小麦冠层图像H分量的K均值聚类分割

大田环境下小麦冠层图像具有光照不均匀、背景复杂及阴影遮挡等特点,经典图像分割算法存在精度低、过分割等问题,提出一种基于HSI空间下H分量的K均值聚类算法。使用[R+G-B]归一化处理RGB空间下的彩色图像,以抑制其B分量;将归一化图像进行RGB到HSI的颜色空间转化;根据光照是否均匀,使用K均值聚类算法对彩色图像的H分量进行不同的聚类处理,经形态学开运算及去噪处理获得最终目标图像。实验表明,该方法对不同施氮量、不同光照、不同生长时期小麦冠层图像的分割效果较好,相对基于Lab空间的K-means聚类分割,该方法可一定程度避免过分割现象;相对基于H分量的Otsu算法,对光照不均匀图像分割更完整,对复杂背景图像分割更精确。     

图像灰度密度分布计算模型及肺结节良恶性分类

提出一种基于密度分布的特征评估算法,同时引入模式识别模型来评估该方法的效率。首先,从肺部肿瘤图像中随机提取像素块集,通过K-均值聚类算法将其分为10类,根据CT图像中肺结节像素值和聚类中心的关系,提取出10维特征向量,利用随机森林分类器进行模型训练,进而判断肺结节良恶性水平。通过CT图像公开数据集LIDC-IDRI实验表明分类平均精度达到0.900 8。实验结果对比分析表明,提出的特征表达方法具有更优的分类效果和更高的鲁棒性。     

Efficient iris segmentation method in unconstrained environments

Recently, iris recognition systems have gained increased attention especially in non-cooperative environments. One of the crucial steps in the iris recognition system is the iris segmentation because it significantly affects the accuracy of the feature extraction and iris matching steps. Traditional iris segmentation methods provide excellent results when iris images are captured using near infrared cameras under ideal imaging conditions, but the accuracy of these algorithms significantly decreases when the iris images are taken in visible wavelength under non-ideal imaging conditions. In this paper, a new algorithm is proposed to segments iris images captured in visible wavelength under unconstrained environments. The proposed algorithm reduces the error percentage even in the presence of types of noise include iris obstructions and specular reflection. The proposed algorithm starts with determining the expected region of the iris using the K-means clustering algorithm. The Circular Hough Transform (CHT) is then employed in order to estimate the iris radius and center. A new efficient algorithm is developed to detect and isolate the upper eyelids. Finally, the non-iris regions are removed. Results of applying the proposed algorithm on UBIRIS iris image databases demonstrate that it improves the segmentation accuracy and time.     

An improved K-means algorithm for underwater image background segmentation

Conventional algorithms fail to obtain satisfactory background segmentation results for underwater images. In this study, an improved K-means algorithm was developed for underwater image background segmentation to address the issue of improper K value determination and minimize the impact of initial centroid position of grayscale image during the gray level quantization of the conventional K-means algorithm. A total of 100 underwater images taken by an underwater robot were sampled to test the aforementioned algorithm in respect of background segmentation validity and time cost. The K value and initial centroid position of grayscale image were optimized. The results were compared to the other three existing algorithms, including the conventional K-means algorithm, the improved Otsu algorithm, and the Canny operator edge extraction method. The experimental results showed that the improved K-means underwater background segmentation algorithm could effectively segment the background of underwater images with a low color cast, low contrast, and blurred edges. Although its cost in time was higher than that of the other three algorithms, it none the less proved more efficient than the time-consuming manual segmentation method. The algorithm proposed in this paper could potentially be used in underwater environments for underwater background segmentation.

