Filters For Pattern Recognition Research Articles

BRAIN TUMOR PATTERN RECOGNITION USING CORRELATION FILTER

This paper presents pattern identification in images which plays an important role in many real time applications worldwide. Different types of filters for pattern recognition have been proposed. But there seems to be growing interest in correlation based pattern recognitions. The reason for this is to design effective recognition system that needed to work on complex image processing applications. There is also a need to process large amount of images in real-time. The brain image processing applications are critical and are to be processed faster. In our approach, for this correlation filters are used which posses good mathematical fundamentals. The correlation filters can be effectively implemented either digitally or optodigitally. The pattern recognition is considered as the basic step for vision systems and efficiency is achieved using correlation filters.

Integrated zigzag Vander Lugt correlators incorporating an optimal trade-off synthetic discriminant filter for invariant pattern recognition

Optical correlators (OCs) have a wide range of applications in the field of pattern recognition. We present a type of integrated zigzag Vander Lugt correlator (IZVLC). The IZVLC incorporates two Fourier transform lenses and one spatial light modulator (SLM) as a programmable filter, which can effectively miniaturize the volume of OCs and hence achieve better optical pattern recognition. In order to precisely recognize distortion targets, an optimal trade-off synthetic discriminant filter (OTSDF) is programmed on the SLM of the IZVLC. Both the simulative and experimental results have shown that the IZVLC can effectively identify distortion targets within a rotation angle of ±π/3 and a scaling range of 0.6–1.6.

Adaptive composite filters for pattern recognition in nonoverlapping scenes using noisy training images

Correlation filters for target detection are usually designed by analytical optimization of performance criteria. The resulting expressions require explicit knowledge about the appearance and shape of the object of interest. As a result, the performance of correlation filters is significantly affected by changes in the appearance of the object in the input scene. These changes can be caused by factors such rotation and scaling. This has been addressed by the use of composite correlation filters that take into account different views of the object. In this work, we propose an algorithm for the design of adaptive composite filters when an object to be recognized is given in noisy training images and its shape and intensity values are not explicitly known. The impulse responses of optimal correlation filters are used to synthesize composite filters for distortion invariant object detection. Two techniques are used to improve the detection performance: an adaptive procedure that achieves a prespecified performance for a typical scene background, and multiple composite filters (bank of filters) when numerous views are available for training. Computer simulation results obtained with the proposed filters are presented and compared with those of common composite filters in terms of detection capability and location accuracy.

Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition

Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or texture. We propose a trainable filter which we call Combination Of Shifted FIlter REsponses (COSFIRE) and use for keypoint detection and pattern recognition. It is automatically configured to be selective for a local contour pattern specified by an example. The configuration comprises selecting given channels of a bank of Gabor filters and determining certain blur and shift parameters. A COSFIRE filter response is computed as the weighted geometric mean of the blurred and shifted responses of the selected Gabor filters. It shares similar properties with some shape-selective neurons in visual cortex, which provided inspiration for this work. We demonstrate the effectiveness of the proposed filters in three applications: the detection of retinal vascular bifurcations (DRIVE dataset: 98.50 percent recall, 96.09 percent precision), the recognition of handwritten digits (MNIST dataset: 99.48 percent correct classification), and the detection and recognition of traffic signs in complex scenes (100 percent recall and precision). The proposed COSFIRE filters are conceptually simple and easy to implement. They are versatile keypoint detectors and are highly effective in practical computer vision applications.

Pattern recognition filtering and bidimensional FFT-based detection of storms in meteorological radar images

Important climate changes are today observed around the world, frequently yielding destructing precipitations. To identify and follow the evolution of storms in real-time, meteorological radar images collected in Setif (Algeria), Bordeaux (France), and Dakar (Senegal), are processed. Template and pattern recognition-based filters are firstly used to remove the ground clutter and keep the precipitation echoes unchanged. Bidimensional FFT is then applied to the filtered images, showing that the Fourier spectra characterising convective clouds differ significantly from those of stratified ones. This difference can be usefully employed by the radar operators to quickly detect the formation of violent storms. To forecast the growing of rainfall clouds and their motion, the related radar echoes are reconstituted using inverse FFT. It is found that the 26 first harmonics are sufficient to both rapidly and accurately reconstitute the surface of clouds whereas 82 distinct harmonics are needed to well reproduce their reflectivity.

Design of correlation filters for pattern recognition using a noisy reference

We present the design of correlation filters for detection of a target in a noisy input scene when the object of interest is given in a noisy reference image. The target signal, shape and location in the reference image are assumed to be unknown. Two signal models are considered for the input scene: additive and nonoverlapping. The design of the filters consists of automated estimation of needed parameters from a noisy reference image and maximization of the peak-to-output energy ratio criterion. Two filter variants are proposed. The matching error metric is used to determine the regions of the parameter space where each filter variant performs better. Computer simulation results obtained with the proposed filters are presented and evaluated in terms of discrimination capability, location errors, and tolerance to input noise.

