Rule-based soft computing for edge detection

In this paper, we present a robust rule-based edge detection method. Although generalized edge detection approaches are effective for most images they often fail in others. Thus the goal of our method is to provide more reliable edge detection results that are effective in most images. We implement the proposed method as follows: (1) transform RGB images to YCbCr format, (2) apply Sobel mask in four edge directions (horizontal, vertical, diagonal, anti-diagonal), (3) apply a bi-directional mask in four edge directions (horizontal–diagonal, vertical–diagonal, horizontal–anti-diagonal, vertical–anti-diagonal), and (4) detect rule-based edges by calculating membership degrees. Simulation results demonstrate that the proposed method is effective in most given images. We used three benchmarks approaches (Canny edge mask, high-pass filter, and Sobel mask) to compare the subjective performance quality.     

Detection of mitotic cells in breast cancer histopathological images using deep versus handcrafted features

One of the most important processes in the diagnosis of breast cancer, which is the leading mortality rate in women, is the detection of the mitosis stage at the cellular level. In literature, many studies have been proposed on the computer-aided diagnosis (CAD) system for detecting mitotic cells in breast cancer histopathological images. In this study, comparative evaluation of conventional and deep learning based feature extraction methods for automatic detection of mitosis in histopathological images are focused. While various handcrafted features are extracted with textural/spatial, statistical and shape-based methods in conventional approach, the convolutional neural network structure proposed on the deep learning approach aims to create an architecture that extracts the features of small cellular structures such as mitotic cells. Mitosis detection/counting is an important process that helps us assess how aggressive or malignant the cancer’s spread is. In the proposed study, approximately 180,000 non-mitotic and 748 mitotic cells are extracted for the evaluations. It is obvious that the classification stage cannot be performed properly due to the imbalanced numbers of mitotic and non-mitotic cells extracted from histopathological images. Hence, the random under-sampling boosting (RUSBoost) method is exploited to overcome this problem. The proposed framework is tested on mitosis detection in breast cancer histopathological images dataset provided from the International Conference on Pattern Recognition (ICPR) 2014 contest. In the results obtained with the deep learning approach, 79.42% recall, 96.78% precision and 86.97% F-measure values are achieved more successfully than handcrafted methods. A client/server-based framework has also been developed as a secondary decision support system for use by pathologists in hospitals. Thus, it is aimed that pathologists will be able to detect mitotic cells in various histopathological images more easily through necessary interfaces.

     

基于群智感知的街景变化检测方法

移动群智感知数据包含的图像和时空情境信息可用于检测街景图像变化,但是群智感知数据通常是低质和不规范的。为了准确检测街景发生的变化,主要解决由拍摄视角差异引起的数据低质问题。首先,针对大视差问题采用图像配准方法初步对齐图像并提取出配准特征点;然后,基于配准特征点分布从图像中提取感兴趣区域;随后,针对差值图像的误检内容,提出基于面积和多特征点的筛选法去除误检区域;最后,结合边缘检测和超像素分割算法提取完整的变化对象。与MDFNet方法进行比较,实验结果显示：当街景发生变化时,该方法的F1-measure值为55.8%,增长6%,错误率为10.8%,降低24%;当街景无变化时,该方法的错误率为2.8%,下降28%。     

Automatic nipple detection in breast thermograms

Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reduction in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decades, several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of interest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the analysis of medical images because it can be used in several applications, such as image registration and modality fusion. This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human body segmentation, determination of nipple candidates using adaptive thresholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.     

Forgery detection using feature-clustering in recompressed JPEG images

JPEG images are widely used in a large range of applications. The properties of JPEG compression can be used for detection of forgery in digital images. The forgery in JPEG images requires the image to be resaved thereby, re-compression of image. Therefore, the traces of recompression can be identified in order to detect manipulation. In this paper, a method to detect forgery in JPEG image is presented and an algorithm is designed to classify the image blocks as forged or non-forged based on a particular feature present in multi-compressed JPEG images. The method performs better than the previous methods which use the probability based approach for detecting forgery in JPEG images.     