     

基于RGB-D融合特征的图像分类

当前经典的图像分类算法大多是基于RGB图像或灰度图像,并没有很好地利用物体或场景的深度信息,针对这个问题,提出了一种基于RGB-D融合特征的图像分类方法。首先,分别提取RGB图像dense SIFT局部特征与深度图Gist全局特征,然后将得到的两种图像特征进行特征融合;其次,使用改进K-means算法对融合特征建立视觉词典,克服了传统K-means算法过度依赖初始点选择的问题,并在图像表示阶段引入LLC稀疏编码对融合特征与其对应的视觉词典进行稀疏编码;最后,利用线性SVM进行图像分类。实验结果表明,所提出的算法能有效地提高图像分类的精度。     

A non-invasive methodology for the grade identification of astrocytoma using image processing and artificial intelligence techniques

Brain tumor grade identification is an invasive technique and clinicians rely on biopsy and spinal tap method. The proposed method takes an effort to develop a non-invasive method for the tumor grade (Low/High) identification using magnetic resonant images. The process involves preprocessing, image segmentation, tumor isolation, feature extraction, feature selection and classification. An analysis on the performance of the segmentation techniques, feature extraction methods, automatic feature selection (SFLA) and constructed classifiers (support vector machines, learning vector quantization and Naives Bayes) is done on the basis of accuracy, efficiency and elapsed time. This analysis motivates towards the accurate determination of tumor grade from MR images instead of depending on magnetic resonant spectroscopy and biopsy. Fuzzy c-means segmentation outperformed other segmentation techniques, shape and size based textural feature promoted the demarcation of tumor grades, Naive Bayes classifier succeeded in terms of efficiency, error and elapse time when compared with SVM and LVQ. The study was carried out with 200 images consisting training set (164 images) and testing set (36 images). The results revealed that the system is robust and accurate (91%), consumed less time in grade identification, an alternative for biopsy and MRS in the brain tumor grade identification diagnosis procedure.     

图像处理技术在赤潮生物自动识别中的应用

根据赤潮生物显微图像的特点，研究图像的预处理、分割和特征提取的处理过程．通过与其他自动分割方法进行比较，证明采用二维最大熵法可以有效地进行赤潮生物图像的自动阈值分割，并结合轮廓分析法和纹理分析法对于赤潮生物图像进行特征提取．实验结论表明，与人工识别计数方式比对，识别符合率大于80％。     

Performance Analysis of Breast Cancer Detection Method Using ANFIS Classification Approach

Breast cancer is one of the deadly diseases prevailing in women. Earlier detection and diagnosis might prevent the death rate. Effective diagnosis of breast cancer remains a significant challenge, and early diagnosis is essential to avoid the most severe manifestations of the disease. The existing systems have computational complexity and classification accuracy problems over various breast cancer databases. In order to overcome the above-mentioned issues, this work introduces an efficient classification and segmentation process. Hence, there is a requirement for developing a fully automatic methodology for screening the cancer regions. This paper develops a fully automated method for breast cancer detection and segmentation utilizing Adaptive Neuro Fuzzy Inference System (ANFIS) classification technique. This proposed technique comprises preprocessing, feature extraction, classifications, and segmentation stages. Here, the wavelet-based enhancement method has been employed as the preprocessing method. The texture and statistical features have been extracted from the enhanced image. Then, the ANFIS classification algorithm is used to classify the mammogram image into normal, benign, and malignant cases. Then, morphological processing is performed on malignant mammogram images to segment cancer regions. Performance analysis and comparisons are made with conventional methods. The experimental result proves that the proposed ANFIS algorithm provides better classification performance in terms of higher accuracy than the existing algorithms.     

改进FCM和LFP相结合的白细胞图像分类

研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率.由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法.应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题.对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法.运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93％.     

基于改进CNN的宫颈细胞自动分类算法

本文采用深度学习算法中的卷积神经网络对细胞图像进行识别, 实现对宫颈细胞图像的自动分类. 首先对宫颈细胞进行预处理, 通过细胞核裁剪解决图像输入尺寸不一的问题, 对图像进行翻转平移, 对数据集进行扩充, 并解决样本量不均衡的问题; 接着选取VGG-16网络进行改进, 使用改进后的VGG-16网络进行特征提取, 以及细胞分类; 并采用迁移学习的方法加载预训练网络参数, 进而加快参数收敛速度, 提高分类准确率; 最终通过对网络的训练, 得到了较好的分类结果, 将分类结果与人工提取特征设计分类器的方法相比, 分类的准确率有所提高, 二分类的准确率达97.3%, 七分类的准确率达89%. 实验结果表明: 卷积神经网络对宫颈细胞图像进行自动分类, 分类准确率相比较人工提取特征分类器效果较好, 且分类结果不受分割图像准确率的影响.     

