Feature normalization via expectation maximization and unsupervised nonparametric classification for M-FISH chromosome images

Multicolor fluorescence in situ hybridization (M-FISH) techniques provide color karyotyping that allows simultaneous analysis of numerical and structural abnormalities of whole human chromosomes. Chromosomes are stained combinatorially in M-FISH. By analyzing the intensity combinations of each pixel, all chromosome pixels in an image are classified. Often, the intensity distributions between different images are found to be considerably different and the difference becomes the source of misclassifications of the pixels. Improved pixel classification accuracy is the most important task to ensure the success of the M-FISH technique. In this paper, we introduce a new feature normalization method for M-FISH images that reduces the difference in the feature distributions among different images using the expectation maximization (EM) algorithm. We also introduce a new unsupervised, nonparametric classification method for M-FISH images. The performance of the classifier is as accurate as the maximum-likelihood classifier, whose accuracy also significantly improved after the EM normalization. We would expect that any classifier will likely produce an improved classification accuracy following the EM normalization. Since the developed classification method does not require training data, it is highly convenient when ground truth does not exist. A significant improvement was achieved on the pixel classification accuracy after the new feature normalization. Indeed, the overall pixel classification accuracy improved by 20% after EM normalization.     

Multispectral image visualization through first-order fusion

We present a new formalism for the treatment and understanding of multispectral images and multisensor imagery based on first-order contrast information. Although little attention has been paid to the utility of multispectral contrast, we develop a theory for multispectral contrast that enables us to produce an optimal grayscale visualization of the first-order contrast of an image with an arbitrary number of bands. We demonstrate how our technique can reveal significantly more interpretive information to an image analyst, who can use it in a number of image understanding algorithms. Existing grayscale visualization strategies are reviewed. A variety of experimental results are presented to support the performance of the new method.     

A multichannel watershed-based segmentation method for multispectral chromosome classification

Multiplex fluorescent in situ hybridization M-FISH is a recently developed chromosome imaging technique where each chromosome class appears to have a distinct color. This technique not only facilitates the detection of subtle chromosomal aberrations but also makes the analysis of chromosome images easier; both for human inspection and computerized analysis. In this paper, a novel method for segmentation and classification of M-FISH chromosome images is presented. The segmentation is based on the multichannel watershed transform in order to define regions of similar spatial and spectral characteristics. Then, a Bayes classifier, task-specific on region classification, is applied. Our method consists of four basic steps: 1 computation of the gradient magnitude of the image, 2 application of the watershed transform to decompose the image into a set of homogenous regions, 3 classification of each region, and 4 merging of similar adjacent regions. The method is evaluated using a publicly available chromosome image database and the obtained overall accuracy is 82.4%. By introducing the classification of each watershed region, the proposed method achieves substantially better results compared to other methods at a lower computational cost. The combination of the multichannel segmentation and the region-based classification is found to improve the overall classification accuracy compared to pixel-by-pixel approaches.     

Wavelet-based compression of M-FISH images

Multiplex fluorescence in situ hybridization (M-FISH) is a recently developed technology that enables multi-color chromosome karyotyping for molecular cytogenetic analysis. Each M-FISH image set consists of a number of aligned images of the same chromosome specimen captured at different optical wavelength. This paper presents embedded M-FISH image coding (EMIC), where the foreground objects/chromosomes and the background objects/images are coded separately. We first apply critically sampled integer wavelet transforms to both the foreground and the background. We then use object-based bit-plane coding to compress each object and generate separate embedded bitstreams that allow continuous lossy-to-lossless compression of the foreground and the background. For efficient arithmetic coding of bit planes, we propose a method of designing an optimal context model that specifically exploits the statistical characteristics of M-FISH images in the wavelet domain. Our experiments show that EMIC achieves nearly twice as much compression as Lempel-Ziv-Welch coding. EMIC also performs much better than JPEG-LS and JPEG-2000 for lossless coding. The lossy performance of EMIC is significantly better than that of coding each M-FISH image with JPEG-2000.     

Subspace-based prototyping and classification of chromosome images.

