Kurt Kramer

Recognizing plankton images from the shadow image particle profiling evaluation recorder

We present a system to recognize underwater plankton images from the shadow image particle profiling evaluation recorder (SIPPER). The challenge of the SIPPER image set is that many images do not have clear contours. To address that, shape features that do not heavily depend on contour information were developed. A soft margin support vector machine (SVM) was used as the classifier. We developed a way to assign probability after multiclass SVM classification. Our approach achieved approximately 90% accuracy on a collection of plankton images. On another larger image set containing manually unidentifiable particles, it also provided 75.6% overall accuracy. The proposed approach was statistically significantly more accurate on the two data sets than a C4.5 decision tree and a cascade correlation neural network. The single SVM significantly outperformed ensembles of decision trees created by bagging and random forests on the smaller data set and was slightly better on the other data set. The 15-feature subset produced by our feature selection approach provided slightly better accuracy than using all 29 features. Our probability model gave us a reasonable rejection curve on the larger data set.

Active learning to recognize multiple types of plankton

Active learning has been applied with support vector machines to reduce the data labeling effort in pattern recognition domains. However, most of those applications only deal with two class problems. In this paper, we extend the active learning approach to multiple class support vector machines. The experimental results from a plankton recognition system indicate that our approach often requires significantly less labeled images to maintain the same accuracy level as random sampling.

Fast Support Vector Machines for Continuous Data

Support vector machines (SVMs) can be trained to be very accurate classifiers and have been used in many applications. However, the training time and, to a lesser extent, prediction time of SVMs on very large data sets can be very long. This paper presents a fast compression method to scale up SVMs to large data sets. A simple bit-reduction method is applied to reduce the cardinality of the data by weighting representative examples. We then develop SVMs trained on the weighted data. Experiments indicate that bit-reduction SVM produces a significant reduction in the time required for both training and prediction with minimum loss in accuracy. It is also shown to typically be more accurate than random sampling when the data are not overcompressed.

Learning to recognize plankton

We present a system to recognize underwater plankton images from the Shadow Image Particle Profiling Evaluation Recorder. As some images do not have clear contours, we developed several features that do not heavily depend on the contour information. A soft margin support vector machine (SVM) was used as the classifier. We developed a new way to assign probability after multi-class SVM classification. Our approach achieved approximately 90% accuracy on a collection of images with minimal noise. On another image set containing manually unidentifiable particles, it also provided promising results. Furthermore, our approach is more accurate on the two data sets than a C4.5 decision tree and a cascade correlation neural network at the 95% confidence level.

Active cleaning of label noise

Mislabeled examples in the training data can severely affect the performance of supervised classifiers. In this paper, we present an approach to remove any mislabeled examples in the dataset by selecting suspicious examples as targets for inspection. We show that the large margin and soft margin principles used in support vector machines (SVM) have the characteristic of capturing the mislabeled examples as support vectors. Experimental results on two character recognition datasets show that one-class and two-class SVMs are able to capture around 85% and 99% of label noise examples, respectively, as their support vectors. We propose another new method that iteratively builds two-class SVM classifiers on the non-support vector examples from the training data followed by an expert manually verifying the support vectors based on their classification score to identify any mislabeled examples. We show that this method reduces the number of examples to be reviewed, as well as providing parameter independence of this method, through experimental results on four data sets. So, by (re-)examining the labels of the selective support vectors, most noise can be removed. This can be quite advantageous when rapidly building a labeled data set. HighlightsNovel method for label noise removal from data is introduced.It significantly reduces the required number of examples to be reviewed.Support vectors of SVM classifier can capture around 99% of label noise examples.Two-class SVM captures more label noise examples than one-class SVM classifierCombination of one-class and two-class SVM produces a marginal improvement.

AUTOMATIC SECTION THICKNESS DETERMINATION USING AN ABSOLUTE GRADIENT FOCUS FUNCTION

Quantitative analysis of microstructures using computerized stereology systems is an essential tool in many disciplines of bioscience research. Section thickness determination in current nonautomated approaches requires manual location of upper and lower surfaces of tissue sections. In contrast to conventional autofocus functions that locate the optimally focused optical plane using the global maximum on a focus curve, this study identified by two sharp ‘knees’ on the focus curve as the transition from unfocused to focused optical planes. Analysis of 14 grey‐scale focus functions showed, the thresholded absolute gradient function, was best for finding detectable bends that closely correspond to the bounding optical planes at the upper and lower tissue surfaces. Modifications to this function generated four novel functions that outperformed the original. The ‘modified absolute gradient count’ function outperformed all others with an average error of 0.56 μm on a test set of images similar to the training set; and, an average error of 0.39 μm on a test set comprised of images captured from a different case, that is, different staining methods on a different brain region from a different subject rat. We describe a novel algorithm that allows for automatic section thickness determination based on just out‐of‐focus planes, a prerequisite for fully automatic computerized stereology.

