# US 2008/0187178 A1 · Detecting and tracking objects in images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2008/0187178 A1 - Document ID: US20080187178A1 - Status: Published application - Kind: A1 - Application number: 12/078,852 - Filed: 2008-04-07 - Published: 2008-08-07 - Earliest claimed: 2005-01-07 - Assignees: GestureTek, Inc. - Inventors: Atid Shamaie - Web page: https://patentgrep.com/patent/US20080187178A1 ## CPC - G06V 40/107: {Static hand or arm} - G06F 18/2135: based on approximation criteria, e.g. principal component analysis - G06F 18/2413: based on distances to training or reference patterns - G06V 10/764: using classification, e.g. of video objects - G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods} - G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract According to one disclosed method, coordinates in a multi-dimensional space are determined for an image point characterizing a particular object. An equation describing a model in the space is provided. The model is characteristic of a set of training images of one or more other objects. The coordinates are applied to the equation to determine a distance between the image point and the model. Based on the determined distance, a determination is made as to whether the particular object matches the one or more other objects. A set of training images may be received. A multi-dimensional space (e.g., eigenspace) may be determined based on the set of training images. A set of training points may be generated by projecting the set of training images into the multi-dimensional space. An equation describing a model in the multi-dimensional space that is characteristic of the set of training points may be determined. ## Claims ### Claim 1 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, an object touching the surface; determine whether the detected object is of a predetermined object type based on dimensions of the detected object; and generate a user input to a computer application based on the detected object, if it is determined that the detected object is of the predetermined object type. ### Claim 2 (depends on 1) The computer program product of claim 1, wherein the electromagnetic radiation is projected onto a first side of the surface, and wherein the object touches a second side of the surface, and wherein the first side is obverse to the second side. ### Claim 3 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, at least first and second objects adjacent to the surface; designate one of the at least first and second objects as a control object based on dimensions of the first and second objects; and generate a user input to a computer application using the control object. ### Claim 4 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, at least first and second objects touching the surface; recognize the first and second objects based on dimensions of the first and second objects; and generate a user input to a computer application based on the recognized first and second object. ### Claim 5 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, at least first and second objects touching the surface; recognize, using a trained recognition model, the at least first and second objects as control objects, the recognition model being trained to identify the control objects based on an appearance of the at least first and second objects; and generate, using the control objects, a user input to a computer application. ### Claim 6 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, an input object touching the surface; compare the input object to a modeled input set of training images of a control object, the input set being modeled as a cone and a tail in an eigenspace; determine whether the detected object is the control object based on comparing the input object to the modeled cone or tail; and generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object. ### Claim 7 A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to: project electromagnetic radiation onto a surface; detect, using the projected electromagnetic radiation, an input object touching the surface; compare the input object to a modeled input set of training images of a control object, the input set being modeled in an eigenspace using a general equation for a three-dimensional quadratic surface; determine whether the detected object is the control object based on comparing the input object to the modeled input set; and generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.