초록 ▼

An apparatus which can acquire, readout and perceive a scene based on the insertion, or etching of photosensitive elements into or on a transparent or semi-transparent substrate such as glass. The substrate itself acts as the optical device which deflects the photons incident to the reflected image

An apparatus which can acquire, readout and perceive a scene based on the insertion, or etching of photosensitive elements into or on a transparent or semi-transparent substrate such as glass. The substrate itself acts as the optical device which deflects the photons incident to the reflected image into the photosensitive elements. Photosensitive elements are interconnected together by a transparent or opaque wiring. A digital neural memory can be trained to recognize specific scenery such as a human face, an incoming object, a surface defect, rain drops on a windshield and more. Other applications include image-perceptive car headlight and flat panel display detecting and identifying the viewer's behavior (gaze tracking, face recognition, facial expression recognition and more). Yet another application includes sliding doors perceiving the direction and speed of an individual coming towards that door. Yet another application includes permanent damage detection (texture change) in dam, bridge or other manmade construction.

대표청구항 ▼

We claim: 1. An image recognition device comprising: a sensing area embedded in or positioned on a transparent or semi-transparent substrate; and a processing element coupled with said sensing area, said processing element being embedded in or positioned on the substrate; wherein said transparent o

We claim: 1. An image recognition device comprising: a sensing area embedded in or positioned on a transparent or semi-transparent substrate; and a processing element coupled with said sensing area, said processing element being embedded in or positioned on the substrate; wherein said transparent or semi-transparent substrate constitutes an optical interface between an incident image to be sensed and a sensing pixel of said sensing area. 2. The image recognition device as recited in claim 1, wherein said sensing area is transparent or semi-transparent. 3. The image recognition device as recited in claim 1, wherein said substrate comprises glass, plexi-glass or other transparent material. 4. The image recognition device as recited in claim 1, wherein said sensing area comprises one or more photo-sensitive elements, and said processing element includes one or more cognitive memory elements, wherein each said photo-sensitive element is configured to output a signal based on light received at an input, and each said cognitive memory element is configured to recognize a pattern from said signals output from said photo-sensitive elements. 5. The image recognition device as recited in claim 4, wherein said cognitive memory elements are trainable. 6. The image recognition device as recited in claim 4, wherein each said cognitive memory element comprises a plurality of neurons coupled on an input side thereof by a multiplexed input bus and on an output side thereof by an output bus, each said neuron being taught with a knowledge, said knowledge allowing the corresponding neuron to recognize a signal and perform a decision. 7. The image recognition device as recited in claim 1, wherein said substrate includes a plurality of lens portions, each lens portion providing an optical interface with a sensing pixel or pixel area of said image recognition device. 8. The image recognition device as recited in claim 7, wherein each lens portion is formed by etching of said substrate. 9. The image recognition device as recited in claim 1, wherein the image recognition device includes a plurality of the sensing areas organized in an array. 10. An image recognition device comprising: a plurality of cognitive sensors positioned on a transparent or semi-transparent substrate, each sensor comprising: a photo sensitive element; and a trainable cognitive memory cell associated to the photosensitive element; a plurality of optical interfaces formed on said substrate each optically coupled with a corresponding one of said plurality of cognitive sensors. 11. The image recognition device as recited in claim 10, wherein said optical interfaces are lenses formed by etching said substrate at position near each said cognitive sensor. 12. The image recognition device as recited in claim 10, wherein each cognitive sensor is trainable and configured to recognize patterns based on incident light. 13. The image recognition device as recited in claim 10, wherein each said cognitive memory element comprises a plurality of neurons coupled on an input side thereof by a multiplexed input bus and on an output side thereof by an output bus, each said neuron being taught with a knowledge, said knowledge allowing the corresponding neuron to recognize a signal and perform a decision. 14. The image recognition device as recited in claim 10, wherein said substrate comprises glass, plexi-glass, or other transparent material. 15. The image recognition device as recited in claim 13, wherein each cognitive memory cell is taught to recognize a different portion of an image, and said plurality of cognitive memory cells are configured to operate collectively to recognize said image. 