Candidate Regions Of Interest Research Articles

General-purpose optical pattern recognition image processors

A general-purpose programmable optical image processor architecture is described. A correlator architecture is used with different filter functions employed to implement a variety of different operations required in the different levels of computer vision. We consider input scenes with a number of objects present in clutter with a number of different object classes, distortions, and contrasts. The system locates all objects and identifies the class of each. The optical image processing operations performed include morphological low-level nonlinear functions, detection of candidate regions of interest, fusion of correlation outputs to reduce false alarms, image enhancement, and feature extraction. The optical correlation filters to realize each operations, examples of each, and real-time optical correlator hardware are described.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A functional anatomical study of unipolar depression

The functional neuroanatomy of unipolar major depression was investigated using positron emission tomography to measure differences in regional cerebral blood flow (BF). A relatively homogeneous subject group was obtained using criteria for familial pure depressive disease (FPDD), which are based upon family history as well as upon symptoms and course. Because of the absence of certain knowledge about the pathophysiology of mood disorders and their underlying functional neuroanatomy, we used data obtained from the subtraction of composite images from one-half of depressed and control subjects to identify candidate regions of interest. The major cortical region defined in this manner was statistically tested on a second set of subjects. Using this strategy, we found increased BF in an area that extended from the left ventrolateral prefrontal cortex onto the medial prefrontal cortical surface. Based upon the connectivity between these portions of the prefrontal cortex and the amygdala and evidence that the amygdala is involved in emotional modulation, activity was measured in the left amygdala and found to be significantly increased in the depressed group. A separate group of subjects with FPDD who were currently asymptomatic were also imaged to determine whether these findings represented abnormalities associated with the depressed state, or with a trait difference that might underlie the tendency to become depressed. Only the depressed group had increased activity in the left prefrontal cortex, suggesting that this abnormality represents a state marker of FPDD. Both the depressed and the remitted groups demonstrated increased activity in the left amygdala, though this difference achieved significance only in the depressed group. This suggests that the abnormality involving the left amygdala may represent a trait marker of FPDD, though further assessment in a larger sample size is necessary to establish this. These data along with other evidence suggest that a circuit involving the prefrontal cortex, amygdala, and related parts of the striatum, pallidum, and medial thalamus is involved in the functional neuroanatomy of depression.

Wavelet and Gabor transforms for detection

We consider wavelet and Gabor transforms for detection of candidate regions of interest in a 2-D scene. We generate wavelet and Gabor coefficients for each spatial region of a scene using new linear combination optical filters to reduce the output dimensionality and to simplify postprocessing. We use two sets of wavelet coefficients as indicators of edge activity to suppress background clutter. The Gabor coefficients are found to be excellent for object detection and robust to object distortions and contrast differences. We provide insight into the selection of the Gabor parameters.