Abstract: Contrast and lightness measures are used to first classify the image as being one of non-turbid and turbid. If turbid, the original image is enhanced to generate a first enhanced image. If non-turbid, the original image is classified in terms of a merged contrast/lightness score based on the contrast and lightness measures. The non-turbid image is enhanced to generate a second enhanced image when a poor contrast/lightness score is associated therewith. When the second enhanced image has a poor contrast/lightness score associated therewith, this image is enhanced to generate a third enhanced image. A sharpness measure is computed for one image that is selected from (i) the non-turbid image, (ii) the first enhanced image, (iii) the second enhanced image when a good contrast/lightness score is associated therewith, and (iv) the third enhanced image. If the selected image is not-sharp, it is sharpened to generate a sharpened image. The final image is selected from the selected image and the sharpened image.

Abstract: Contrast and lightness measures are used to first classify the image as being one of non-turbid and turbid. If turbid, the original image is enhanced to generate a first enhanced image. If non-turbid, the original image is classified in terms of a merged contrast/lightness score based on the contrast and lightness measures. The non-turbid image is enhanced to generate a second enhanced image when a poor contrast/lightness score is associated therewith. When the second enhanced image has a poor contrast/lightness score associated therewith, this image is enhanced to generate a third enhanced image. A sharpness measure is computed for one image that is selected from (i) the non-turbid image, (ii) the first enhanced image, (iii) the second enhanced image when a good contrast/lightness score is associated therewith, and (iv) the third enhanced image. If the selected image is not-sharp, it is sharpened to generate a sharpened image. The final image is selected from the selected image and the sharpened image.

Abstract: A system and method for identifying and quantifying targets within a liquid medium. A raw sidescan sonar image is collected. A region of interest is separated from the image. An image transformation is performed using an extraction algorithm. Salient image characteristics are calculated. Spurious pixels are removed from the image to obtain an extracted region of interest. Particle analysis is performed on the extracted region of interest to generate a feature vector which is presented to a neural network for classification.

Abstract: A system and method for identifying and quantifying targets within a liquid medium. A raw sidescan sonar image is collected. A region of interest is separated from the image. An image transformation is performed using an extraction algorithm. Salient image characteristics are calculated. Spurious pixels are removed from the image to obtain an extracted region of interest. Particle analysis is performed on the extracted region of interest to generate a feature vector which is presented to a neural network for classification.

Abstract: The present invention is a method of processing a digital image that is initially represented by digital data indexed to represent positions on a display. The digital data is indicative of an intensity value Ii(x,y) for each position (x,y) in each i-th spectral band. The intensity value for each position in each i-th spectral band is adjusted to generate an adjusted intensity value for each position in each i-th spectral band in accordance with ? n = 1 N ? W n ? ( log ? ? ? I i ? ( x , y ) - log ? ? [ I i ? ( x , y ) * F n ? ( x , y ) ] ) , i = 1 , … ? ? , S where Wn is a weighting factor, “*” is the convolution operator and S is the total number of unique spectral bands. For each n, the function Fn(x,y) is a unique surround function applied to each position (x,y) and N is the total number of unique surround functions. Each unique surround function is scaled to improve some aspect of the digital image, e.g.

Abstract: The present invention is a method of processing a digital image that is initially represented by digital data indexed to represent positions on a display. The digital data is indicative of an intensity value Ii(x,y) for each position (x,y) in each i-th spectral band. A classification of the image based on its dynamic range is then defined in each of the image's S spectral bands.

Abstract: The present invention is a method of processing a digital image that is initially represented by digital data indexed to represent positions on a display. The digital data is indicative of an intensity value Ii(x,y) for each position (x,y) in each i-th spectral band. A classification of the image based on its dynamic range is then defined in each of the image's S spectral bands.

Abstract: The present invention is a method of processing a digital image that is initially represented by digital data indexed to represent positions on a display. The digital data is indicative of an intensity value Ii(x,y) for each position (x,y) in each i-th spectral band.

Abstract: A method of improving a digital image is provided. The image is initially represented by digital data indexed to represent positions on a display. The digital data is indicative of an intensity value I.sub.i (x,y) for each position (x,y) in each i-th spectral band. The intensity value for each position in each i-th spectral band is adjusted to generate an adjusted intensity value for each position in each i-th spectral band in accordance with ##EQU1## where S is the number of unique spectral bands included in said digital data, W.sub.n is a weighting factor and "*" denotes the convolution operator. Each surround function F.sub.n (x,y) is uniquely scaled to improve an aspect of the digital image, e.g., dynamic range compression, color constancy, and lightness rendition. The adjusted intensity value for each position in each i-th spectral band is filtered with a common function and then presented to a display device.