linear model and single neural network methods. Finally, we show that our nutrient estimation approach is superior to the commonly used soil-plant analysis development meter based prediction. [ABSTRACT FROM PUBLISHER]

Staining and scanning of tissue samples for microscopic examination is fraught with undesirable color variations arising from differences in raw materials and manufacturing techniques of stain vendors, staining protocols of labs, and color responses of digital scanners. When comparing tissue samples, color normalization and stain separation of the tissue images can be helpful for both pathologists and software. Techniques that are used for natural images fail to utilize structural properties of stained tissue samples and produce undesirable color distortions. The stain concentration cannot be negative. Tissue samples are stained with only a few stains and most tissue regions are characterized by at most one effective stain. We model these physical phenomena that define the tissue structure by first decomposing images in an unsupervised manner into stain density maps that are sparse and non-negative. For a given image, we combine its stain density maps with stain color basis of a pathologist-preferred target image, thus altering only its color while preserving its structure described by the maps. Stain density correlation with ground truth and preference by pathologists were higher for images normalized using our method when compared to other alternatives. We also propose a computationally faster extension of this technique for large whole-slide images that selects an appropriate patch sample instead of using the entire image to compute the stain color basis. [ABSTRACT FROM AUTHOR]