Abstract: A system, method, and computer program product for a search engine of Boolean nature wherein a multiplicity of key words are searched through a database. The results of each key word search become the database for searching with the next key word. In a normal Boolean search documents not found to contain a searched key word are immediately disposed of. In this method documents not containing the key word being searched are held until it has been determined if other documents containing the key word have been found. If so then the documents not containing the key word are disposed of; if not, all the documents of the database being searched are retained and become the database to be searched by the next word. Every key word is searched through the database resulting from the previous search. There are no search failures and results are always generated.

Abstract: A system, method and computer program product for a search engine utilizing a large number of key words or phrases, and having the search engine program, in an initial search, individually search each of the key words through an initial database. Documents found as a result of each individual key word search are placed in a smaller more relevant database, after eliminating duplicate documents. Each document will contain at least one of the key words being searched. In a secondary search the remainder of the key words are searched through each document in the smaller more relevant database. The search engine notes the occurrence of any key word in each document without regard to frequency of occurrence. A relevancy factor for each document is determined based on the percentage of the total individual key words, disregarding frequency, that appear in each document. The cumulative total of key word appearances for all key words in each document is then determined.

Abstract: Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image.

Abstract: Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image.

Abstract: Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image.

Abstract: Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image.