A grid-density based technique for finding clusters in satellite image

High resolution and high dimensional satellite images cause problems for clustering methods due to clusters of different sizes, shapes and densities as they contain huge amount of data. Due to this reason, most algorithms for clustering satellite data sacrifice the correctness of their results for fast processing time. The processing time may be greatly influenced by the use of grids. In this paper, we propose a grid density based clustering method for detecting the clusters present in satellite images. The clustering is based on both the band values as well as the texture features in the satellite images. Experimental results are presented to establish the efficiency of this technique in detecting the clusters present in satellite images.     

Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm

Non-Hodgkin lymphoma is the most common cancer of the lymphatic system and should be considered as a group of several closely related cancers, which can show differences in their growth patterns, their impact on the body and how they are treated. The diagnosis of the different types of neoplasia is made by a specialist through the analysis of histological images. However, these analyses are complex and the same case can lead to different understandings among pathologists, due to the exhaustive analysis of decisions, the time required and the presence of complex histological features. In this context, computational algorithms can be applied as tools to aid specialists through the application of segmentation methods to identify regions of interest that are essential for lymphomas diagnosis. In this paper, an unsupervised method for segmentation of nuclear components of neoplastic cells is proposed to analyze histological images of lymphoma stained with hematoxylin-eosin. The proposed method is based on the association among histogram equalization, Gaussian filter, fuzzy 3-partition entropy, genetic algorithm, morphological techniques and the valley-emphasis method in order to analyze neoplastic nuclear components, improve the contrast and illumination conditions, remove noise, split overlapping cells and refine contours. The results were evaluated through comparisons with those provided by a specialist and techniques available in the literature considering the metrics of accuracy, sensitivity, specificity and variation of information. The mean value of accuracy for the proposed method was 81.48%. Although the method obtained sensitivity rates between 41% and 51%, the accuracy values showed relevance when compared to those provided by other studies. Therefore, the novelties presented here may already encourage new studies with a more comprehensive overview of lymphoma segmentation.     

ECM-aware cell-graph mining for bone tissue modeling and classification

Pathological examination of a biopsy is the most reliable and widely used technique to diagnose bone cancer. However, it suffers from both inter- and intra- observer subjectivity. Techniques for automated tissue modeling and classification can reduce this subjectivity and increases the accuracy of bone cancer diagnosis. This paper presents a graph theoretical method, called extracellular matrix (ECM)-aware cell-graph mining, that combines the ECM formation with the distribution of cells in hematoxylin and eosin stained histopathological images of bone tissues samples. This method can identify different types of cells that coexist in the same tissue as a result of its functional state. Thus, it models the structure-function relationships more precisely and classifies bone tissue samples accurately for cancer diagnosis. The tissue images are segmented, using the eigenvalues of the Hessian matrix, to compute spatial coordinates of cell nuclei as the nodes of corresponding cell-graph. Upon segmentation a color code is assigned to each node based on the composition of its surrounding ECM. An edge is hypothesized (and established) between a pair of nodes if the corresponding cell membranes are in physical contact and if they share the same color. Hence, multiple colored-cell-graphs coexist in a tissue each modeling a different cell-type organization. Both topological and spectral features of ECM-aware cell-graphs are computed to quantify the structural properties of tissue samples and classify their different functional states as healthy, fractured, or cancerous using support vector machines. Classification accuracy comparison to related work shows that the ECM-aware cell-graph approach yields 90.0% whereas Delaunay triangulation and the simple cell-graph approach achieves 75.0 and 81.1% accuracy, respectively.     

基于文本与图像的肺疾病研究与预测EI北大核心CSCD

通过对目前现有的肺癌检测技术研究,发现大部分研究人员主要针对肺癌(Computed tomography,CT)影像进行研究,忽略了电子病历所隐藏的肺癌信息,本文提出一种基于图像与文本相结合的肺癌分类方法,从现有的基于深度学习的肺癌图像分类出发,引入了电子病历信息,使用Multi-head attention以及(Bi-directional long short-term memory,Bi-LSTM)对文本建模.实验结果证明,将电子病历信息引入到图像分类模型之后,对模型的性能有进一步的提升.相对仅使用电子病历进行预测,准确率提升了大约14%,精确率大约提升了15%,召回率提升了14%.相对仅使用肺癌CT影像来进行预测,准确率提升了3.2%,精确率提升了4%,召回率提升了4%.     