Species classification of aquatic plants using PSVM and ANFIS

This work presents a method for plant species identification using the images of flowers. It focuses on the stable feature extraction of flowers such as color, texture and shape features in addition to fractal dimension. Color based segmentation using K-means clustering and active contour model is used to extract the color features. Texture segmentation using texture filter is used to segment the image and obtain texture features. Sobel, Prewitt and Robert operators are used to extract the boundary of image and to obtain the shape features. Classification of the plants is done using Proximal Support Vector Machine (PSVM) and Adaptive Neuro Fuzzy Inference System (ANFIS) classifiers.     

基于K-均值与蚁群混合聚类的图像分割

针对单一聚类算法在图像分割中容易陷人局部最优或有过分割现象,造成分割精确度低等问题,文章提出了基于K-均值聚类和蚁群聚类相结合的新算法.新算法先将K-均值算法作快速分类,根据K-均值分类结果更新蚂蚁各路径上的信息素,指导其他蚂蚁选择,以提高蚁群聚类算法的运行效率.实验结果证明,新算法在图像分割处理的精确度上较单一的K均...     

Image segmentation using fuzzy competitive learning based counter propagation network

Image segmentation is the method of partitioning an image into some homogenous regions that are more meaningful for its better understanding and examination. Soft computing methods having the capabilities of achieving artificial intelligence are predominately used to perform the task of segmentation. Due to the variability and the uncertainty present in natural scenes, segmentation is a complicated task to perform with the help of conventional image segmentation techniques. Therefore, in this article a hybrid Fuzzy Competitive Learning based Counter Propagation Network (FCPN) is proposed for the segmentation of natural scene images. This method compromises of the uncertainty handling capabilities of the fuzzy system and proficiency of parallel learning ability of neural network. To identify the number of clusters automatically in less computational time, the instar layer of Counter propagation network (CPN) has been trained by using Fuzzy competitive learning (FCL). The outstar layer of counter propagation network is trained by using Grossberg learning for obtaining the desired output. Region growing method having the tendency to correctly identify edges with simplicity is used for initial seed point selection. Then, the most similar regions in the image are clustered and the number of clusters is estimated automatically. Finally, by identifying the cluster centers the images are segmented. Bacterial foraging algorithm is used to initialize the initial weights to the network, which helps the proposed method in achieving low convergence ratio with higher accuracy. Results validated the higher performance of proposed FCPN method when compared with other states-of-the-art methods. For future work, some other adaptive methods like the fuzzy model-based network can be used to identify multiple object regions and classifying them among separate clusters.

     

聚类分析在高保真彩色印刷分色中的应用

研究一种新的基于改进的K均值聚类的高保真彩色印刷分色方法,算法首先将彩色图像通过非线性变换,转换到Lab颜色空间,再利用改进的K均值聚类算法进行色彩学习,最后经过改进的误差分散求取结果.算法优点是利用图像的空间相关信息,使分色结果得到局部优化;同时,由于阈值的引入,可以很好地控制分类精度;最后,通过对误差分散算法的改进,同时保证了分色图像色彩的连续性与差异性.     

AUTOMATIC FLOWER BOUNDARY EXTRACTION USING IPSOAntK-MEANS ALGORITHM

Automatic flower boundary extraction is an important part of flower image recognition and retrieval. Identifying a flower of interest or segmenting against the background is a difficult task. We proposed and developed a hybrid automatic flower boundary extraction method called IPSOAntK-means based on swarm intelligence techniques in this article. The method employs ant colony optimization, incremental particle swarm optimization (IPSO), and K-means algorithms and it is the first swarm-based technique in flower segmentation on color images. The parameters of the algorithm are tuned by iterated F-race and experiments are conducted over two different benchmark data sets: CAVIAR-Flower and Oxford 17 flowers data sets. In the CAVIAR-flower data set, IPSOAntK-means outperformed K-means with 96.4% accuracy on average over 600 colored flower images. Comparison results of the Oxford flower data set show that our method is one of the best flower segmentation methods in the literature.     

Segmentation of psoriasis vulgaris images using multiresolution-based orthogonal subspace techniques.

