CN115249271A

CN115249271A - Method and equipment for detecting and correcting image color cast and refrigerator

Info

Publication number: CN115249271A
Application number: CN202110458507.1A
Authority: CN
Inventors: 毕研华
Original assignee: Qingdao Haier Refrigerator Co Ltd; Haier Smart Home Co Ltd
Current assignee: Qingdao Haier Refrigerator Co Ltd; Haier Smart Home Co Ltd
Priority date: 2021-04-27
Filing date: 2021-04-27
Publication date: 2022-10-28
Also published as: WO2022228033A1

Abstract

The invention discloses a method, equipment and a refrigerator for detecting and correcting image color cast, wherein the method comprises the following steps: cutting a plurality of ROI (region of interest) areas of an image to be detected to obtain N ROI areas, wherein N is a positive integer larger than 1; performing color cast detection based on HSV space on the N areas respectively, and if at least one area in the N areas has color cast, judging that the image to be detected has color cast; and after the color cast of the image to be detected is judged, automatically correcting the color cast of the image by adjusting the brightness of light supplement lamps arranged around the camera. Compared with the prior art, the method for detecting and correcting the image color cast can quickly detect whether the image has color cast or not, and has high detection precision; and after detecting that the color cast of the image occurs, the brightness of the light supplement lamp is automatically adjusted, so that the color cast of the image is automatically corrected.

Description

Method and equipment for detecting and correcting image color cast and refrigerator

Technical Field

The invention relates to the field of household appliances, in particular to a method and equipment for detecting and correcting image color cast and a refrigerator.

Background

The color is one of the important features of the image, is also an important basis for image processing and analysis in general, and has a very important meaning for the research in the computer vision field such as target recognition and detection, image segmentation and video retrieval. The color of an object is determined by the reflectivity characteristic of the object, and because a human eye vision system has color constancy, the influence of factors such as illumination conditions on the color can be eliminated to a certain extent, but the imaging equipment does not have the 'adjusting' function, and can be influenced by factors such as the external light environment, the characteristics of imaging photosensitive components and the like, so that errors, namely 'color cast', exist between the image color and the real color of the object to a certain extent. Meanwhile, when the external light environment is too dark or too bright, the photosensitive component cannot acquire a normally exposed image, and the phenomenon of too dark or too explosion of image colors can also be caused. If image color cast is not detected and calibrated in time efficiently, then color-based image vision algorithms may not be able to proceed.

In the refrigerator field, when the light inside the refrigerator is sheltered from by colored plastic bag, lead to the colour of light to change, serious color cast can appear in the image of the inside shooting of refrigerator, and then influence the rate of accuracy of object identification in the image. In order to reduce the problem of the decrease in the image recognition accuracy caused by the above-mentioned situation, it is necessary to perform color cast detection and correction on a picture taken inside the refrigerator. However, the existing color cast detection theoretical method is large in calculation amount, time-consuming and low in accuracy for color cast detection of images shot inside a refrigerator.

Therefore, it is highly desirable to provide an efficient and accurate method for detecting and correcting color cast of an image inside a refrigerator.

Disclosure of Invention

The invention aims to provide a method and equipment for detecting and correcting image color cast and a refrigerator.

In order to achieve one of the above objects, an embodiment of the present invention provides a method for detecting and correcting color cast of an image, the method comprising:

cutting a plurality of ROI (region of interest) areas of an image to be detected to obtain N ROI areas, wherein N is a positive integer larger than 1;

performing color cast detection based on HSV space on the N areas respectively, and if at least one area in the N areas has color cast, judging that the image to be detected has color cast;

and after the color cast of the image to be detected is judged, automatically correcting the color cast of the image by adjusting the brightness of light supplement lamps arranged around the camera.

As a further improvement of an embodiment of the present invention, performing HSV space-based color cast detection on an area specifically includes:

reading in the region image in an RGB space;

converting the image of the RGB color channel into an HSV channel;

performing channel segmentation on the image, and segmenting the image into H, S, V channel data;

calculating the average value of the data of the three channels 5363 at H, S, V of all pixel points of the image respectively;

and if at least one of the three average values is not in the set value range, judging that the regional image has color cast.

