WND-CHARM: Multi-purpose image classification using compound image transforms
Introduction
The increasing use of digital imagery in many fields of science and engineering introduces a demand for accurate image analysis and classification. Applications include remote sensing (Smith and Li, 1999), face recognition (Shen and Bai, 2006, Jing and Zhang, 2004, Jing et al., 2006, Pentland and Choudhury, 2000), and biological and medical image classification (Boland and Murphy, 2001, Awate et al., 2006, Cocosco et al., 2004, Ranzato et al., 2007). Although attracting considerable attention in the past few years, image classification is still considered a challenging problem in machine learning due to the very complex nature of the subjects in real-life images, making quantitative similarity measures difficult.
A common approach to quantitatively measure similarity between images is to extract and analyze a set of low-level image features (Heidmann, 2005, Gurevich and Koryabkina, 2006). These can include color (Stricker and Orengo, 1995, Funt and Finlayson, 1995, Tieu and Viola, 2004, texture (Smith and Chang, 1994, Smith and Chang, 1996, Livens et al., 1996, Ferro and Warner, 2002), shape (Mohanty et al., 2005), histograms (Flickner et al., 1995, Chapelle et al., 1999, Qiu et al., 2004), and more. However, image features perform differently depending on the image classification problem (Gurevich and Koryabkina, 2006) making the accuracy of a task-specific image classifier limited when applied to a different imaging task.
The performance of task-specific classifiers in problems they were not originally designed for can often be inadequate, introducing a significant barrier to using automated image classification in science and engineering. New image classification problems are continually emerging in these fields, requiring the continual development and optimization of new image classifiers to specifically address these problems. The knowledge and experience needed to successfully implement such vision systems are not typically available to an experimentalist or application developer who does not specialize in image analysis or pattern recognition.
The proliferation of imaging problems and classifiers to address them is acute in the field of cell biology. The range of instrumentation and imaging modes available for capturing images of cells multiplexed with the variety of morphologies exhibited by cells and tissues preclude a standard protocol for constructing problem-specific classifiers. There are very few “standard problems” in cell biology: Identification of specific sub-cellular organelles is an important exception, but the vast majority of experiments where image classification would be an invaluable tool do not fall into standard problem types. The advent of high content screening (HCS) where the goal is to search through tens of thousands of images for a specific target morphology requires a flexible classification tool that allows any morphology to be used as a target. Since the variety of target morphologies is vast, a general image classification tool is required to fully exploit the potential offered by HCS.
Here, we describe a multi-purpose image classifier and its application to a wide variety of image classification problems without the sacrifice of classification accuracy. Although the classifier was initially developed to address high content screening, it was found surprisingly effective in image classification tasks outside the scope of cell biology. In Section 2 we describe the features extracted from training and test images, in Section 3 we discuss the high dimensionality classifier that computes similarities between the test and training images, and in Section 4 we present experimental results demonstrating the efficacy of the proposed algorithm in several test cases along with comparisons to previously proposed task-specific classifiers.
Section snippets
Image feature extraction
The first step in generalized image classification is to represent the image content as a set of numeric values (features). Due to the wide range of possible tasks performed by generalized image classifiers, the number of features computed during training is far greater than in task-specific classifiers. The types of features used by the image classifier described in this paper fall into four categories: polynomial decompositions, high contrast features, pixel statistics, and textures. In
Feature value classification
Due to the high dimensionality of the feature set, some of the features computed on a given image dataset are expected to represent noise. Therefore, selecting an informative feature sub-space by rejecting noisy features is a required step. In task-specific image classification, selection of relevant image features is often manual. For general image classification, however, feature selection (or dimensionality reduction) and weighting must be accomplished in an automated way.
There are two
Experimental results
The performance of WND-CHARM was evaluated using several datasets from different types of image classification problems. For each dataset evaluated, the performance of the algorithm described in this paper was compared with the performance of previously proposed application-specific algorithms that were developed exclusively for that dataset. For biological images we used the HeLa dataset (Boland and Murphy, 2001), consisting of fluorescence microscopy images of HeLa cells using 10 different
Conclusion
We described an image classification algorithm that can address a wide variety of image classification problems without modifications or parameter adjustments, and can provide accuracy favorably comparable to previously proposed application-specific classifiers. WND-CHARM is based on computing a very large set of image features. Since different groups of image features are more informative for different image classification problems, the large set of features used by this method can provide a
Acknowledgement
The images in Fig. 3, Fig. 5 were from Murphy Lab, CMU. This research was supported by the Intramural Research Program of the NIH, National Institute on Aging.
References (66)
- et al.
Adaptive Markov modeling for mutual-information-based, unsupervised MRI brain-tissue classification
Medical Image Anal.
(2006) - et al.
Rotation-invariant and scale-invariant Gabor features for texture image retrieval
Image Vision Comput.
(2007) - et al.
Face recognition based on discriminant fractional Fourier feature extraction
Pattern Recognition Lett.
(2006) - et al.
Wrappers for feature subset selection
Artificial Intell.
(1997) - et al.
Compressing histogram representations for automatic colour photo categorization
Pattern Recognition
(2004) - et al.
Automatic recognition of biological particles in microscopic images
Pattern Recognition Lett.
(2007) - et al.
MutualBoost learning for selecting Gabor features for face recognition
Pattern Recognition Lett.
(2006) - et al.
Image classification and querying using composite region templates
Computer Vision and Image Understanding
(1999) - et al.
A direct LDA algorithm for high-dimensional data with application to face recognition
Pattern Recognition
(2001) - et al.
Eigenfaces vs. fisherface: Recognition using class specific linear projection
IEEE Trans. Pattern Anal. Machine Intell.
(1997)