A system for texture-based automatic detection of man-made objects or targets or features of scenes (automatic target recognition, ATR or detection, ATD) in representations of sensed natural environmental scenes spatially partitions digitized picture elements (pixels) of the scene into plural spatially coordinated groups of pixels and simultaneously determines texture measures including a composite texture measure for each group of pixels. Following self-calibration of the spatially coordinated composite texture measure values along spatially delineated row and orthogonal column directions of groups of pixels, areas of interest (AOIs) are identified as the groups of pixels most likely to contain a man-made object, target or feature in a decision logic which performs a group of statistical tests. Automatic detection of the spatial location of a man-made object, target, or feature within each AOI occurs by a single-threshold segmentation of pixels associated with each AOI into a grouping of target pixels and a grouping of non-target pixels. The spatial location of the man-made object, target, or feature within each AOI can be visually displayed, and the target location coordinates within the entire scene reported, whereupon the automatic detection system is reset for sensing and processing of a subsequent scene.
RELATED APPLICATIONS
This application is a continuation-in-part of application Ser. No. 07/729,139, filed Apr. 6, 1992, U.S. Pat. No. 5,274,715, which is a continuation-in-part of application Ser. No. 410,218, filed Sep. 21, 1989, now abandoned.
The invention uses fuzzy logic and/or probability distributions to automatically calculate and display the effects of contextual information on the confidence that an object in an image is an object of interest. The goal is to assist in determining the location and type of target objects of interest in that imagery. The imagery can come from any kind of imaging sensor or can be non-sensor imagery (e.g., two-and three-dimensional maps), and can be live or archived imagery. The locations of context objects can be provided by a human or a computer. The resulting set of data, including the original imagery, the locations of context objects, any results from AOD, and predictions about target object type and location, can be combined into a display that helps a human better understand where target object appears in the imagery.
A novel method of region segmentation for an image is disclosed. Specifically, region segmentation is accomplished by dividing the image into a plurality of sticks of pixels and determining whether each stick belongs to any region from a set of region. Each stick that belongs to any region is classified as belonging to a specific region.
A method for superimposing graphic representations of ground locations onto images of ground locations after detecting the presence of material failure(s) or failures in man-made structures in such ground locations including providing an image sensor spaced remotely from the ground and which sequentially captures a number of images of various ground locations to provide digital images of such ground locations; processing captured digital images to determine the presence of a potential material failure in a man-made structure in accordance with predetermined coordinate positions which locate the man-made structures in one or more of the captured digital images; identifying reference points in the ground locations corresponding to the same reference points in the graphic representations of the ground location; and superimposing the graphic representation with the reference points onto at least one of the captured digital images.
Methods and apparatuses are disclosed for identifying regions of similar texture in an image. The areas of similar texture include areas conventionally thought of as similar texture regions as well as areas of more varied texture that are treated as regions of similar texture in order to identify them within an image. The method associates frequency characteristics of an image with a spatial position within the image by: applying a frequency analysis on sub-regions of the image, thereby, generating frequency characteristics representative of the sub-regions: and associating the frequency characteristics with the origin of the sub-regions. An embodiment disclosed applies a fast Fourier transform on sub-regions in a given direction to determine a dominant frequency of the sub-region and the power of the dominant frequency, both of which are associated with the respective sub-region by storing the dominant frequency and power in a frequency image and power image, respectively, at the position of the origin. Thereafter, the frequency image and the power image are segmented to generate binary images containing regions having similar frequencies and powers, respectively. The binary images are then logically anded together to further refine the regions possessing similar frequency, and thereby finding regions having similar texture in an image.
A character string region extracting apparatus comprises an extracting section for extracting a plurality of primitives from image information in which a character and a graphic pattern other than the character are mixedly present, a character string candidate region forming section for generating character candidate regions from the primitives and connecting the character candidate regions, thereby forming at least one character string candidate region, a character recognizing section for subjecting the character candidate regions included in the character string candidate region to character recognition, and a character string region extracting section for extracting a character string region from the character string candidate region by the character recognition.