As a further improvement of an embodiment of the present invention, the method further comprises:

when color cast does not occur in an image area, the initial average values of data of all the pixels in H, S, V of the image area are calculated, and the value range of the average value of all the pixels in three channels of the image area is set according to the three initial average values.

As a further improvement of an embodiment of the present invention, the "automatically correcting color shift of an image by adjusting the brightness of a fill-in light disposed around a camera" specifically includes:

the method comprises the steps that when the brightness of a light supplement lamp is gradually increased, a camera is controlled to shoot images periodically, and whether the shot images have color cast or not is detected;

and stopping increasing the brightness of the light supplementing lamp after detecting that the image shot by the camera has no color cast.

As a further improvement of an embodiment of the present invention, the light supplement lamp is a plurality of LED lamps distributed around the camera according to a certain rule.

As a further improvement of an embodiment of the present invention, a distance between the fill-in light and the camera is in a range of 20 to 40 cm.

and acquiring a shot image of a special yoghourt area in the refrigerator as an image to be detected, wherein the special yoghourt area comprises a bottle seat for placing yoghourt.

As a further improvement of an embodiment of the present invention, the N ROI regions are distributed around the bottle seat of the image to be detected.

In order to achieve one of the above objects, an embodiment of the present invention provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program operable on the processor, and the processor implements the steps of any one of the methods for detecting and correcting image color cast when executing the program.

In order to achieve one of the above objects, an embodiment of the present invention provides a refrigerator, which includes the electronic device.

Compared with the prior art, the method for detecting and correcting the image color cast can quickly detect whether the image has color cast or not, and has high detection precision; and after detecting that the color cast of the image occurs, the brightness of the light supplement lamp is automatically adjusted, so that the color cast of the image is automatically corrected.

Drawings

FIG. 1 is a flowchart illustrating a method for detecting and correcting color cast of an image according to the present invention.

Fig. 2 is a schematic diagram of the distribution of the ROI region in the image to be detected according to the present invention.

Fig. 3 is a partial structural view of the inside of the refrigerator of the present invention.

Wherein, 1, a refrigerator; 2. a special yogurt area; 3. a first bottle holder; 4. a second bottle holder; 5. a camera and a light supplement lamp; 6. an image to be detected; 7. an ROI area.

Detailed Description

The present invention will be described in detail below with reference to specific embodiments shown in the accompanying drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes in accordance with the embodiments are within the scope of the present invention.

A special yoghourt area is arranged in the refrigerator, and yoghourt can be monitored in a centralized manner. Generally, a bottle seat is arranged in a special yoghourt area, and yoghourt is placed in the bottle seat. In the process of monitoring the yoghourt in the bottle seat, image shooting and identification are required to be carried out on a special yoghourt area. However, sometimes the camera is shielded by a colored plastic bag or the like, so that the color of light changes, and the color cast of the shot image occurs, thereby affecting the accuracy of image recognition.

Therefore, the invention provides a method for detecting and correcting the color cast of an image, which can quickly detect whether the image has color cast or not and has high detection precision; and after detecting that the color cast of the image occurs, the brightness of the light supplement lamp is automatically adjusted, so that the color cast of the image is automatically corrected.

As shown in fig. 1, the method includes:

step S100: cutting a plurality of ROI areas of an image to be detected to obtain N ROI areas, wherein N is a positive integer larger than 1.

When the color cast detection is performed on the whole image, the detection efficiency is low, and the accuracy is low (for example, only 1/3 of the regions have color cast, and the color cast detection based on the whole image cannot detect the color cast), so that a plurality of ROI regions (regions of interest) of the image to be detected are cut, and N ROI regions larger than 1 are obtained. Because the size of the cut ROI area image is far smaller than that of the whole image, the color cast detection efficiency of the ROI area images is high, the detection speed is high, and the accuracy is high.

The method mainly aims at detecting the color cast of the image of the special yoghourt area in the refrigerator, so that the shot image of the special yoghourt area in the refrigerator is obtained as the image to be detected, wherein the special yoghourt area comprises a bottle seat for placing yoghourt.

