Abstract: Recognizable data storage apparatus stores an image feature parameter of an object and its classification result for those objects for which said classification results are evaluated as having high reliability and recognizable and for which a classification result is outputted by first pattern recognition apparatus, and recognition suspension data storage apparatus stores an image feature parameter for those objects for which said classification results are evaluated as having low reliability and as being suspended from recognition. Pattern recognition method constitution apparatus constructs second pattern recognition apparatus on the basis of the classification result stored in the recognizable data storage apparatus, and re-classification is conducted for those objects recognition of which is to be suspended. A neural network, for example, is used for the second pattern recognition apparatus.

Abstract: In a pattern recognition system provided with a pattern recognition processing unit having a network structure constructed of an input layer for inputting a feature parameter of a subject under recognition as input information an intermediate layer for processing the input information and an output layer for outputting a processed result output values of respective output nodes for constituting the output layer, corresponding to the input information, are compared with each other by the pattern recognition processing unit, and a classification item corresponding to the output node whose output value is maximum is stored into a storage unit as a recognized result with respect to the input information. The pattern recognition system is also provided with a reliability evaluating unit for setting a threshold with respect to an output value of each of the output nodes and for evaluating reliability of the recognized result based upon the output values of the respective output nodes.

Abstract: A flow type particle image analytical method for feeding a particles-suspended sample by surrounding it by a cleaning solution, imaging particles in the sample by irradiating light to it, and automatically classifying the particles in the sample by analyzing the picked-up particle images, wherein the method comprises a means for designating the kind of particles to be reviewed beforehand among the classified particles, a means for storing only particles which are automatically classified to the designated particle kind in a review image memory, a means for displaying particles of the same kind on a CRT display in batch so as to review particle images, and a means for classifying each of the displayed particles finally by an operator or for changing the particle name.

Abstract: Sample fluids including biological particles are mixed with a stain solution, and stained biological particles are fed into a flow through cell. Still frame images of the particles flowing through the flow-through cell are photographed by a television camera, and are processed for particle classification. Prior to such processing of biological particle images, a calibration coefficient is calculated using reference particles. The reference particles may include polystyrene resin which contains functional radicals such as sulfonic radicals, and are stained by mixing the suspended fluid containing these reference particles with the stain solution. The calibration coefficient is calculated according to the information on the stain in the still frame images, and is used to calibrate biological particle data.

Abstract: Dyeing agents which are excellent in visual recognition of discernible or tangible components in a sample cause no coagulation of proteins, sugars or glycoproteins dissolved in the sample. An apparatus for image analysis of flow type stain particles uses the dyeing agents, and particles of discernible components suspended in a flowing sample can be detected so that images of the particles can be efficiently photographed and the discernible components can thus be analyzed by image processing of the thus-obtained image.

Abstract: In a stained particle analyzing method and apparatus for staining a test sample containing suspended particles, shooting an image of the stained sample, and classifying the particles and computing the density from the shot image of the sample, the sample, which may not be analyzed precisely, is detected before the start of an image analyzing process. Only the sample, which will be analyzed precisely, is stained and subjected to the image analysis. Color information of the sample before the staining is detected and stored. Color information of an image of the sample shot after the staining is compensated based on the color information of the sample detected before the staining. The sort and density of the particles are classified and computed on the basis of the image after the color compensation.

Abstract: A cavity resonator having adjustably tunable resonant frequency in which tuning of the resonant frequency is carried out by means of a movable side plate, characterized in that contactor pieces supported by the edges of said movable side plate for realizing high frequency short-circuiting to a cavity wall, consist of metallic wires, each of which is wound in a coil shape preferably having a diameter that is no greater than the distance between the opposite side plate edges in which the coils are mounted.