We define a new image feature called the color correlogram and use it for image indexing and comparison. This feature distills the spatial correlation of colors, and is both effective and inexpensive for content-based image retrieval. The correlogram robustly tolerates large changes in appearance and shape caused by changes in viewing positions, camera zooms, etc. Experimental evidence suggests that this new feature outperforms not only the traditional color histogram method but also the recently proposed histogram refinement methods for image indexing/retrieval.

/pdf/image-indexing-using-color-correlograms-46xcwi22a8.pdf

Image indexing using color correlograms

The present invention involves method and apparatus for analyzing two measured signals that are modeled as containing primary and secondary portions. Coefficients relate the two signals according to a model defined in accordance with the present invention. In one embodiment, the present invention involves utilizing a transformation which evaluates a plurality of possible signal coefficients in order to find appropriate coefficients. Alternatively, the present invention involves using statistical functions or Fourier transform and windowing techniques to determine the coefficients relating to two measured signals. Use of this invention is described in particular detail with respect to blood oximetry measurements.

Signal processing apparatus.

A method and an apparatus to analyze two measured signals that are modeled as containing desired and undesired portions such as noise, FM and AM modulation. Coefficients relate the two signals according to a model defined in accordance with the present invention. In one embodiment, a transformation is used to evaluate a ratio of the two measured signals in order to find appropriate coefficients. The measured signals are then fed into a signal scrubber which uses the coefficients to remove the unwanted portions. The signal scrubbing is performed in either the time domain or in the frequency domain. The method and apparatus are particularly advantageous to blood oximetry and pulserate measurements. In another embodiment, an estimate of the pulserate is obtained by applying a set of rules to a spectral transform of the scrubbed signal. In another embodiment, an estimate of the pulserate is obtained by transforming the scrubbed signal from a first spectral domain into a second spectral domain. The pulserate is found by identifying the largest spectral peak in the second spectral domain.

Signal processing apparatus and method

An intelligent, rule-based processor provides recognition of individual pulses in a pulse oximeter-derived photo-plethysmograph waveform. Pulse recognition occurs in two stages. The first stage identifies candidate pulses in the plethysmograph waveform. The candidate pulse stage identifies points in the waveform representing peaks and valleys corresponding to an idealized triangular wave model of the waveform pulses. At this stage, waveform features that do not correspond to this model are removed, including the characteristic dicrotic notch. The second stage applies a plethysmograph model to the candidate pulses and decides which pulses satisfies this model. This is done by first calculating certain pulse features and then applying different checks to identify physiologically acceptable features. Various statistics can then be derived from the resulting pulse information, including the period and signal strength of each pulse and pulse density, which is the ratio of the analyzed waveform segment that has been classified as physiologically acceptable.

Plethysmograph pulse recognition processor

Embodiments of the present disclosure include a handheld multi-parameter patient monitor capable of determining multiple physiological parameters from the output of a light sensitive detector capable of detecting light attenuated by body tissue. For example, in an embodiment, the monitor is capable of advantageously and accurately displaying one or more of pulse rate, plethysmograph data, perfusion quality, signal confidence, and values of blood constituents in body tissue, including for example, arterial carbon monoxide saturation (“HbCO”), methemoglobin saturation (“HbMet”), total hemoglobin (“Hbt”), arterial oxygen saturation (“SpO2”), fractional arterial oxygen saturation (“SpaO2”), or the like. In an embodiment, the monitor displays a line associated with a patient wellness level.

Noninvasive multi-parameter patient monitor

A distributed hierarchical evolutionary modeling and visualization of empirical data method and machine readable storage medium for creating an empirical modeling system based upon previously acquired data. The data represents inputs to the systems and corresponding outputs from the system. The method and machine readable storage medium utilize an entropy fonction based upon information theory and the principles of thermodynamics to accurately predict system outputs from subsequently acquired inputs. The method and machine readable storage medium identify the most information-rich (i.e., optimum) representation of a data set in order to reveal the underlying order, or structure, of what appears to be a disordered system. Evolutionary programming is one method utilized for identifying the optimum representation of data.

Distributed hierarchical evolutionary modeling and visualization of empirical data

The present invention relates to a digital image analysis method for automatically identifying an object in a background, characterizing the object by color by determining at least one interior point of the object, and displaying the object on a monitor in color corresponding to the natural color of the object and a digital image analysis method for displaying an object on a monitor in color. The methods are adaptive in that they create a new pallette for each image being processed. The system used to implement the methods is cost effective in that a black-and-white image processing board can be used in conjunction with a color filter and a color monitor.

Adaptive display system

The present invention relates to image analysis methods and systems for identifying objects in a background by generating a description, which may be either a histogram or co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver. The present invention includes recursive, iterative and parallel processing methods. The methods may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer.

Iterative method and system of identifying valid objects in a background of an image

The present invention relates to image analysis methods and systems for identifying objects in a background by generating a description, which may be either a histogram or co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver The present invention includes recursive, iterative and parallel processing methods The methods may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer

Adaptive vision system

Accessing the exterior points of an object is used in the area of object identification when it is important to use the information in the local exterior environment of an object in order to extract a feature which may be useful for object recognition. Examples of this type of feature which are important for recognizing and classifying objects occur in the area if bacterial detection. Adaptive classification is a way of making the analysis independent of variations in imaging conditions, such as lighting, positioning, electronic amplification, etc. Two general methods can be used to access the local exterior environment of an object, knowing the perimeter points of the object. In the first method, the shape of an annular exterior region around the object of interest can be made to follow the shape of the object itself. In the second method, a known exterior shape, such as a circle, is used to characterize the exterior contour region, approximating the shape of the object.

Akhileswar Ganesh Vaidyanathan

Papers

Distributed hierarchical evolutionary modeling and visualization of empirical data

Adaptive display system

Iterative method and system of identifying valid objects in a background of an image

Adaptive vision system

Methods for determining the exterior points of an object in a background