In this paper, a method is proposed for the segmentation of color images using a multiresolution-based signature subspace classifier (MSSC) with application to psoriasis images. The essential techniques consist of feature extraction and image segmentation (classification) methods. In this approach, the fuzzy texture spectrum and the two-dimensional fuzzy color histogram in the hue-saturation space are first adopted as the feature vector to locate homogeneous regions in the image. Then these regions are used to compute the signature matrices for the orthogonal subspace classifier to obtain a more accurate segmentation. To reduce the computational requirement, the MSSC has been developed. In the experiments, the method is quantitatively evaluated by using a similarity function and compared with the well-known LS-SVM method. The results show that the proposed algorithm can effectively segment psoriasis images. The proposed approach can also be applied to general color texture segmentation applications.     

基于PSO与K-均值聚类算法优化结合的图像分割方法

为了提高图像分割的质量和效率,同时,针对粒子群优化算法（Particle Swarm Optimization, PSO）容易陷于局部最优和K-均值算法对初始聚类中心敏感的问题,本文将PSO和K-均值算法相结合,提出一种通过调整惯性权重和学习因子的优化算法。首先,对图像进行去噪预处理,并将处理后的颜色图像转换到HSV空间,以提高色彩质量。然后,改进粒子群算法中的惯性权重和学习因子公式及参数,避免陷入局部最优。最后,根据粒子的适应度切换到K-均值算法执行局部搜索,使聚类中心不断更新实现快速收敛。实验结果表明,在图像分割的过程中,改进的算法具有全局搜索能力强的优点,能够实现更快的收敛速度和更高的分割精度。     

最优算法组合在目标检测图像信号处理中的应用

针对网域内简单背景下目标感知识别处理速度慢、准确率低的问题,提出了基于最优算法组合的目标检测方法;该方法将多种图像处理方法融入目标识别算法中,在采用不同算法对采集到的图像进行预处理、分割和特征提取效果比较的基础上,确定出最优算法组合并设计实验验证其可靠性和鲁棒性;试验结果表明该方法能够快速有效的判别行人目标,识别率达到96.67%,解决了网域内目标检测问题;与其他单一算法相比具有处理速度更快、判别更加有效,实时性高等特点,明显优于一般算法。     

Brain tumor segmentation and classification in MRI using SVM and its variants: a survey

The process of separation of brain tumor from normal brain tissues is Brain tumor segmentation. Segmentation of tumor from the MR images is a very challenging task as brain tumors are of different shapes and sizes. There are multiple phases to achieve the segmentation and the phases are pre-processing, segmentation, feature extraction, feature reduction, and classification of the tumor into benign and malignant. In this paper, Otsu thresholding is used in segmentation phase, Discrete Wavelet Transform (DWT) in feature extraction phase, Principal Component Analysis (PCA) in feature reduction phase and Support Vector Machine (SVM), Least Squared-Support Vector Machine (LS-SVM), Proximal Support Vector Machine (PSVM) and Twin Support Vector Machine (TWSVM) in the classification phase. We have compared the performances of all these classifiers, where TWSVM outperformed all other classifiers with 100% accuracy.

     

基于图像融合与YOLOv3的铝型材表面缺陷检测

我国是工业铝型材制造大国，铝型材生产质量检测意义重大。针对传统的人工目测等方式检测效率低下，稳定性相对较弱；单一YOLOv3方法特征提取不突出，检测精度有限等问题，提出一种基于图像融合与YOLOv3的铝型材表面缺陷检测方法。首先利用图像增强、空域滤波的方法对原始图像进行预处理得到处理图像；然后借鉴SLAM中特征提取与匹配的思想对原始图像和处理图像进行特征提取与匹配；之后进行图像融合得到最终的处理后图像；再通过K-means算法聚类和调参优化，最后利用单阶段物体检测模型YOLOv3对铝型材表面缺陷进行检测。通过一个end-to-end的全卷积神经网络完成从原始图像的输入到Bounding box和box中物体类别与置信度的输出。实验结果表明，此图像融合与YOLOv3的方法对表面缺陷分类检出的平均成功率为98.33%,比单一YOLOv3方法提高了3.75个百分点；验证集mAP值为88.81%，提高了4.18个百分点，具有更强的特征提取能力和泛化能力，能精确检测表面缺陷，进行分类和定位。