Nonlinear cascaded correlation processes to improve the performances of automatic spatial-frequency-selective filters in pattern recognition

Three-dimensional identification of microorganisms using a digital holographic microscope

This paper reports a method for three-dimensional (3D) analysis of shift-invariant pattern recognition and applies to holographic images digitally reconstructed from holographic microscopes. It is shown that the sequential application of a 2D filter to the plane-by-plane reconstruction of an optical field is exactly equivalent to the application of a more general filter with a 3D impulse response. We show that any 3D filters with arbitrary impulse response can be implemented in this way. This type of processing is applied to the two-class problem of distinguishing different types of bacteria. It is shown that the proposed technique can be easily implemented using a modified microscope to develop a powerful and cost-effective system with great potential for biological screening.

Decision optimization for face recognition based on an alternate correlation plane quantification metric

We consider a new approach for enhancing the discrimination performance of the VanderLugt correlator. Instead of trying to optimize the correlation filter, or propose a new decision correlation peak detection criterion, we propose herein to denoise the correlation plane before applying the peak-to-correlation energy (PCE) criterion. For that purpose, we use a linear functional model to express a given correlation plane as a linear combination of the correlation peak, noise, and residual components. The correlation peak is modeled using an orthonormalized function and the singular value decomposition method. A set of training correlation planes is then selected to create the correlation noise components. Finally, an optimized correlation plane is reconstructed while discarding the noise components. Independently of the filter correlation used, this technique denoises the correlation plane by lowering the correlation noise magnitude in case of true correlation and decreases the false alarm rate when the target image does not belong to the desired class. Test results are presented, using a composite filter and a face recognition application, to verify the effectiveness of the proposed technique.

Rotationally invariant pattern recognition by use of linear and nonlinear cascaded filters

We discuss the merits of using single-layer (linear and nonlinear) and multiple-layer (nonlinear) filters for rotationally invariant and noise-tolerant pattern recognition. The capability of each approach is considered with reference to a two-class, rotation-invariant, character recognition problem. The minimum average correlation energy (MACE) filter is a linear filter that is generally accepted to be optimal for detecting signals that are free from noise. Here it is found that an optimized MACE filter cannot differentiate between the characters E and F in a rotation-invariant manner. We have found, however, that this task is possible when a single optimized linear filter is used to achieve the required response when a nonlinear threshold function is included after the filter. We show that this structure can be cascaded to form a multiple-layer, cascaded filter and that the capability of such a system is enhanced by its increased noise tolerance in the character recognition problem. Finally, we show the capability of a two-layer cascade as a means to detect different species of bacteria in images obtained from a phase-contrast microscope.

Pattern recognition with a digital holographic microscope working in partially coherent illumination

We describe the implementation of the automatic spatial-frequency-selection filter for recognition of patterns obtained with a digital holographic microscope working with a partially coherent source. The microscope provides the complex-optical-amplitude field that allows a refocusing plane-by-plane of the sample under investigation by numerical computation of the optical propagation. By inserting a correlation filter in the propagation equation, the correlation between the filter and the propagated optical field is obtained. In this way, the pattern is located in the direction of the optical axis. Owing to the very weak noise level generated by the partially coherent source, the correlation process is shift invariant. Therefore the samples can be located in the three dimensions. To have a robust recognition process, a generalized version of the automatic spatial-frequency-selection filters has been implemented. The method is experimentally demonstrated in a two-class problem for the recognition of protein crystals.

Cascaded linear shift-invariant processors in optical pattern recognition

We study a cascade of linear shift-invariant processing modules (correlators), each augmented with a nonlinear threshold as a means to increase the performance of high-speed optical pattern recognition. This configuration is a special class of multilayer, feed-forward neural networks and has been proposed in the literature as a relatively fast best-guess classifier. However, it seems that, although cascaded correlation has been proposed in a number of specific pattern recognition problems, the importance of the configuration has been largely overlooked. We prove that the cascaded architecture is the exact structure that must be adopted if a multilayer feed-forward neural network is trained to produce a shift-invariant output. In contrast with more generalized multilayer networks, the approach is easily implemented in practice with optical techniques and is therefore ideally suited to the high-speed analysis of large images. We have trained a digital model of the system using a modified backpropagation algorithm with optimization using simulated annealing techniques. The resulting cascade has been applied to a defect recognition problem in the canning industry as a benchmark for comparison against a standard linear correlation filter, the minimum average correlation energy (MACE) filter. We show that the nonlinear performance of the cascade is a significant improvement over that of the linear MACE filter in this case.