Contextual classification of multispectral image data

Compound decision theory is invoked to develop a method for classifying image data using spatial context. Methods for characterizing contextual information in an image are proposed and tested. Experimental results based on both simulated and real multispectral remote sensing data demonstrate the effectiveness of the contextual classifier. A number of practical problems associated with this approach are discussed and possible solutions are explored.     

Differential Evolution as a viable tool for satellite image registration

A software system grounded on Differential Evolution to automatically register multiview and multitemporal images is designed, implemented and tested through a set of 2D satellite images on two problems, i.e. mosaicking and changes in time. Registration is effected by looking for the best affine transformation in terms of maximization of the mutual information between the first image and the transformation of the second one, and no control points are needed in this approach. This method is compared against five widely available tools, and its effectiveness is shown.     

Iterative fuzzy image segmentation

The multispectral signature of features has been used for identification of objects in remotely sensed scenes for a number of years. Recently these techniques have been applied to feature selection in natural scenes. Due to the inherent noise and degradation of the input cues to the algorithms, meaningful image segmentation is a difficult process. In an effort to reduce the sensitivity of a system to these problems, we have been led to the development of a iterative fuzzy clustering technique for image segmentation. It is believed that this method represents an image segmentation scheme which can be used as a preprocessor for a multivalued logic based computer vision system.     

Use of the Hough transform for image data compression

It is shown here that the Hough transform may be used for encoding of line curves and waveforms that consist of the concatenation of curves from an underlying set of families of curves. Several properties of the transform are given in this context.     

Leukocyte image analysis in the diff3 system

The diff3 System uses image processing and pattern recognition techniques to automatically analyze normal and abnormal white blood cells in a blood smear. The system consists of a spinner which creates a monolayer of cells on a glass slide, a stainer utilizing Wright's stain, the reagents to support the spinner and stainer, and an analyzer for automatic slide handling, analysis and report generation. The analyzer incorporates a wide range of image processing functions, including the generation and storage of gray scale image data, whole-field and partial-field image histogramming, and high-order binary image texture analysis and image transformation using the Golay processor (GLOPR). This paper describes the manner in which these hardware capabilities are used for white cell acquisition, scene segmentation and feature analysis. It concludes with some examples of texture extraction which illustrate the power of the Golay processor as a tool for image analysis.     

A cellular logic array for image processing

A cellular logic image processor employing 192 cells in a 16 by 12 hexagonal array is described. The processor has been constructed and its performance assessed. The various classes of functions which can be implemented in the cellular array are discussed and sample programs explained in detail.     

Classifier ensemble for an effective cytological image analysis

Breast cancer is the most common type of cancer among women. As early detection is crucial for the patient’s health, much attention has been paid to the development of tools for effective recognition of this disease. This article presents an application of image analysis and classification methods for fine needle biopsy. In our approach, each patient is described by nine microscopic images taken from the biopsy sample. The images are related to regions of the biopsy that seem interesting to the physician who selects them arbitrarily. We propose four different hybrid segmentation algorithms dedicated to processing these images and examine their effectiveness for the nuclei feature extraction task. Classification is carried out with the usage of a classifier ensemble based on the Random Subspaces approach. To boost its effectiveness, we use a linear combination of the support functions returned by the individual classifiers in the ensemble. In the proposed medical support system, the final decision about the patient is delivered after a fusion of nine separate outputs of the classifier – each for a different image. Experimental results carried out on a diverse dataset collected by the authors prove that the proposed solution outperforms state-of-the-art classifiers and shows itself to be a valuable tool for supporting day-to-day cytologist’s routine.     

Detection and analysis of individual leaf-off tree crowns in small footprint, high sampling density lidar data from the eastern deciduous forest in North America

