Abstract: A multi-neural net imaging apparatus and method for classification of image elements, such as biological particles. The multi-net structure utilizes subgroups of particle features to partition the decision space by an attribute or physical characteristic of the particle and/or by individual and group particle classification that includes an unknown category. Preprocessing and post processing enables heuristic information to be included as part of the decision making process. Preprocessing classifies particles as artifacts based on certain physical characteristics. Post processing enables the use of contextual information either available from other sources or gleaned from the actual decision making process to further process the probability factors and enhance the decisions.

Abstract: A method and apparatus for selecting the best focal position of an image in a field of view is based upon pixel values located in the image that correspond to locations defining an invariant optical property of the image. In the preferred embodiment, the invariant optical property of the image are pixels that form a "halo" that surround the boundary of an object and are contiguous and immediately adjacent thereto. It has been determined that a certain relationship should exist for this "halo" that surround the boundary of an object when the best focal position is selected.

Abstract: To identify the boundary pixels of a number of particles in the same field of view, an electrical image of the field of view is formed by a CCD raster scan device. The electrical signal from the CCD device is segmented and is digitized. The signals are processed such that the boundary pixels have non-zero values and are linked to one another. The values of the pixels are stored in a boundary memory addressable by a row signal and column signal. In an addressable index memory, a plurality of values are stored with each value being an address to the boundary memory where the pixels having the boundary are located. Finally, a location memory has the same addressable dimensions as the boundary memory. The location memory stores, in address locations corresponding to address locations in the boundary memory where the pixels having characteristics of interest are located, addresses to the addressable index memory.

Abstract: A method and apparatus for selecting the best focal position of an image in a field of view is based upon pixel values located in the image that correspond to locations defining an invariant optical property of the image. In the preferred embodiment, the invariant optical property of the image are pixels that form a "halo" that surround the boundary of an object and are contiguous and immediately adjacent thereto. It has been determined that a certain relationship should exist for this "halo" that surround the boundary of an object when the best focal position is selected.

Abstract: A method for quickly and easily identifying the five basic components of leukocyte cells: basophils, eosinophils, neutrophils, monocytes and lymphocytes is disclosed. The method measures the size of each of the cells. Computation of the quantile feature of the cells and their color is then made. BA and EO cells are differentiated from LY and MO and NE cells using the present method. BA and EO cells can also be differentiated from LY, MO, and NE cells using methods of the prior art. Once BA and EO cells have been differentiated from the five leukocyte cells, LY cells can be differentiated from MO and NE cells based upon the size of the LY cells. The average color intensity of the LY cells determined is then used as the threshold to differentiate MO cells from NE cells.

Abstract: A method and an apparatus for generating a plurality of parameters of an object in a field of view is disclosed. An electrical image of the field of view is formed. The electrical image is processed to form a plurality of different representations of the electrical image where each different representation is a representation of a different parameter of the field of view. The positional information, which represents the boundary of the object, is generated. In response to the positional information that represents the boundary of the object being generated, corresponding locations in each of the different representations is traced. The different parameters from each of the different represents are calculated as the locations are traced in each of the different representations.

Abstract: The present invention relates to a method and an apparatus for identifying an object under examination. The object has a discernible boundary. An image of the object is first formed. The image is segmented to form a plurality of pixels. The boundary of the object under examination in the image is then detected. The parameters of the pixels measured within the boundary detected are formed in an ordered sequence:P.sub.1 . . . P.sub.k . . . P.sub.Nwhere P.sub.1 is the first value of the parameter of the pixel within the boundary detected;where P.sub.N is the last value of the parameter of the pixel within the boundary detected;N is the total number of pixels within the boundary detected; and k is the index to the N pixels. The P.sub.k data point is determined such that k, the index satisfies the following relationship: ##EQU1## M--total number of quantile partitions i-i.sup.th fraction of partition or i.sup.th quantile partition. The object under examination is identified based upon the P.sub.

Abstract: A method of identifying a plurality of different types of particles in the field of view is disclosed. A first parameter is measured for each of the plurality of different particles. One of the type of particles is identified based upon the first parameter measured. Once the one type of particle is identified, a second parameter, different from the first parameter, is then measured for the one type of particle. The other types of particles in the field of view can be identified based upon the second parameter associated with the one type of particle which has been identified. In one example, color is first used to differentiate various different particles in the field of view and to identify one particular type of particle. Thereafter, a morphological parameter, such as size, associated with the one type of particle identified is measured.

Abstract: A and an apparatus method for quickly and easily identifying the five basic components of leukocyte cells: basophils, eosinophils, neutrophils, monocytes and lymphocytes is disclosed. The method measures the size of each of the cells. Computation of the quantile feature of the cells and their color is then made. BA and EO cells are differentiated from LY and MO and Ne cells using the present method. BA and EO cells can also be differentiated from LY, MO, and Ne cells using methods of the prior art. Once BA and EO cells have been differentiated from the five leukocyte cells, LY cells can be differentiated from MO and NE cells based upon the size of the LY cells. The average color intensity of the LY cells determined is then used as the threshold to differentiate MO cells from NE cells.

Abstract: A method and an apparatus for generating a plurality of parameters of an object in a field of view is disclosed. An electrical image of the field of view is formed. The electrical image is processed to form a plurality of different representations of the electrical image where each different representation is a representation of a different parameter of the field of view. The positional information, which represents the boundary of the object, is generated. In response to the positional information that represents the boundary of the object being generated, corresponding locations in each of the different representations is traced. The different parameters from each of the different represents are calculated as the locations are traced in each of the different representations.

Abstract: A passive method for selecting the best focal position from a plurality of focal positions for a lens focussing on an image in a field of view is disclosed. The lens forms an image at a first position. The image is segmented to form a plurality of pixels. A histogram of the intensity of light at each of the pixels in the image is determined. A cumulative histogram is developed therefrom. A sharpness value is determined from the cumulative histogram. The sharpness value is the intensity of light that corresponds to the smallest cumulative pixel number having a non-zero intensity of light value. The lens is then moved to a new position and another sharpness for the new position is determined. From the plurality of positions moved by the lens, the smallest or lowest sharpness value is chosen and the position that corresponds to that smallest or lowest sharpness value is the position that represents the best focal position.

Abstract: Fabric such as textile material is automatically inspected at high speed by diffraction of light techniques. The fabric is moved through a plane and irradiated with monochromatic light of given cross sectional area sufficient to encompass a large number of warp and fillings making up the fabric. The diffraction pattern developed after the beam has passed through the fabric is detected and various regions of this diffraction pattern are processed to provide data indicative of the quality of the fabric. The major regions involved in the diffraction pattern include the developed central lobe and first order side lobes along orthogonal axes normal to the directions of the warps and filling threads of the fabric.

Abstract: A reference diffraction pattern is generated by radiating an invariant physical characteristic such as a fingerprint with coherent light, this reference diffraction pattern being converted by a detector into a reference electrical function which is stored. A person to be identified then has a corresponding invariant physical characteristic such as his fingerprint radiated by coherent light to cause generation of a sample diffraction pattern. The frequency domain of the entire sample diffraction pattern is detected simultaneously to provide a sample electrical function. The reference electrical function in storage is then compared with the sample electrical function and if a correlation exists within a given tolerance, it is known that the person from which the sample electrical function is derived corresponds to the person from which the reference electrical function was derived. The invariant physical characteristics may be fingerprints as mentioned, or signatures, or combinations of both.