Breast Mammogram Analysis and Classification Using Deep Convolution Neural Network

One of the fast-growing disease affecting women’s health seriously is breast cancer. It is highly essential to identify and detect breast cancer in the earlier stage. This paper used a novel advanced methodology than machine learning algorithms such as Deep learning algorithms to classify breast cancer accurately. Deep learning algorithms are fully automatic in learning, extracting, and classifying the features and are highly suitable for any image, from natural to medical images. Existing methods focused on using various conventional and machine learning methods for processing natural and medical images. It is inadequate for the image where the coarse structure matters most. Most of the input images are downscaled, where it is impossible to fetch all the hidden details to reach accuracy in classification. Whereas deep learning algorithms are high efficiency, fully automatic, have more learning capability using more hidden layers, fetch as much as possible hidden information from the input images, and provide an accurate prediction. Hence this paper uses AlexNet from a deep convolution neural network for classifying breast cancer in mammogram images. The performance of the proposed convolution network structure is evaluated by comparing it with the existing algorithms.     

Fovea center detection based on the retina anatomy and mathematical morphology

In this work, we present a new fovea center detection method for color eye fundus images. This method is based on known anatomical constraints on the relative locations of retina structures, and mathematical morphology. The detection of this anatomical feature is a prerequisite for the computer aided diagnosis of several retinal diseases, such as Diabetic Macular Edema. The proposed method is adaptive to local illumination changes, and it is robust to local disturbances introduced by pathologies in digital color eye fundus images (e.g. exudates). Our experimental results using the DRIVE image database indicate that our method is able to detect the fovea center in 37 out of 37 images (i.e. with a success rate of 100%). Using the DIARETDB1 database, our method was able to detect the fovea center in 92.13% of all tested cases (i.e. in 82 out of 89 images). These results indicate that our approach potentially can achieve a better performance than comparable methods proposed in the literature.     

一种新的背景预测方法在红外弱小目标检测中的应用

针对空中红外弱小目标的检测,提出了一种新的背景预测方法。该方法对云层边缘区域的点采用亮暗点分类,寻求最相似点的方法进行预测;对非边缘区域的点采用基本背景预测法进行预测;最后经过背景对消和阈值分割,将弱小目标检测出来。实验结果表明,该方法能够提高对起伏背景预测的准确性,减小由于云层边缘预测不准确而引起的虚警,从而能够更加有效地检测到弱小目标。     

多角度融合的RGB-D显著检测

显著检测是计算机视觉的重要组成部分,但大部分的显著检测工作着重于2D图像的分析,并不能很好地应用于RGB-D图片的显著检测。受互补的显著关系在2D图像检测中取得的优越效果的启发,并考虑RGB-D图像包含的深度特征,提出多角度融合的RGB-D显著检测方法。此方法主要包括三个部分,首先,构建颜色深度特征融合的图模型,为显著计算提供准确的相似度关系;其次,利用区域的紧密度进行全局和局部融合的显著计算,得到相对准确的初步显著图;最后,利用边界连接权重和流形排序进行背景和前景融合的显著优化,得到均匀平滑的最终显著图。在RGBD1000数据集上的实验对比显示,所提出的方法超越了当前流行的方法,表明多个角度互补关系的融合能够有效提高显著检测的准确率。     

Multiple source imagery and linear features for detection of urban expansion in Aqaba City,Jordan

Aqaba is one of the most strategic cities in Jordan and the entire region, as it is the only seaport for Jordan and has a special economic zone as the only window to global markets. The main purpose of this study is to detect urban development in Aqaba region by detecting and registering linear features in images with various geometric and radiometric properties taken at different times. This article used linear features for image registration that were chosen since they can be reliably extracted from imagery with significantly different geometric and radiometric properties. The modified iterated Hough transform (MIHT) is used as the matching strategy for automatically deriving an estimate of the parameters involved in the transformation function relating the images to be registered as well as the correspondence between conjugate lines. Derived edges from the registered images are used as the basis for change detection. The utilization of edges is motivated by the fact that they are invariant with respect to possible radiometric differences between the images in question. Linear features extraction, feature matching, image registration and pixel–pixel subtraction have been implemented using SPOT, Landsat, Ikonos and aerial photographs that have different radiometric, spatial and temporal resolutions. It has been shown that linear features (straight-line segments) have high semantics and can be reliably extracted from the images. These linear features can be used for accurate co-registration as an essential prerequisite for a reliable change detection procedure. For the purpose of change detection, image–image registration is more crucial than image–ground registration, where corresponding features in images are registered with respect to each other regardless of the associated absolute errors. The results illustrate that using edges as the base for change detection in urban areas is efficient and reliable.     