Chromosomes are essential genomic information carriers. Chromosome classification constitutes an important part of routine clinical and cancer cytogenetics analysis. Cytogeneticists perform visual interpretation of banded chromosome images according to the diagrammatic models of various chromosome types known as the ideograms, which mimic artists' depiction of the chromosomes. In this paper, we present a subspace-based approach for automated prototyping and classification of chromosome images. We show that 1) prototype chromosome images can be quantitatively synthesized from a subspace to objectively represent the chromosome images of a given type or population, and 2) the transformation coefficients (or projected coordinate values of sample chromosomes) in the subspace can be utilized as the extracted feature measurements for classification purposes. We examine in particular the formation of three well-known subspaces, namely the ones derived from principal component analysis (PCA), Fisher's linear discriminant analysis, and the discrete cosine transform (DCT). These subspaces are implemented and evaluated for prototyping two-dimensional (2-D) images and for classification of both 2-D images and one-dimensional profiles of chromosomes. Experimental results show that previously unseen prototype chromosome images of high visual quality can be synthesized using the proposed subspace-based method, and that PCA and the DCT significantly outperform the well-known benchmark technique of weighted density distribution functions in classifying 2-D chromosome images.     

A MRF model-based segmentation approach to classification formultispectral imagery

An unsupervised segmentation approach to classification of multispectral image is suggested here in Markov random field (MRF) frame work. This work generalizes the work of Sarkar et al. (2000) on gray value images for multispectral images and is extended for landuse classification. The essence of this approach is based on capturing intrinsic characters of tonal and textural regions of any multispectral image. The approach takes an initially oversegmented image and the original. multispectral image as the input and defines a MRF over region adjacency graph (RAG) of the initially segmented regions. Energy function minimization associated with the MRF is carried out by applying a multivariate statistical test. A cluster validation scheme is outlined after obtaining optimal segmentation. Quantitative evaluation of classification accuracy of test data for three illustrations are shown and compared with conventional maximum likelihood procedure. Comparison of the proposed methodology with a recent work of texture segmentation in the literature has also been provided. The findings of the proposed method are found to be encouraging     

A wrapper-based approach to image segmentation and classification.

The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest from the background image. It is extremely difficult to obtain a reliable segmentation without any prior knowledge about the object that is being extracted from the scene. This is further complicated by the lack of any clearly defined metrics for evaluating the quality of segmentation or for comparing segmentation algorithms. We propose a method of segmentation that addresses both of these issues, by using the object classification subsystem as an integral part of the segmentation. This will provide contextual information regarding the objects to be segmented, as well as allow us to use the probability of correct classification as a metric to determine the quality of the segmentation. We view traditional segmentation as a filter operating on the image that is independent of the classifier, much like the filter methods for feature selection. We propose a new paradigm for segmentation and classification that follows the wrapper methods of feature selection. Our method wraps the segmentation and classification together, and uses the classification accuracy as the metric to determine the best segmentation. By using shape as the classification feature, we are able to develop a segmentation algorithm that relaxes the requirement that the object of interest to be segmented must be homogeneous in some low-level image parameter, such as texture, color, or grayscale. This represents an improvement over other segmentation methods that have used classification information only to modify the segmenter parameters, since these algorithms still require an underlying homogeneity in some parameter space. Rather than considering our method as, yet, another segmentation algorithm, we propose that our wrapper method can be considered as an image segmentation framework, within which existing image segmentation algorithms may be executed. We show the performance of our proposed wrapper-based segmenter on real-world and complex images of automotive vehicle occupants for the purpose of recognizing infants on the passenger seat and disabling the vehicle airbag. This is an interesting application for testing the robustness of our approach, due to the complexity of the images, and, consequently, we believe the algorithm will be suitable for many other real-world applications.     

Supervised learning-based cell image segmentation for p53 immunohistochemistry

In this paper, we present two new algorithms for cell image segmentation. First, we demonstrate that pixel classification-based color image segmentation in color space is equivalent to performing segmentation on grayscale image through thresholding. Based on this result, we develop a supervised learning-based two-step procedure for color cell image segmentation, where color image is first mapped to grayscale via a transform learned through supervised learning, thresholding is then performed on the grayscale image to segment objects out of background. Experimental results show that the supervised learning-based two-step procedure achieved a boundary disagreement (mean absolute distance) of 0.85 while the disagreement produced by the pixel classification-based color image segmentation method is 3.59. Second, we develop a new marker detection algorithm for watershed-based separation of overlapping or touching cells. The merit of the new algorithm is that it employs both photometric and shape information and combines the two naturally in the framework of pattern classification to provide more reliable markers. Extensive experiments show that the new marker detection algorithm achieved 0.4% and 0.2% over-segmentation and under-segmentation, respectively, while reconstruction-based method produced 4.4% and 1.1% over-segmentation and under-segmentation, respectively.     

