Image feature amount output device, image recognition device, the image feature amount output program, and image recognition program

Patent metadata

Field	Value
Publication number	US-2019392249-A1
Application number	US-201816480960-A
Country	US
Kind code	A1
Filing date	Jan 31, 2018
Priority date	Jan 31, 2017
Publication date	Dec 26, 2019
Grant date	—

Abstract

An image processing device converts an image that is a recognition object image to high-resolution, medium-resolution, and low-resolution images. The device sets the pixel of interest of the high-resolution image, and votes the co-occurrence in a gradient direction with offset pixels, the co-occurrence in the gradient direction pixels in the medium-resolution image, and the co-occurrence in the gradient direction pixels in the low-resolution image, to a co-occurrence matrix. The device creates such a co-occurrence matrix for each pixel combination and for each resolution. The device executes the process on each of the pixels of the high-resolution image, and creates a co-occurrence histogram wherein the elements of a plurality of co-occurrence matrices are arranged in a line. The device normalizes the co-occurrence histogram and extracts, as a feature quantity of the image, a vector quantity having as a component a frequency resulting from the normalization.

First claim

1 - 8 . (canceled)

9 . An image feature amount output device comprising:
an image input means for inputting an image; a resolution conversion means for converting a resolution of the input image; a gradient direction acquiring means for acquiring a luminance gradient directions of pixels included in the input image and the image obtained by converting the resolution; a pixel combination acquiring means for acquiring a combination of two pixels from the pixels included in the input image and the image obtained by converting the resolution; a co-occurrence acquiring means for acquiring a co-occurrence in the luminance gradient direction acquired by the gradient direction acquiring means with respect to the two pixels related to the acquired combination, using the acquired luminance gradient direction of each pixel; an occurrence frequency acquiring means for acquires distribution of an occurrence frequency of the co-occurrence acquired by the co-occurrence acquiring means while changing the combination of the pixel to be acquired in the pixel combination acquiring means; and an output means for outputting the distribution of the occurrence frequency of the co-occurrence acquired by the occurrence frequency acquiring means not including the distribution of the occurrence frequency with respect to the acquired luminance gradient direction, as a feature amount of the image.

10 . An image feature amount output device comprising:
an image input means for inputs an image; a resolution conversion means for converting a resolution of the input image; a pixel combination acquiring means for acquiring a combination of two pixels from the pixels included in the input image and the image obtained by converting the resolution; a co-occurrence acquiring means for acquires the co-occurrence in luminance gradient directions of the two pixels related to the acquired combination; an occurrence frequency acquiring means for acquiring distribution of an occurrence frequency of the co-occurrence to be acquired while changing the acquired combination of the pixels; and an output means for outputting the acquired distribution of the occurrence frequency of the co-occurrence, as feature amount of the image.

11 . The image feature amount output device according to claim 9 , wherein the pixel combination acquiring means acquires at least a combination of adjacent pixels over the whole image.

12 . The image feature amount output device according to claim 10 , wherein the pixel combination acquiring means acquires at least a combination of adjacent pixels over the whole image.

13 . The image feature amount output device according to claim 9 , wherein the pixel combination acquiring means acquires a combination of pixels having different resolutions.

14 . The image feature amount output device according to claim 10 , wherein the pixel combination acquiring means acquires a combination of pixels having different resolutions.

15 . The image feature amount output device according to claim 11 , wherein the pixel combination acquiring means acquires a combination of pixels having different resolutions.

16 . The image feature amount output device according to claim 12 , wherein the pixel combination acquiring means acquires a combination of pixels having different resolutions.

17 . The image feature amount output device according to claim 9 , wherein the pixel combination acquiring means acquires a combination of pixels having the same resolution for each resolution.

18 . The image feature amount output device according to claim 10 , wherein the pixel combination acquiring means acquires a combination of pixels having the same resolution for each resolution.

19 . The image feature amount output device according to claim 11 , wherein the pixel combination acquiring means acquires a combination of pixels having the same resolution for each resolution.

20 . The image feature amount output device according to claim 12 , wherein the pixel combination acquiring means acquires a combination of pixels having the same resolution for each resolution.

21 . An image recognition device comprising:
a reference feature amount acquiring means for acquiring a reference feature amount expressing a feature amount of a recognizing object with distribution of an occurrence frequency of co-occurrence in a luminance gradient direction; an object image acquiring means for acquiring an object image which is an object to be determined; an object image feature amount acquiring means for inputting the acquired object image into the image input means of the image feature amount output device according to claim 9 , and for acquiring a feature amount of the aforementioned object image; a determination means for determining whether or not the object image includes a recognizing object image by comparing the acquired reference feature amount and the acquired feature amount of the object image; and a result outputting means for outputting a result of the determination.

22 . An image recognition device comprising:
a reference feature amount acquiring means for acquiring a reference feature amount expressing a feature amount of a recognizing object with distribution of an occurrence frequency of co-occurrence in a luminance gradient direction; an object image acquiring means for acquiring an object image which is an object to be determined; an object image feature amount acquiring means for inputting the acquired object image into the image input means of the image feature amount output device according to claim 10 , and for acquiring a feature amount of the aforementioned object image; a determination means for determining whether or not the object image includes a recognizing object image by comparing the acquired reference feature amount and the acquired feature amount of the object image; and a result outputting means for outputting a result of the determination.

23 . An image feature amount output program realizing functions by using a computer, the functions comprising:
an image input function for inputting an image; a resolution conversion function for converting a resolution of the input image; a gradient direction acquiring function for acquiring a luminance gradient directions of pixels included in the input image and the image obtained by converting the resolution; a pixel combination acquiring function for acquiring a combination of two pixels from the pixels included in the input image and the image obtained by converting the resolution; a co-occurrence acquiring function for acquiring a co-occurrence in the luminance gradient direction acquired by the gradient direction acquiring function with respect to the two pixels related to the acquired combination, using the acquired luminance gradient direction of each pixel; an occurrence frequency acquiring function for acquires distribution of an occurrence frequency of the co-occurrence acquired by the co-occurrence acquiring function while changing the combination of the pixel to be acquired in the pixel combination acquiring function; and an output function for outputting the distribution of the occurrence frequency of the co-occurrence acquired by the occurrence frequency acquiring function not including the distribution of the occurrence frequency with respect to the acquired luminance gradient direction, as a feature amount of the image.

24 . An image recognition program realizing functions by using a computer, the functions comprising:
a reference feature amount acquiring function for acquiring a reference feature amount expressing a

Assignees

• Equos Res Co Ltd
• Kyushu Inst Tech

Inventors

• Yamada Hideo
• Kuno Kazuhiro
• Shibata Masatoshi
• Enokida Shuichi
• TAMUKOH Hakaru

Classifications

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V10/56

  relating to colour · CPC title

• G06V10/758

  Involving statistics of pixels or of feature values, e.g. histogram matching · CPC title

• G06T3/40

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G06T7/00

  Image analysis · CPC title