Igor V Ternovskiy

6487312, Nov 26, 2002

Dec 21, 2000

09/745392

Andrew Kostrzewski - Garden Grove CA
Igor Ternovskiy - Rancho Palos Verdes CA
Tomasz P. Jannson - Torrance CA

Physical Optics Corporation - Torrance CA

G06K 936

382232, 382241, 382233, 35842616

Methods and apparatuses for still image compression, video compression and automatic target recognition are disclosed. The method of still image compression uses isomorphic singular manifold projection whereby surfaces of objects having singular manifold representations are represented by best match canonical polynomials to arrive at a model saved and compressed using standard lossy compression. The coefficients from the best match polynomial together with the difference data, if any, are then compressed using lossless compression. The method of motion estimation for inhanced video compression sends I frames on an âas neededâ basis, based on comparing the error between segments of a current frame and a predicted frame. If the error exceeds a predetermined threshold, which can be based on program content, the next frame sent will be an I frame. The method of automatic target recognition (ATR) including tracking, zooming, and image enhancement, uses isomorphic singular mainfold projection to separate texture and sculpture portions of an image.

7747085, Jun 29, 2010

Dec 21, 2000

09/745363

Andrew Kostrzewski - Garden Grove CA, US
Igor Ternovskiy - Rancho Palos Verdes CA, US
Tomasz P. Jannson - Torrance CA, US

Physical Optics Corporation - Torrance CA

G06K 9/36

382232

Methods and apparatuses for still image compression, video compression and automatic target recognition are disclosed. The method of still image compression uses isomorphic singular manifold projection whereby surfaces of objects having singular manifold representations are represented by best match canonical polynomials to arrive at a model representation. The model representation is compared with the original representation to arrive at a difference. If the difference exceeds a predetermined threshold, the difference data are saved and compressed using standard lossy compression. The coefficients from the best match polynomial together with the difference data, if any, are then compressed using lossless compression. The method of motion estimation for enhanced video compression sends I frames on an “as-needed” basis, based on comparing the error between segments of a current frame and a predicted frame. If the error exceeds a predetermined threshold, which can be based on program content, the next frame sent will be an I frame.

20020095513, Jul 18, 2002

Jan 16, 2001

09/760614

Freddie Lin - Redondo Beach CA, US
Igor Ternovskiy - Rancho Palos Verdes CA, US

G06F015/173
G06F015/16

709/238000, 709/247000

A method and apparatus for compressing and transmitting data across a network. Packets of data are received. The packets of data are combined based on packet header destination information to form a first combined file. The first combined file is compressed to form a first compressed file. The first compressed file is transmitting across the network. The first compressed file is repacketized to form a repacketized first compressed file and the repacketized first compressed file is transmitted across the network. The packets combined to form the first combined file have headers addressed to the same first subnetwork and the first subnetwork comprises a plurality of users. Headers addressed to the first subnetwork are inserted on the packets of the repacketized first compressed file. A second group of packets of data with headers addressed to a second subnetwork is selected. the second group of packets of data is combined to form a second combined file. The second combined file is compressed and transmitted.

20020176624, Nov 28, 2002

Dec 21, 2000

09/745354

Andrew Kostrzewski - Garden Grove CA, US
Igor Ternovskiy - Rancho Palos Verdes CA, US
Tomasz Jannson - Torrance CA, US

PHYSICAL OPTICS CORPORATION

G06K009/34
G06K009/36
G06K009/46

382/173000, 382/284000, 382/243000

Methods and apparatuses for still image compression, video compression and automatic target recognition are disclosed. The method of still image compression uses isomorphic singular manifold projection whereby surfaces of objects having singular manifold representations are represented by best match canonical polynomials to arrive at a model representation. The model representation is compared with the original representation to arrive at a difference. If the difference exceeds a predetermined threshold, the difference data are saved and compressed using standard lossy compression. The coefficients from the best match polynomial together with the difference data, if any, are then compressed using lossless compression. The method of motion estimation for enhanced video compression sends I frames on an “as-needed” basis, based on comparing the error between segments of a current frame and a predicted frame. If the error exceeds a predetermined threshold, which can be based on program content, the next frame sent will be an I frame. The method of automatic target recognition (ATR) including tracking, zooming, and image enhancement, uses isomorphic singular manifold projection to separate texture and sculpture portions of an image. Soft ATR is then used on the sculptured portion and hard ATR is used on the texture portion.

20080159604, Jul 3, 2008

Dec 30, 2005

11/323877

Allan Wang - Irvine CA, US
Igor Ternovskiy - Rancho Palos Verdes CA, US

G06K 9/00
A61B 5/05

382128, 600410, 600407

Apparatus and method for determining an extent of vascularization in which a digitaldigitalized representation of blood vessels in a selected area is generated; one or more statistical quantative measures for the blood vessels in the selected area are calculated; and the one or more statistical quantative measures are compared to corresponding statistical standards to determine an extent of vascularization. The statistical quantative measures may include the density of branch points and the density of end points in a skeleton representing the blood vessels and a fractal dimension for the skeleton.

6167155, Dec 26, 2000

Jul 28, 1997

8/901832

Andrew Kostrzewski - Garden Grove CA
Igor Ternovskiy - Rancho Palos Verdes CA
Tomasz P. Jannson - Torrance CA

Physical Optics Corporation - Torrance CA

G06K 936

382232

Methods and apparatuses for still image compression, video compression and automatic target recognition are disclosed. The method of still image compression uses isomorphic singular manifold projection whereby surfaces of objects having singular manifold representations are represented by best match canonical polynomials to arrive at a model representation. The model representation is compared with the original representation to arrive at a difference. If the difference exceeds a predetermined threshold, the difference data are saved and compressed using standard lossy compression. The coefficients from the best match polynomial together with the difference data, if any, are then compressed using lossless compression. The method of motion estimation for enhanced video compression sends I frames on an "as-needed" basis, based on comparing the error between segments of a current frame and a predicted frame. If the error exceeds a predetermined threshold, which can be based on program content, the next frame sent will be an I frame.