Comparison of scene segmentations: SMAP, ECHO, and maximumlikelihood

Sequential maximum a posteriori (SMAP) and the extraction and classification of homogeneous objects (ECHO), two spectral/spatial scene segmentation algorithms, were compared with traditional maximum likelihood (ML) estimation in a supervised classification of multispectral data. SMAP generalized better than both ECHO and ML. Significant differences were found in all mean class classification accuracies: SMAP>ECHO>ML     

A novel lacunarity estimation method applied to SAR image segmentation

Based on the relative differential box-counting algorithm and the gliding-box algorithm, a novel method for estimating the lacunarity features of grayscale digital images is proposed. Four natural texture images are used to test the performance of the novel lacunarity measure. Comparisons with published methods show that the proposed method can efficiently describe texture images, and provide accurate classification results. Real synthetic aperture radar (SAR) images analyses are found to have different lacunarity values for different regions. We show that good results can be obtained with appropriate lacunarity parameters applied to SAR images segmentation.     

Simultaneous vector-valued image segmentation and intensity nonuniformity correction using variational level set combined with Markov random field modeling

Object quantification requires an image segmentation to make measurements about size, material composition and morphology of the object. In vector-valued or multispectral images, each image channel has its signal characteristics and provides special information that may improve the results of image segmentation method. This paper presents a region-based active contour model for vector-valued image segmentation with a variational level set formulation. In this model, the local image intensities are characterized using Gaussian distributions with different means and variances. Furthermore, by utilizing Markov random field, the spatial correlation between neighboring pixels and voxels is modeled. With incorporation of intensity nonuniformity model, our method is able to deal with brain tissue segmentation from multispectral magnetic resonance (MR) images. Our experiments on synthetic images and multispectral cerebral MR images with different noise and bias level show the advantages of the proposed method.     

基于神经网络的典型地物的偏振多光谱图像分类（特邀）

相比传统的多光谱成像探测,偏振多光谱成像探测方法可以探测目标表面的粗糙度、含水量等更多信息,给目标检测带来了很大便利,但目前主要用于目标探测,尚未广泛应用于目标分类。BP神经网络是目前常用的一种典型神经网络,可以建立从端到端的映射,在训练样本集足够大的前提下,训练完毕且效果良好的神经网络是一种高效、精确、快速的工具。首先,利用基于旋转偏振片和滤波片的偏振光谱成像探测系统获取了典型地物的偏振多光谱图像,对图像进行了预处理,建立了数据集;其次,在该数据集上进行了神经网络的训练,训练后的神经网络可以处理未知的偏振多光谱图像,并实现了对几种典型地物的分类;最后,对神经网络分类的效果进行了评价,并与其他几种典型分类方法的效果进行了对比,发现神经网络方法具有更好的分类精度和效果,相比典型的最大似然分类算法,其总体分类精度可从91.7%提升至94.2%,Kappa系数可从0.851提升至0.898。研究结果表明:基于神经网络的偏振光谱图像分类方法对于改进和优化现有的偏振多光谱图像数据处理方法具有一定的研究意义。     

Wavelet-based multispectral face recognition

This paper proposes a novel wavelet-based face recognition method using thermal infrared （IR） and visible-light face images. The method applies the combination of Gabor and the Fisherfaces method to the reconstructed IR and visible images derived from wavelet frequency subbands. Our objective is to search for the subbands that are insensitive to the variation in expression and in illumination. The classification performance is improved by combining the multispectal information coming from the subbands that attain individually low equal error rate. Experimental results on Notre Dame face database show that the proposed wavelet-based algorithm outperforms previous multispectral images fusion method as well as monospectral method.     