16. The image recognition device as recited in claim 15, wherein said cognitive sensors are configured to output a signal upon the recognition of said image. 17. The image recognition device as recited in claim 10, wherein said cognitive sensors operate in parallel at low frequencies. 18. The image recognition device as recited in claim 10, wherein the cognitive sensors operate at very low current. 19. An image recognition device comprising: a transparent or semi-transparent substrate; cognitive sensing means for sensing patterns of incident light and outputting a signal based on the sensed patterns, said cognitive sensing means being embedded into said substrate; and optical interface means for providing an optical interface to said cognitive sensing means. 20. The image recognition device as recited in claim 19, wherein said cognitive sensing means comprises a plurality of photo-detectors and a plurality of cognitive memory cells, wherein each said photo-detector is configured to output a signal based on light received at an input, and each said cognitive memory cell is configured to recognize a pattern from said signals output from said photo-detectors. 21. The image recognition device as recited in claim 19, wherein said optical interface means comprises a plurality of lenses formed in said substrate. 22. The image recognition device as recited in claim 19, wherein said cognitive sensing means comprises: a plurality of cognitive sensors, each comprising: a photo sensitive element; and a trainable cognitive memory cell associated to the photosensitive element. 23. The image recognition device as recited in claim 22, wherein each said cognitive memory cell comprises a plurality of neurons coupled on an input side thereof by a multiplexed input bus and on an output side thereof by an output bus, each said neuron being taught with a knowledge, said knowledge allowing the corresponding neuron to recognize a signal and perform a decision. 24. The image recognition device recited in claim 19, wherein said cognitive sensing means performs image recognition operations digitally without a software program through a plurality of parallel elements each having self contained, autonomous behavior. 25. The image recognition device as recited in claim 1, wherein the image recognition device is configured to output a wireless output signal. 26. The image recognition device as recited in claim 10, wherein each cognitive sensor is configured to send and receive wireless signals. 27. The image recognition device as recited in claim 19, wherein cognitive sensing means is configured to send and receive wireless signals. 28. The image recognition device as recited in claim 1, wherein the device is powered wirelessly. 29. The image recognition device as recited in claim 10, wherein the device is powered wirelessly. 30. The image recognition device as recited in claim 19, wherein the device is powered wirelessly. 31. An image recognition device comprising a combination of neurons with a sensor and data presentation logic, wherein said combination is embedded in or positioned on a transparent or semi-transparent substrate. 32. An image recognition method comprising steps of: embedding in or depositing on a transparent or semi-transparent substrate, cognitive sensing device configured to sense patterns of incident light and outputting a signal based on the sensed patterns; and providing an optical interface element configured to provide an optical interface to said cognitive sensing device. 33. The image recognition method as recited in claim 32, wherein said cognitive sensing device comprises a plurality of photo-detectors and a plurality of cognitive memory cells, wherein each said photo-detector is configured to output a signal based on light received at an input, and each said cognitive memory cell is configured to recognize a pattern from said signals output from said photo-detectors. 34. The image recognition method as recited in claim 32, further comprising a step of providing a plurality of lenses formed in or deposited on said substrate as part of said optical interface element. 35. The image recognition method as recited in claim 32, wherein said cognitive sensing device comprises: a plurality of cognitive sensors, each comprising: a photo sensitive element; and a trainable cognitive memory cell associated to the photosensitive element. 36. The image recognition method as recited in claim 35, wherein each said cognitive memory cell comprises a plurality of neurons coupled on an input side thereof by a multiplexed input bus and on an output side thereof by an output bus, each said neuron being taught with a knowledge, said knowledge allowing the corresponding neuron to recognize a signal and perform a decision. 37. An image recognition method comprising: using a plurality of optical interfaces embedded in or provided on a transparent or semi-transparent substrate to provide an optical path to a plurality of sensing elements embedded in or provided on said substrate, and processing in parallel signals generated from said plurality of sensing elements in a plurality of processing elements each coupled to one of said sensing elements and each embedded in or provided on said substrate.