Rotation invariant detection in a noisy environment using a wavelet-based joint transform correlator (original) (raw)

Filter-feature-based rotation-invariant joint Fourier transform correlator

Applied Optics, 1995

Rotation-invariant target detection using a trained filter-feature-based joint Fourier transform 1JFT2 correlator is investigated. First, a composite reference image is obtained from a training set of targets. An optimum filter formulation is then applied on this composite image to come up with a new feature that we refer to as a filter feature. This feature is then used in a JFT correlator, which results in a simple and robust rotation-invariant target recognition system.

Distortion-invariant target detection using shifted-reference joint transform correlator

Optics and Photonics for Information Processing II, 2008

A new pattern recognition system is proposed using multiple phase-shifted-reference fringe-adjusted joint transform correlation technique. The algorithm involves four different phase-shifted versions of the reference image, which eliminates all unwanted correlation terms and produces a single cross-correlation signal corresponding to each potential target. A fringe-adjusted filter is designed to generate a delta-like correlation peak with high discrimination between the signal and the noise. In addition, the detection performance is made invariant to different spatial distortions by incorporating a synthetic discriminant function, which is created from a set of training images of the reference object. The target detection system is also designed for recognition of multiple targets belonging to multiple reference objects simultaneously in the given input scene and hence provides a real-time class-associative decision on the presence of any target. The proposed technique is investigated using computer simulation with binary as well as gray images in various complex environments where it performs excellent in every case.

Wavelet-modified fringe-adjusted joint transform correlator

Optics & Laser Technology, 2008

In this paper, we implement a wavelet-modified fringe-adjusted joint transform correlator (JTC) for real-time target recognition applications. In real-time situation the input scene is captured using a charge-coupled device (CCD) camera. The obtained joint power spectrum is multiplied by a pre-synthesized fringe-adjusted filter and the resultant function is processed with an appropriately scaled wavelet filter. Three performance measure parameters: correlation peak intensity, peak-to-sidelobe ratio, and signal-to-clutter ratio have been calculated for fringe-adjusted joint transform correlator (FJTC) and wavelet-modified fringe-adjusted joint transform correlator (WFJTC). The WFJTC has been found to yield better results in comparison to conventional FJTC. To suppress the undesired strong dc, the resultant function is differentiated. Differential processing wavelet-modified fringe-adjusted joint power spectrum removes the zeroorder spectra and hence improves the detection efficiency. To focus the correlation terms in different planes in order to capture one of the desired autocorrelation peaks and discard the strong dc and another autocorrelation peak, chirp-encoding technique has also been applied. Targets with Gaussian and speckle noise have also been used to check the correlation outputs. Computer simulation and experimental results are presented. r

Detection and Tracking of Rotated and Scaled Targets by Use of Hilbert-Wavelet Transform

Applied Optics, 2003

In a recent work, we demonstrated the usefulness of the Hilbert transform in identifying the in-plane rotation angle between two objects. Here we use the Hilbert-wavelet bases instead of the Hilbert transform in the determination of the exact angle of rotation. We describe the design of the two-dimensional Hilbert-wavelet filter based on the spectral-factorization method to generate a Hilbert-transform pair of orthogonal wavelet bases. We compare the relative performance of the Hilbert transform and the Hilbert wavelet to identify both in-plane and out-of-plane rotation angles. We demonstrate that the Hilbert wavelet offers better rotation-angle determination than the Hilbert transform. We present correlation based rotated and scaled object identification and tracking using Hilbert or Hilbert-wavelet transformed infrared image sequences. We also demonstrate reduced data handling and improved tracking of distorted objects using the Hilbert-wavelet transform.

Analysis of Image Detection Based on Fourier Plane Nonlinear Filtering in a Joint Transform Correlator

Applied Optics, 1998

Signal and image and detection systems based on nonlinear operations of Fourier-transformed data often exhibit greater selectivity than standard matched-filtering techniques. One such system is the joint transform correlator. We analyze the performance of the nonlinear joint transform correlator in terms of the output signal-to-noise ratio; this signal-to-noise ratio is evaluated in terms of both output contrast ͑peak-to-noise floor͒ and output variability ͑peak-to-peak standard deviation͒. The main assumption used is that the signal energy is small relative to that of the additive noise; this assumption is defensible in practice owing to the generally small spatial extent of target images relative to scenes. With respect to the first performance measure, this study is an extension of that in an earlier paper ͓Appl. Opt. 34, 5218 ͑1995͔͒. The previous analysis was carried out under a restriction that the signal and noise spectra were to be similar ͑actually multiples of one another͒. In the current study there is no such constraint, and all analysis of the second measure is new. The analysis is supported by simulation. A benefit of analytical rather than simulational study is that conclusions can be drawn with greater confidence. One of the most interesting of these is that the smooth square-root Fourier plane nonlinearity, more usually known as the k-law processor with k ϭ 0.5, offers extremely robust performance with respect to relative noise bandwidth.

Multiple-target detection by using joint transform correlator with compressed reference images

Optics Communications, 2005

Effects of JPEG compression of reference image on multiple-target detection by using joint transform correlator are quantitatively studied by using computer simulation. Two types of images with different spatial-frequency contents are used as test scenes in the presence of noise in the input plane and the contrast difference. The results show that in comparison with the use of the compressed reference with high spatial-frequency contents, the multiple-target detection by using the joint transform correlator with the compressed reference with low spatial-frequency contents produces better detection performance in that it is robust to noise and contrast difference for a wide range of compression qualities. While in the presence of noise and contrast difference, the compression of the reference image with high spatialfrequency contents may cause false alarms.

Improved Feature Extraction by use of a Joint Wavelet Transform Correlator

Applied Optics, 1998

A new joint wavelet transform correlation-based technique is proposed for feature extraction such as the detection of edges in an unknown input scene. We exploited a modified version of the Roberts and the Sobel wavelet filters as reference images for extracting the edges of an unknown input scene. The performance of the proposed technique with the aforementioned wavelet filters is evaluated and compared by use of numerical simulations. For noise-free input scenes the Roberts wavelet filter was found to yield a superior output compared with that of the Sobel wavelet filter. However, for noisy input scenes the Sobel wavelet filter was found to yield a better output compared with the Roberts wavelet filter.

Automatic target detection using wavelet transform

Eurasip Journal on Advances in Signal Processing, 2004

Automatic target recognition (ATR) involves processing images for detecting, classifying, and tracking targets embedded in a background scene. This paper presents an algorithm for detecting a specified set of target objects embedded in visual images for an ATR application. The developed algorithm employs a novel technique for automatically detecting man-made and non-manmade single, two, and multitargets from nontarget objects, located within a cluttered environment by evaluating nonoverlapping image blocks, where block-by-block comparison of wavelet cooccurrence feature is done. The results of the proposed algorithm are found to be satisfactory.