Design of correlation filters for pattern recognition with disjoint reference image

Correlation filters for pattern recognition are commonly designed under the assumption that the shape and appearance of an object of interest are explicitly known. In this paper, we consider a signal model in which an object of interest is given at unknown coordinates in a cluttered reference image and corrupted by additive noise. The reference image is used to design filters for detecting a target in scenes with a nonoverlapping background and additive noise. An optimum correlation filter with respect to peak-to-output energy for object detection is derived. The shape and appearance of the target are estimated from the reference image. Two methods to estimate the frequency response of the derived filter are used. Computer simulation results obtained with the proposed filters are presented and discussed. The performance of the filters is evaluated in terms of discrimination capability and location accuracy for different statistics of the backgrounds and noise processes present in the signal model.

Pattern recognition in nonoverlapping background with noisy target image

In the design of conventional correlation filters for pattern recognition, the appearance and the shape of a target are assumed to be known. In this work, the target is assumed to have unknown coordinates in a noise-corrupted reference image. We obtain a filter th at is optimal in terms of the ratio of the correlation peak to the energy of the correlation plane. Computer simulation is used to compare the performance of the conventional and the developed filters with regard to the detection of targets.

Content-addressable holographic data storage system for invariant pattern recognition of gray-scale images

Conventionally a holographic data storage system uses binary digital data as the input pages. We propose and demonstrate the use of a holographic data storage system for the purpose of invariant pattern recognition of gray-scale images. To improve the correlation accuracy for gray-scale images, we present a coding technique, phase Fourier transform (phase-FT) coding, to code a gray-scale image into a random and balanced digital binary image. In addition to the fact that a digital data page is obtained for incorporation into a holographic data storage system, this phase-FT coded image produces dc-free homogenized Fourier spectrum. This coded image can also be treated as an image for further processing, such as synthesis of distortion-invariant filters for invariant pattern recognition. A space-domain synthetic discriminant function (SDF) filter has been synthesized using these phase-FT coded images for rotation-invariant pattern recognition. Both simulation and experimental results are presented. The results show good correlation accuracy in comparison to correlation results obtained for SDF filter synthesized using the original gray-scale images themselves.

Indexed optical composite filters

A new technique called indexed composite filters (ICFs) for multiple object pattern recognition is proposed. Contrary to the usual so-called composite filters, the proposed ICF offers the possibility to identify which object of the learning class is detected at the output. The major advantage of ICF is that the output gives for every object detected two correlation peaks encoding the position and identity of the detected object. Computer simulation results are given using alphabetic input scenes that illustrates the efficiency of the proposed method.

Adaptive nonlinear composite filters for pattern recognition

Adaptive composite nonlinear filters for reliable illumination-invariant pattern recognition are proposed. The information about objects to be recognized, false objects, and a background to be rejected is utilized in an iterative training procedure to design a nonlinear adaptive correlation filter with a given value of discrimination capability. The designed filter during recognition process adapts its parameters to local statistics of the input image. Computer simulation results obtained with the proposed filters in test nonuniform illuminated scenes are discussed and compared with those of linear composite correlation filters in terms of recognition performance.

Nonlinear synthetic discriminant function filters for illumination-invariant pattern recognition

Novel nonlinear adaptive composite filters for illumination-invariant pattern recognition are presented. Pattern recognition is carried out with space-variant nonlinear correlation. The information about objects to be recognized, false objects, and a background to be rejected is utilized in an iterative training procedure to design a nonlinear adaptive correlation filter with a given discrimination capability. The designed filter during recognition process adapts its parameters to local statistics of the input image. Computer simulation results obtained with the proposed filters in nonuniformly illuminated test scenes are discussed and compared with those of linear composite correlation filters with respect to discrimination capability, robustness to input additive and impulsive noise, and tolerance to small geometric image distortions.

Adaptive composite filters for pattern recognition in linearly degraded and noisy scenes

New adaptive correlation filters for reliable recognition of geometrically distorted objects in blurred and noisy scenes are proposed. The filters are based on modified synthetic discriminant functions. The information about objects to be recognized, false objects, disjoint background, additive noise, and expected degradations of targets and input scenes are utilized in an iterative training algorithm. The algorithm is used to design a correlation filter with a specified discrimination capability. Computer simulation results obtained with the proposed adaptive filters in test scenes are discussed and compared with those of various correlation filters in terms of discrimination capability and location errors.

On steerability of Gabor-type filters for feature detection

We discuss the use of Gabor filters in pattern recognition. We derive optimal steering functions for non-spherical Gabor, DC-free Gabor and angular Gaussian filters and evaluate the accuracy of the approximative orientation steering numerically. Gabor-type filters can be steerable, but the error performance depends heavily on the parameters.