Leaf-off individual trees in a deciduous forest in the eastern USA are detected and analysed in small footprint, high sampling density lidar data. The data were acquired February 1, 2001, using a SAAB TopEye laser profiling system, with a sampling density of approximately 12 returns per square meter. The sparse and complex configuration of the branches of the leaf-off forest provides sufficient returns to allow the detection of the trees as individual objects and to analyse their vertical structures. Initially, for the detection of the individual trees only, the lidar data are first inserted in a 2D digital image, with the height as the pixel value or brightness level. The empty pixels are interpolated, and height outliers are removed. Gaussian smoothing at different scales is performed to create a three-dimensional scale-space structure. Blob signatures based on second-order image derivatives are calculated, and then normalised so they can be compared at different scale-levels. The grey-level blobs with the strongest normalised signatures are selected within the scale-space structure. The support regions of the blobs are marked one-at-a-time in the segmentation result image with higher priority for stronger blobs. The segmentation results of six individual hectare plots are assessed by a computerised, objective method that makes use of a ground reference data set of the individual tree crowns. For analysis of individual trees, a subset of the original laser returns is selected within each tree crown region of the canopy reference map. Indices based on moments of the first four orders, maximum value and number of canopy and ground returns, are estimated. The indices are derived separately for height and laser reflectance of branches for the two echoes. Significant differences (p<0.05) are detected for numerous indices for three major native species groups: oaks (Quercus spp.), red maple (Acer rubrum) and yellow poplar (Liriodendron tuliperifera). Tree species classification results of different indices suggest a moderate to high degree of accuracy using single or multiple variables. Furthermore, the maximum tree height is compared to ground reference tree height for 48 sample trees and a 1.1-m standard error (R²=68% (adj.)) within the test-site is observed.     

Generic visual analysis for multi- and hyperspectral image data

Multi- and hyperspectral imaging and data analysis has been investigated in the last decades in the context of various fields of application like remote sensing or microscopic spectroscopy. However, recent developments in sensor technology and a growing number of application areas require a more generic view on data analysis, that clearly expands the current, domain-specific approaches. In this context, we address the problem of interactive exploration of multi- and hyperspectral data, consisting of (semi-)automatic data analysis and scientific visualization in a comprehensive fashion. In this paper, we propose an approach that enables a generic interactive exploration and easy segmentation of multi- and hyperspectral data, based on characterizing spectra of an individual dataset, the so-called endmembers. Using the concepts of existing endmember extraction algorithms, we derive a visual analysis system, where the characteristic spectra initially identified serve as input to interactively tailor a problem-specific visual analysis by means of visual exploration. An optional outlier detection improves the robustness of the endmember detection and analysis. An adequate system feedback of the costly unmixing procedure for the spectral data with respect to the current set of endmembers is ensured by a novel technique for progressive unmixing and view update which is applied at user modification. The progressive unmixing is based on an efficient prediction scheme applied to previous unmixing results. We present a detailed evaluation of our system in terms of confocal Raman microscopy, common multispectral imaging and remote sensing.     

Detecting and monitoring plumes caused by major industrial accidents with JPLUME, a new software tool for low-resolution image analysis

A new software tool for the automatic detection and monitoring of plumes caused by major industrial accidents is described. This tool has been designed in order to use near real time information as provided by satellite images, perform sophisticated image analysis and elaborate a user-friendly operational environment for the detection of plumes caused by major industrial accidents. The methodology, based on NOAA/AVHRR (Advanced Very High Resolution Radiometer) imagery, uses a two-dimensional feature space in order to discriminate pixels that contain plumes from those that correspond to clouds or to the underlying surface. The two-dimensional feature space is generated by combining AVHRR channels 1 (visible), 2 (near infrared) and 5 (thermal infrared). The software tool proposed has been coded in JAVA2 language, using the concepts of interoperability and object-oriented programming. This study demonstrates the applicability of the tool for the detection of a plume caused by a massive explosion in a firework factory in Enschede, The Netherlands, on May 13, 2000. The effectiveness and reliability of the software tool was found to be satisfactory, as plume was automatically detected and discriminated from the underlying surface.     

Hidden Markov Models for crop recognition in remote sensing image sequences

This work proposes a Hidden Markov Model (HMM) based technique to classify agricultural crops. The method uses HMM to relate the varying spectral response along the crop cycle with plant phenology, for different crop classes, and recognizes different agricultural crops by analyzing their spectral profiles over a sequence of images. The method assigns each image segment to the crop class whose corresponding HMM delivers the highest probability of emitting the observed sequence of spectral values. Experimental analysis was conducted upon a set of 12 co-registered and radiometrically corrected LANDSAT images of region in southeast Brazil, of approximately 124.100 ha, acquired between 2002 and 2004. Reference data was provided by visual classification, validated through extensive field work. The HMM-based method achieved 93% average class accuracy in the identification of the correct crop, being, respectively, 10% and 26% superior to multi-date and single-date alternative approaches applied to the same data set.     