Further, as shown in fig. 2, the N ROI areas are distributed around the bottle seat of the image to be detected. Because the bottle seat is used for placing the yoghourt, after the yoghourt is placed, the bottle seat is partially shielded by the yoghourt, and a stable environment cannot be provided for color cast detection. Therefore, the peripheral region of the bottle seat which is not shielded by the yoghourt is selected as the ROI region for detection, and the influence of the placed yoghourt can not be caused. And because these N ROI regional distribution are around the bottle seat, even the partial color cast that appears of image can detect, and the rate of accuracy of detection is high.

Step S200: and respectively carrying out color cast detection based on HSV space on the N areas, and if at least one area in the N areas has color cast, judging that the image to be detected has color cast.

If partial areas of the image to be detected have color cast, the accuracy of image identification of the partial areas with color cast will be reduced, so that in the detection process, as long as one area detects color cast, it is determined that the image to be detected has color cast, and the color cast of the image needs to be corrected.

If it is detected that the image has color cast, the user may also be notified to manually eliminate the abnormal condition (for example, if the camera is blocked by a colored plastic bag, the user may remove the colored plastic bag).

HSV (Hue, saturation) is a color space created by a.r. smith in 1978, also known as the hexagonal cone Model (Hexcone Model), based on the intuitive nature of color. The parameters of the colors in this model are: hue (H), saturation (S), lightness (V).

The color cast detection of the area image based on the HSV space specifically comprises the following steps:

step S210: reading in the region image in an RGB space.

The RGB color space is based on three basic colors of R (Red), G (Green) and B (Blue) and is superposed to different degrees to generate rich and wide colors, so the RGB color space is commonly called a three-primary-color mode.

Step S220: and converting the image of the RGB color channel into the HSV channel.

Data conversion of the image between the RGB color channel and the HSV channel is prior art, and is not described herein in detail.

Step S230: and (3) performing channel segmentation on the image, and segmenting the image into H, S, V three pieces of channel data respectively.

Step S240: and calculating the average value of the data of all pixel points of the image in H, S, V three channels respectively.

And calculating the average value of all pixel points of the image in the H channel data, the average value of all pixel points of the image in the S channel data and the average value of all pixel points of the image in the V channel data, wherein the three average values are used for representing the comprehensive values of the regional image in three channels.

Step S250: and if at least one of the three average values is not in the set value range, judging that the regional image has color cast.

And judging whether the three average values are all in a preset value range, and judging that the regional image has color cast as long as one average value is not in the preset value range.

Before the refrigerator leaves a factory, the initial average value of all pixel points of each region in each channel can be obtained through a shot picture, and the value range of the average value of all pixel points of three channels of the image region is set through the initial average value.

In a specific embodiment, when an image region has no color cast, initial average values of data of all pixels in H, S, V of the three channels of the image region are obtained, and value ranges of the average values of all pixels in the three channels of the image region are set according to the three initial average values.

Step S300: and after the color cast of the image to be detected is judged, automatically correcting the color cast of the image by adjusting the brightness of light supplement lamps arranged around the camera.

The light supplement lamp of the invention preferably adopts an LED lamp emitting white light, and when the LED lamp is gradually lightened, the gradually enhanced white light can weaken other colored light, thereby achieving the purpose of correcting color cast.

In a specific embodiment, the "automatically correcting color shift of an image by adjusting brightness of a fill-in light disposed around a camera" specifically includes:

step S310: and controlling the camera to periodically shoot images and detecting whether the shot images have color cast or not while gradually increasing the brightness of the light supplement lamp.

First, the brightness of the fill-in light is gradually increased, and at the same time, images are periodically (the interval between two adjacent periods is short) photographed, and whether the newly photographed image has color cast is detected by the method of step S100 and step S200.

Step S320: and stopping increasing the brightness of the light supplement lamp after detecting that the image shot by the camera has no color cast.

When the fact that the color cast does not occur in the image shot by the camera is detected, the quality of the image shot at present is proved to be up to the standard, and the image can be normally used for image recognition, so that the increase of the brightness of the light supplement lamp is stopped. And when the image recognition is finished, the light supplement lamp is turned off.