Road Detection and Tracking from Aerial Desert Imagery

We present a fast, robust road detection and tracking algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 96% of the images. We experimentally validated our algorithm on over a thousand aerial images obtained using our UAV. These images consist of straight and curved roads in various conditions with significant changes in lighting and intensity. We have also developed a road-tracking algorithm that searches a local rectangular area in successive images. Initial results are presented that shows the efficacy and the robustness of this algorithm. Using this road tracking algorithm we are able to further improve the road detection and achieve a 98% accuracy.     

Analysis of spatial distribution pattern of change-detection error caused by misregistration

Misregistration between multitemporal remotely sensed images is one of the significant sources of change-detection errors. In this study, spatial distribution of change-detection errors induced by misregistration was analysed quantitatively. First, multitemporal images are registered with different misregistration values measured by root mean square error (RMSE) from 0 to 1 pixels. The image differencing method, one of the most widely used change-detection methods, is then used to detect changes. Finally, the spatial distribution pattern of change-detection errors caused by misregistration is analysed using buffering analysis based on multitemporal image edges. Experimental results indicate that the commission errors caused by misregistration values from 0 to 1 pixels are almost always within 1 pixel of the edge, regardless of image resolution. In addition, the omission errors falling within 1 pixel of the edges are about 70% for medium-resolution images. The omission errors falling within 1 or 2 pixels of the edges for high-resolution images can be as much as 50% to 60%. This work improves the understanding of spatial distribution of change-detection errors caused by misregistration and shows the relations between these errors and image edges. Moreover, it is helpful for developing new methods by combining edge and spatial information to reduce the adverse effects of misregistration on change-detection.     

基于图像的城市场景垃圾自动检测

基于城市场景照片快速准确地自动检测垃圾在“智慧城管”等应用中具有重要的研究价值。城市垃圾在颜色纹理、几何形态上具有极大的多样性,甚至部分垃圾的认定具有一定的主观性,这给垃圾自动检测带来很大的挑战。文章提出了一种基于高速区域卷积神经网络的垃圾检测方法,通过使用数据融合、数据扩充、迁移学习等方法解决训练样本不足的问题,实现了城市场景图片中垃圾的自动、快速、准确检测。文章最后基于深圳市道路垃圾照片构建了一个包含多种形态类型垃圾的垃圾图片数据库,在该库中垃圾检测准确度高达89.07%。     

基于PCNN的灰度图像边缘检测方法

脉冲耦合神经网络(PCNN)最初由Eckhorn根据猫大脑中视觉皮层神经元的同步脉冲(SynchronousBurst)现象而提出。由于具有一系列良好的特性,PCNN在图像处理、模式识别等领域获得了广泛的应用。文献[6]根据PCNN的传播特性提出了一种利用PCNN检测二值图像边缘的有效方法,但这种方法并不能直接用于对灰度图像的边缘进行检测。由于实际处理的图像大部分为灰度图像,因而其方法的适用性是很有限的。该文提出了一种基于PCNN的灰度图像边缘检测方法,从而直接对256色灰度图像的边缘进行提取,具有较好的适用性。实验结果表明该方法是有效的。     

Robust global and local fuzzy energy based active contour for image segmentation

Though various image segmentation techniques have been developed, it is still a very challenging task to design a robust and efficient algorithm to segment (noisy, blurred or even discontinuous edged) images having high intensity inhomogeneity or non-homogeneity. In this article, a robust fuzzy energy based active contour, using both global and local information, is proposed to detect objects in a given image based on curve evolution. The local energy is generated by considering both local spatial and gray level/color information. The proposed model can better deal with images having high intensity inhomogeneity or non-homogeneity, noise and blurred boundary or discontinuous edges by incorporating local energy term in the proposed active contour energy function. The global energy term is used to avoid unsatisfactory results due to bad initialization. In this article, instead of solving the Euler–Lagrange equation, a level set based optimization is used for the convergence. We show a realization of the proposed method and demonstrate its performance (both qualitatively and quantitatively) with respect to state-of-the-art techniques on several images having such kind of artifacts. Analysis of results concludes that the proposed method can detect objects from given images in a better way than the existing ones.