A multi-resolution area-based technique for automatic multi-modal image registration

To allow remotely sensed datasets to be used for data fusion, either to gain additional insight into the scene or for change detection, reliable spatial referencing is required. With modern remote sensing systems, reliable registration can be gained by applying an orbital model for spaceborne data or through the use of global positioning (GPS) and inertial navigation (INS) systems in the case of airborne data. Whilst, individually, these datasets appear well registered when compared to a second dataset from another source (e.g., optical to LiDAR or optical to radar) the resulting images may still be several pixels out of alignment. Manual registration techniques are often slow and labour intensive and although an improvement in registration is gained, there can still be some misalignment of the datasets. This paper outlines an approach for automatic image-to-image registration where a topologically regular grid of tie points was imposed within the overlapping region of the images. To ensure topological consistency, tie points were stored within a network structure inspired from Kohonen’s self-organising networks [24]. The network was used to constrain the motion of the tie points in a manner similar to Kohonen’s original method. Using multiple resolutions, through an image pyramid, the network structure was formed at each resolution level where connections between the resolution levels allowed tie point movements to be propagated within and to all levels. Experiments were carried out using a range of manually registered multi-modal remotely sensed datasets where known linear and non-linear transformations were introduced against which our algorithm’s performance was tested. For single modality tests with no introduced transformation a mean error of 0.011 pixels was identified increasing to 3.46 pixels using multi-modal image data. Following the introduction of a series of translations a mean error of 4.98 pixels was achieve across all image pairs while a mean error of 7.12 pixels was identified for a series of non-linear transformations. Experiments using optical reflectance and height data were also conducted to compare the manually and automatically produced results where it was found the automatic results out performed the manual results. Some limitations of the network data structure were identified when dealing with very large errors but overall the algorithm produced results similar to, and in some cases an improvement over, that of a manual operator. We have also positively compared our method to methods from two other software packages: ITK and ITT ENVI.     

Hierarchical generalized Hough transforms and line-segment based generalized Hough transforms

Generalized Hough transforms are fast point pattern matching algorithms which have applications in image processing. Two extensions to generalized Hough transforms are described. The first allows for matching hierarchically organized point patterns. An example concerning image registration using hierarchical point patterns is described. The second extension concerns matching patterns of simple geometric objects, such as line segments, rather than patterns of points.     

The effects of data filtering on neural network learning

This paper describes various experiments involving the pre-processing of training data in order to improve the performance of a neural network classifier. To minimise the effect of noisy training samples we applied k-nearest neighbour filtering to the training data. This effectively detects and eliminates outliers, which would otherwise degrade the learning process of the neural network. For a range of neural network complexities, and for two classification tasks, the filtering operation increased classification accuracy.     

An image recognition method by rough classification for a scene image

We have recognized the regions of scene images for image recognition. First, the proposed segmentation method classifies images into several segments without using the Euclidian distance. We need several features to recognize regions. However, they are different for chromatic and achromatic colors. The regions are divided into three categories (black, achromatic, and chromatic). In this article, we focus on the achromatic category. The averages of the intensity and the fractal dimension features of the regions in the achromatic category are calculated. We recognize the achromatic region by using a neural network with suitable features. In order to show the effectiveness of the proposed method, we have recognized the regions. This work was presented in part at the 10th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2005     

图像分割技术及其在路面开裂损坏识别中的应用

研究了一种基于神经网络的图像分割技术，并将其应用于路面识别。该方法通过分析路面的照片，根据路面图像灰度与纹理的特征来判断路面损坏的类型、面积和严重程度，得出路面状况指数，具有速度快、数据质量高、方便等优点，远远优于目前的人工调查方法。     

Size–density spectra and their application to image classification

We develop a density opening operator that is shown to satisfy the properties of an algebraic opening. This density opening enables the development of a number of variants of pattern spectra, which quantify the size or density information of a blob arrangement within the image. In contrast to regular morphological pattern size spectra, the proposed pattern spectra are spatially sensitive and robust to noise distortions. A pattern size–density spectrum or 2D signature was introduced and used for solving image classification tasks. Its application to the classification of real world medical images is illustrated.     

大数据量微机遥感图像处理技巧

介绍了一些在微机上实现的高效实用的算法设计,增强了微机遥感图像处理的能力,同时这种技术也可与大中小型机上的图像处理相结合,从而使图像处理运行速度明显提高。