In the present invention, as shown in fig. 3, the special yogurt region includes a first bottle holder for placing yogurt, the camera and the light supplement lamp are disposed at the bottom of a second bottle holder, preferably, the camera and the light supplement lamp are on the same horizontal plane, and the light supplement lamp is a plurality of LED lamps regularly distributed around the camera. Specifically, a plurality of light filling lamps are rectangular or circular and are distributed, and the camera is arranged in the middle of the rectangle or the circle. And a plurality of light filling lamps emit downward parallel light beams, so that shadow is reduced or prevented while light filling is performed.

Further, the distance between the light supplement lamp and the camera is preferably within the range of 20-40 cm.

In a specific embodiment, a camera and a light supplement lamp are arranged at the bottom of a second bottle seat of the refrigerator, the camera is used for shooting an image of a special yoghourt area at the bottom of the second bottle seat, and the special yoghourt area comprises a first bottle seat for placing yoghourt. And taking the image shot by the camera as an image to be detected, and cutting the area around the bottle seat of the image to be detected to obtain N ROI (region of interest), wherein the N ROI is distributed as shown in figure 2. And then carrying out color cast detection based on HSV space on the N areas respectively, and if at least one area in the N areas has color cast, judging that the image to be detected has color cast. And after detecting that the color cast occurs in the image to be detected, gradually increasing the brightness of the light supplement lamp, periodically shooting the image, and continuously detecting whether the newly shot image has the color cast or not by adopting the color cast detection method. And stopping increasing the brightness of the light supplement lamp after detecting that the image shot by the camera has no color cast. And finally, after the image recognition is finished, turning off the light supplement lamp.

According to the method for detecting and correcting the image color cast, the regions around the bottle seat in the picture to be detected are cut to obtain N ROI regions, then the ROI regions are subjected to color cast detection based on HSV space, and finally the color cast detection result of the image to be detected is obtained according to the color cast detection result of each ROI region. And after detecting that the color cast of the image occurs, the brightness of the light supplement lamp can be automatically adjusted, and the color cast of the image is automatically corrected, so that the accuracy of image identification is not influenced by the color cast.

The invention further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program operable on the processor, and the processor implements any one of the steps of the method for detecting and correcting image color cast, that is, implements any one of the steps of the method for detecting and correcting image color cast.

The invention also provides a refrigerator comprising the electronic equipment.

Preferably, as shown in fig. 3, the refrigerator further includes a yogurt special area, a first bottle seat and a second bottle seat, a camera and a light supplement lamp are arranged at the bottom of the second bottle seat, the camera and the light supplement lamp are on the same horizontal plane, the light supplement lamp is a plurality of LED lamps distributed around the camera according to a rectangle, and the camera is arranged in the middle of the rectangle. And a plurality of light filling lamps emit downward parallel light beams, so that shadow is reduced or prevented while light filling is performed.

It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.

The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.

Claims

1. A method for detecting and correcting image color cast is characterized in that the method comprises the following steps:

2. The method for detecting and correcting image color cast according to claim 1, wherein performing color cast detection based on HSV space for a region specifically comprises:

reading the region image in an RGB space;

converting the image of the RGB color channel into an HSV channel;

calculating the average value of the data of all pixel points of the image in H, S, V three channels respectively;

3. The method of detecting and correcting image color cast according to claim 2, further comprising:

4. The method for detecting and correcting image color cast according to claim 1, wherein the "automatically correcting image color cast by adjusting brightness of a fill-in light disposed around a camera" specifically comprises:

and stopping increasing the brightness of the light supplement lamp after detecting that the image shot by the camera has no color cast.

5. The method for detecting and correcting image color cast according to claim 4, wherein:

the light filling lamp is a plurality of LED lamps distributed around the camera according to a certain rule.

6. The method for detecting and correcting image color cast according to claim 4, wherein:

the distance between the light supplement lamp and the camera is within the range of 20-40 cm.

7. The method of claim 1, further comprising:

8. The method for detecting and correcting image color cast according to claim 7, wherein:

the N ROI areas are distributed on the periphery of the bottle seat of the image to be detected.

9. An electronic device comprising a memory and a processor, the memory storing a computer program operable on the processor, wherein the processor implements the steps of the method for detecting and correcting image color cast according to any one of claims 1-8 when executing the program.

10. A refrigerator characterized in that it contains an electronic apparatus as claimed in claim 9.