Adaptive correlation filters for pattern recognition

Adaptive correlation filters based on synthetic discriminant functions (SDFs) for reliable pattern recognition are proposed. A given value of discrimination capability can be achieved by adapting a SDF filter to the input scene. This can be done by iterative training. Computer simulation results obtained with the proposed filters are compared with those of various correlation filters in terms of recognition performance.

Adaptive synthetic discriminant function filters for pattern recognition

New adaptive correlation filters based on a conventional synthetic discriminant function (SDF) for reliable recognition of an object in cluttered background are proposed. The information about an object to be recognized, false objects, and a background to be rejected is utilized in an iterative training procedure to design a correlation filter with a given value of discrimination capability. Computer simulation results obtained with the proposed adaptive filter in test scenes are discussed and compared with those of various correlation filters in terms of discrimination capability, tolerance to input additive noise that is always present in image sensors, and to small geometric image distortions.

Binary phase only filters for rotation and scale invariant pattern recognition with the joint transform correlator

The joint transform correlator (JTC) is one of the two main optical image processing architecture which provides a highly effective way of comparing images in a wide range of applications. Traditionally, an optical correlator is used to compare an unknown input scene with a pre-captured reference image library, to detect if the reference occurs within the input. Strength of the correlation signal decreases rapidly as the input object rotates or varies in scale relative to the reference object. The aim of this paper is to overcome the intolerance of the JTC to rotation and scale changes in the target image. Many JTC systems are constructed with the use of ferroelectric liquid crystal (FLC) spatial light modulators (SLMs) as they provide fast two-dimensional binary modulation of coherent light. Due to the binary nature of the FLC SLMs used in the JTC systems, any image addressed to the device need to have some form of thresholding. Carefully thresholding the grey scale input plane and the joint power spectrum (JPS) has significant effect on the quality of correlation peaks and zero order (DC) noise. A new thresholding technique to binarise the JPS has been developed and implemented optically. This algorithm selectively enhances the desirable fringes in the JPS which provide correlation peaks of higher intensity. Zero order noise is further reduced when compared to existing thresholding techniques. Keeping in mind the architecture of the JTC and limitations of FLC SLMs, a new technique to design rotation and scale invariant binary phase only filters for the JTC architecture is presented. Filers design with this technique have limited dynamic range, higher discriminability among target and non-target objects, and convenience for implementation on FLC SLMs. Simulation and experiments shows excellent results of various rotation and scale invariant filters designed with this technique. A rotation invariant filter is needed for various machine vision applications of the JTC. By fixing the distance between camera and input object, the scale sensitivity of the correlator can be avoided. In contrast to the industrial machine vision applications, scale factor is very important factor for the applications of the JTC systems in defence and security. A security system using a scale invariant JTC will be able to detect a target object well in advance and will provide more time to take a decision.

Optical wavelet subband filtering for joint transform correlation

This work presents an experimental demonstration of an optical joint transform correlator based on the wavelet subband filter for texture pattern recognition. The optical wavelet subband filter is implemented using 4f filtering architecture and utilized to extract the texture features of fingerprints under noisy environments through frequency- and orientation-selective properties. The filtered texture features with noise reduction are applied to optimize recognition via joint transform correlation. Experimental results show that the optical wavelet subband filter enhances the significant texture features from corrupted fingerprints and increases the pattern discrimination of the joint transform correlator.

Engineering implementation of a hybrid optical correlator using SLMs

Optical correlators have been widely used for such applications as automatic target identification, invariant pattern recognition and machine vision. In hybrid optical correlators, Spatial light modulators (SLMs) are used to dynamically update the input and the filter. However, implementation is difficult because of the interference of “ghost” images; rigorous requirements for filter registration, accurate and effective filter sizing and complex valued filtering functions. This paper proposes some practical approaches to handle these issues and provides engineering details of how to build a hybrid optical correlator, where a SLM serves as an updateable intensity filter for real-time pattern recognition.

Low spatial frequency characterization of holographic recording materials applied to correlation

Accurate recording of computer-generated holograms (CGH) on a phase material is not a trivial task. The range of available phase materials is large, and their suitability depends on the fabrication technique chosen to produce the hologram. We are particularly interested in low-cost fabrication techniques, easily available for any lab. In this work we present the results obtained with a wide variety of phase holographic recording materials, characterized at low spatial frequencies (≤32 lp mm−1) which is the range associated with the technique we use to produce the CGHs. We have considered bleached emulsion, silver halide sensitized gelatin (SHSG) and dichromated gelatin. Some interesting differences arise between the behaviour of these materials in the usual holographic range (}1000\ntilde {\mathrm {lp\ntilde mm^{-1}}}$>>1000 lp mm−1), and the low-frequency range intended for digital holography. The ultimate goal of this paper is to establish the suitability of different phase materials as the media to generate correlation filters for optical pattern recognition. In all the materials considered, the phase filters generated ensure the discrimination of the target in the recognition process. Taking into account all the experimental results, we can say that SHSG is the best material to generate phase CGHs with low spatial frequencies.