Detection of Anomalous Particles from the Deepwater Horizon Oil Spill Using the SIPPER3 Underwater Imaging Platform

The aim of this study is to investigate a data mining approach to help assess consequences of oil spills in the maritime environment. The approach under investigation is based on detecting suspected oil droplets in the water column adjacent to the Deepwater Horizon oil spill. Our method automatically detects particles in the water, classifies them and provides an interface for visual display. The particles can be plankton, marine snow, oil droplets and more. The focus of this approach is to generalize the methodology utilized for plankton classification using SIPPER (Shadow Imaging Particle Profiler and Evaluation Recorder). In this paper, we report on the application of image processing and machine learning techniques to discern suspected oil droplets from plankton and other particles present in the water. We train the classifier on the data obtained during one of the first research cruises to the site of the Deepwater Horizon oil spill. Suspected oil droplets were visually identified in SIPPER images by an expert. The classification accuracy of the suspected oil droplets is reported and analyzed. Our approach reliably finds oil when it is present. It also classifies some particles (air bubbles and some marine snow), up to 3.3%, as oil in clear water. You can reliably find oil by visually looking at the examples put in the oil class ordered by probability, in which case oil is found in the first 10% of images examined.

Increased classification accuracy and speedup through pair-wise feature selection for support vector machines

Support vector machines are binary classifiers that can implement multi-class classifiers by creating a classifier for each possible combination of classes or for each class using a one class versus all strategy. Feature selection algorithms often search for a single set of features to be used by each of the binary classifiers. This ignores the fact that features that may be good discriminators for two particular classes might not do well for other class combinations. As a result, the feature selection process may not include these features in the common set to be used by all support vector machines. It is shown that by selecting features for each binary class combination, overall classification accuracy can be improved (as much as 2.1%), feature selection time can be significantly reduced (speed up of 3.2 times), and time required for training a multi-class support vector machine is reduced. Another benefit of this approach is that considerably less time is required for feature selection when additional classes are added to the training data. This is because the features selected for the existing class combinations are still valid, so that feature selection only needs to be run for the new class combinations created.

A novel algorithm for automated counting of stained cells on thick tissue sections

Design-based (unbiased) stereology provides an accurate, precise, and efficient method to quantify morphological parameters of biological microstructures, such as the total number of three-dimensional (3D) objects (cells) in stained tissue sections. The current requirement for extensive user interaction with commercially available computerized stereology systems limits the throughput of data collection. To increase the efficiency of this process, an algorithm was developed to automate data collection from stained objects in thick, transparent tissue sections. We present a novel approach to extract, count and classify stained objects of interest in 3D by linking them through a z-stack of images. Skeletonization and erosion are used to further segment the under segmented (overlapping) cells resulting from the extraction of out of focus cells in conjunction with in focus cells. Finally, 3D shape features, computed from the re-linked cells, are used for final classification of counted objects into “cells” and “not-cells”. We achieve a classification accuracy of 85% using SVM in a leave one-out experiment. The results demonstrate the effectiveness of our algorithm to count cells in 3D from thick, transparent tissue sections.

Toward automated quantification of biological microstructures using unbiased stereology

Quantitative analysis of biological microstructures using unbiased stereology plays a large and growing role in bioscience research. Our aim is to add a fully automatic, high-throughput mode to a commercially available, computerized stereology device (Stereologer). The current method for estimation of first- and second order parameters of biological microstructures, requires a trained user to manually select objects of interest (cells, fibers etc.,) while stepping through the depth of a stained tissue section in fixed intervals. The proposed approach uses a combination of color and gray-level processing. Color processing is used to identify the objects of interest, by training on the images to obtain the threshold range for objects of interest. In gray-level processing, a region-growing approach was used to assign a unique identity to the objects of interest and enumerate them. This automatic approach achieved an overall object detection rate of 93.27%. Thus, these results support the view that automatic color and gray-level processing combined with unbiased sampling and assumption and model-free geometric probes can provide accurate and efficient quantification of biological objects.