Sensor-synchronized spectrally-structured-light imaging

Patent metadata

Field	Value
Publication number	US-2016187199-A1
Application number	US-201514836878-A
Country	US
Kind code	A1
Filing date	Aug 26, 2015
Priority date	Aug 26, 2014
Publication date	Jun 30, 2016
Grant date	—

Abstract

An image capture device, such as a smartphone or point of sale scanner, is adapted for use as an imaging spectrometer, by synchronized pulsing of different LED light sources as different image frames are captured by the image sensor. A particular implementation employs the CIE color matching functions, and/or their orthogonally transformed functions, to enable direct chromaticity capture. These and various other configurations of spectral capture devices are employed to capture spectral images comprised of spectral vectors having multi-dimensions per pixel. These spectral images are processed for use in object identification, classification, and a variety of other applications. Particular applications include produce (e.g., fruit or vegetable) identification. A great variety of other features and arrangements are also detailed.

First claim

1 . An apparatus comprising:
an imaging apparatus for obtaining pixels sampled from a scene, the pixels each comprising an N-D spectral vector; a digital signal processing device in communication with the imaging apparatus for computing a spatial relationship function of pixels of the N-D spectral vector, sampled from different locations of the object; and a classifier for classifying the object based on the N-D spectral vector and output of the spatial relationship function to ascertain class of the object in the scene.

2 . The apparatus of claim 1 wherein the imaging apparatus samples pixels under different illumination to obtain the N-D spectral vector, comprising N different spectral samples per pixel.

3 . The apparatus of claim 1 wherein the scene comprises at least one produce item, and the classifier classifies the produce item based on the N-D spectral vector and output of the spatial relationship function.

4 . The apparatus of claim 1 wherein the spatial relationship function comprises a function of values of pixels at 2 or more spatial dimensions.

5 . The apparatus of claim 4 wherein the spatial relationship function comprises differences of values of the pixels at different directions and scales.

6 . The apparatus of claim 1 including a programmed processor for computing spectral distribution values from N-D spectral vectors of pixels, and inputting the spectral distribution values to the classifier for classifying the object based on the spectral distribution values.

7 . The apparatus of claim 1 including a programmed processor for computing texture feature distribution values from an image captured of the scene, and inputting the texture feature distribution values to the classifier for classifying the object based on the texture feature distribution values.

8 . The apparatus of claim 7 including a programmed processor for computing spectral distribution values from N-D spectral vectors of pixels, and inputting the spectral distribution values to the classifier for classifying the object based on the spectral distribution values.

9 . The apparatus of claim 1 wherein the imaging apparatus comprises:
LED arrays;
a camera for capturing images of the scene in a field of view;
an LED controller coupled to the LED arrays for sending LED drive signals to LEDs of the LED arrays;
a camera and light source controller coupled to the camera to issue control signals for image capture synchronized with strobe control signals to the LED controller, which, responsive to the strobe control signals, issues the LED drive signals to the LEDs; and
diffusers positioned relative to the LED arrays to diffuse light from the LED arrays prior to the light entering the field of view.

10 . The apparatus of claim 9 wherein the LED arrays are arranged in rows and columns.

11 . The apparatus of claim 1 wherein the imaging apparatus comprises:
LEDs arranged in a cluster and positioned to project light from the LEDs into an aperture of an optical system comprising a reflector shaped to direct the light into a beam and through a lens;
a camera for capturing images of the scene in a field of view;
an LED controller coupled to the LEDs for sending LED drive signals to the LEDs;
a camera and light source controller coupled to the camera to issue control signals for image capture synchronized with strobe control signals to the LED controller, which, responsive to the strobe control signals, issues the LED drive signals to the LEDs.

12 . A method of recognizing an object comprising:
obtaining pixels sampled from a scene, the pixels each comprising an N-D spectral vector, the pixels being sampled under different illumination to obtain the N-D spectral vector, comprising N different spectral samples per pixel; computing a spatial relationship function of pixels of the N-D spectral vector, sampled from different locations of an object in the scene; and classifying the object based on the N-D spectral vector and the spatial relationship.

13 . The method of claim 12 wherein the scene comprises at least one produce item, and the act of classifying classifies the produce item based on the N-D spectral vector and the spatial relationship.

14 . The method of claim 12 wherein the spatial relationship function comprises a function of values of pixels at 2 or more spatial dimensions.

15 . The method of claim 14 wherein the spatial relationship function comprises differences of values of the pixels at different directions and scales.

16 . The method of claim 12 including:
executing a programmed processor to compute spectral distribution values from N-D spectral vectors of pixels, and classifying the object based on the spectral distribution values and the spatial relationship.

17 . The method of claim 12 including:
executing a programmed processor to compute texture feature distribution values from an image captured of the scene, and classifying the object based on the texture feature distribution values.

18 . The method claim 17 including:
executing a programmed processor to compute spectral distribution values from N-D spectral vectors of pixels, and classifying the object based on the spectral distribution values.

Assignees

• Digimarc Corp

Inventors

• Brunk Hugh L
• Rhoads Geoffrey B
• Archer Cynthia
• Conner Arlie

Classifications

• G06V20/66

  Trinkets, e.g. shirt buttons or jewellery items (recognising microscopic objects G06V20/69) · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/24323

  Tree-organised classifiers · CPC title

• H04N25/134

  based on three different wavelength filter elements · CPC title

• H04N23/74

  by influencing the scene brightness using illuminating means · CPC title