Compression of multispectral images by spectral classification andtransform coding

This paper presents a new technique for the compression of multispectral images, which relies on the segmentation of the image into regions of approximately homogeneous land cover. The rationale behind this approach is that, within regions of the same land cover, the pixels have stationary statistics and are characterized by mostly linear dependency, contrary to what usually happens for unsegmented images. Therefore, by applying conventional transform coding techniques to homogeneous groups of pixels, the proposed algorithm is able to effectively exploit the statistical redundancy of the image, thereby improving the rate distortion performance. The proposed coding strategy consists of three main steps. First, each pixel is classified by vector quantizing its spectral response vector, so that both a reliable classification and a minimum distortion encoding of each vector are obtained. Then, the classification map is entropy encoded and sent as side information, Finally, the residual vectors are grouped according to their classes and undergo Karhunen-Loeve transforming in the spectral domain and discrete cosine transforming in the spatial domain. Numerical experiments on a six-band thematic mapper image show that the proposed technique outperforms the conventional transform coding technique by 1 to 2 dB at all rates of interest.     

基于Contourlet域图谱聚类和多尺度Markov模型的多光谱遥感图像分割

针对多光谱遥感图像的特点,结合图谱聚类、Co ntourlet系数分布的统计特性和多尺度Markov模型, 提出了一种基于Contourlet域图谱聚类和多尺度Markov模型的分割(CSCMMS)方法。首先对 待分割图像进行Contourlet变换,利用图谱聚类对最粗尺度低频图像聚类得到可靠的初始分 割结果;然后 利用互信息构造Contourlet域的多尺度Markov模型,结合多尺度、多方向的图像信息将低频 图像的初始分 割结果逐尺度传递到最细尺度,得到原始图像的分割。对合成图像和多光谱遥感图像的实验 结果表明,提 出方法在边缘信息保持和噪声敏感性上具有明显改进,错分率和运算时间进一步降低。     

Maximum Likelihood Estimation of Label Imperfection Probabilities and Its Use in the Identification of Mislabeled Patterns

This paper presents the problem of estimating label imperfections and the use of the estimation in identifying mislabeled patterns. Expressions for the maximum likelihood estimates of classification errors and a priori probabilities are derived from the classification of a set of labeled and unlabeled patterns. Expressions also are presented for the asymptotic variances of probability of correct classification and proportions. Simple models are developed for imperfections in the labels and for classification errors and are used in the formulation of a maximum likelihood estimation scheme. Schemes are presented for the identification of mislabeled patterns in terms of thresholds on the discriminant functions for both two-class and multiclass cases. Expressions are derived for the probability that the imperfect label identifi'cation scheme will result in a wrong decision and are used in computing thresholds. Furthermore, the results of practical applications of these techniques in the processing of remotely sensed multispectral data are presented.     

Integrated method for boundary delineation of agricultural fieldsin multispectral satellite images

Most agricultural statistics are calculated per field, and it is well known that classification procedures for homogeneous objects produce better results than per-pixel classification. In this study, a multispectral segmentation method for automated delineation of agricultural field boundaries in remotely sensed images is presented. Edge information from a gradient edge detector is integrated with a segmentation algorithm. The multispectral edge detector uses all available multispectral information by adding the magnitudes and directions of edges derived from edge detection in single bands. The addition is weighted by edge direction, to remove "noise" and to enhance the major direction. The resulting edge from the edge detection algorithm is combined with a segmentation method based on a simple ISODATA algorithm, where the initial centroids are decided by the distances to the edges from the edge detection step. From this procedure, the number of regions will most likely exceed the actual number of fields in the image and merging of regions is performed. By calculating the mean and covariance matrix for pixels of neighboring regions, regions with a high generalized likelihood-ratio test quantity will be merged. In this way, information from several spectral bands (and/or different dates) can be used for delineating field borders with different characteristics. The introduction of the ISODATA classifier compared with a previously used region growing procedure improves the output. Some results are compared with manually extracted field boundaries     

Hybrid threshold optimization between global image and local regions in image segmentation for melasma severity assessment

Melasma image segmentation plays a fundamental role for computerized melasma severity assessment. A method of hybrid threshold optimization between a given image and its local regions is proposed and used for melasma image segmentation. An analytic optimal hybrid threshold solution is obtained by minimizing the deviation between the given image and its segmented outcome. This optimal hybrid threshold comprises both local and global information around image pixels and is used to develop an optimal hybrid thresholding segmentation method. The developed method is firstly evaluated based on synthetic images and subsequently used for melasma segmentation and severity assessment. Statistical evaluations of experimental results based on real-world melasma images show that the proposed method outperforms other state-of-the-art thresholding segmentation methods for melasma severity assessment.     

Feature analysis and centromere segmentation of human chromosome images using an iterative fuzzy algorithm

Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.