CN115211578A

CN115211578A - Baking control method and device, baking equipment and storage medium

Info

Publication number: CN115211578A
Application number: CN202210838391.9A
Authority: CN
Inventors: 闫润强; 李奇峰; 宋季锟
Original assignee: Henan Xunfei Artificial Intelligence Technology Co ltd
Current assignee: Henan Xunfei Artificial Intelligence Technology Co ltd
Priority date: 2022-07-12
Filing date: 2022-07-12
Publication date: 2022-10-21
Anticipated expiration: 2042-07-12
Also published as: CN115211578B

Abstract

The application provides a baking control method, a baking control device, baking equipment and a storage medium, which can compare a baking target image corresponding to a current baking target with sample images in a sample image library, and determine a reference image matched with the baking target image from the sample images based on image difference between the baking target image and the sample images and baking state credibility of the sample images. According to the method and the device, the baking parameters of the baking target are adjusted according to the baking parameters corresponding to the reference image matched with the baking target image, so that the automatic adjustment of the baking parameters is realized, the influence of the experience and level of baking personnel on the baking quality is avoided, and the product quality is ensured.

Description

Baking control method and device, baking equipment and storage medium

Technical Field

The present application relates to the field of automatic control technologies, and in particular, to a baking control method and apparatus, a baking device, and a storage medium.

Background

For the production of certain products, the baking dehydration treatment of the baking target in the product production is an essential step in the product production process. For example, tobacco baking is a necessary process for cigarette processing, and the requirements of subsequent production steps such as cigarette packaging and the like can be met only by baking tobacco to reduce the moisture content in the tobacco.

At present, in the baking and dehydrating process of a baking target, in order to ensure the baking quality of the baking target, baking personnel are required to observe the color, moisture, shape and the like of the baking target, and then judge the baking state of the baking target according to experience and adjust parameters such as drying temperature, humidity and the like. However, the baking mode causes the baking quality to be greatly influenced by the experience and level of baking personnel, so that the baking quality is uneven, and the product quality is influenced.

Disclosure of Invention

Based on the above requirements, the application provides a baking control method, a baking control device, baking equipment and a storage medium, so as to solve the problem that the baking mode in the prior art affects the product quality.

The technical scheme provided by the application is as follows:

in one aspect, the present application provides a baking control method, including:

calculating the image difference between the baking target image and a sample image in a preset sample image library; wherein the sample image comprises an image of a sample baking target during baking;

selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image; the target moment is the moment when the sample image is shot;

and adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

Further, in the method described above, the baking target image includes an image group obtained by photographing the baking target from each photographing position; the sample image library comprises a plurality of sample image groups, and each sample image group comprises images obtained by shooting a sample baking target from each shooting position;

the calculating of the image difference between the baking target image and the sample image in the preset sample image library includes:

calculating the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group;

and determining the image difference degree of the baking target image and each sample image group based on the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

Further, in the method described above, the calculating a degree of difference between the baking target image and the image corresponding to the same photographing position in each of the sample image groups includes:

and calculating the image characteristic distance between the baking target image and the image corresponding to the same shooting position in each sample image group.

Further, in the method described above, the selecting a reference image matching the baking target image from the sample image library based on the image difference and the baking state reliability of the sample image includes:

and selecting the sample image group matched with the baking target image from the sample image library as a reference image based on the image difference degree and the baking state credibility of the sample image group.

Further, in the method described above, the selecting, from the sample image library, a sample image group matching the baking target image based on the image difference degree and the baking state reliability of the sample image group as a reference image includes:

calculating the product of the image difference and the baking state difference of each sample image group; a baking state difference degree of each sample image group representing a difference between a baking state determined from the baking parameters at the time of photographing the group of sample images and a baking state determined from the group of sample images; the baking state difference degree and the baking state reliability are in a negative correlation relationship;

and determining a sample image group matched with the baking target image from the sample image library according to the product corresponding to each sample image group as a reference image.

Further, in the method described above, the process of determining the baking status reliability of the sample image group includes:

acquiring a first baking state and a second baking state corresponding to each image in each sample image group; the first baking state is determined according to baking parameters when each image is shot, and the second state is determined according to each image;

calculating the baking state difference between the first baking state and the second baking state corresponding to each image;

and determining the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group.

Further, in the above method, the determining the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group includes:

determining the baking state difference corresponding to all the images in each sample image group and the sum of preset correction parameters as the baking state reliability of each sample image group; wherein the correction parameter is a positive number.

Further, in the method described above, the adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image includes:

judging whether the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image or not;

if the baking parameters of the baking target are different from the baking parameters corresponding to the reference image, the baking parameters of the baking target are adjusted until the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image.

Further, in the method described above, the target of baking comprises tobacco.

On the other hand, this application still provides a toast controlling means, includes:

the calculation module is used for calculating the image difference degree between the baking target image and the sample image in the preset sample image library; wherein the sample image comprises an image of a sample baking target during baking;

the selection module is used for selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters of the target moment and the baking state determined according to the sample image: the target moment is the moment when the sample image is shot;

and the adjusting module is used for adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

On the other hand, the application also provides baking equipment, which comprises a processor, a memory and a camera, wherein the memory and the camera are connected with the processor;

the camera is used for acquiring a baking target image;

the memory is used for storing a computer program and a sample image library, and the sample image and the baking state credibility information of the sample image are stored in the sample image library; wherein the sample image comprises an image of a sample baking target during baking; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image; the target moment is the moment when the sample image is shot;

the processor is used for calculating the image difference degree between the baking target image acquired from the camera and the sample image stored in the memory by running the computer program; selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; and adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

In another aspect, the present application further provides a storage medium, including: the storage medium has a computer program stored thereon, which when executed by a processor, implements the steps of the baking control method according to any one of the above.

According to the baking control method, the baking control device, the baking equipment and the storage medium, the baking target image corresponding to the current baking target can be compared with the sample images in the sample image library, and the reference image matched with the baking target image is determined from the sample images on the basis of the image difference degree between the baking target image and the sample images and the baking state credibility of the sample images. According to the method and the device, the baking parameters of the baking target are adjusted according to the baking parameters corresponding to the reference image matched with the baking target image, so that the automatic adjustment of the baking parameters is realized, the influence of the experience and level of baking personnel on the baking quality is avoided, and the product quality is ensured.

Further, the image difference degree can represent the difference degree between the baking target image and the sample image; the baking state reliability is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image, and the reliability of the baking state of the sample image can be represented, namely, the smaller the baking state difference determined by the two methods, the higher the reliability of the baking state of the sample image. The method and the device consider based on two angles of image difference and baking state credibility, select a reference image with small difference degree with the baking target image and high baking state reliability from the sample image library, and can adjust according to a more accurate adjustment direction when automatically adjusting the baking parameters of the baking target according to the corresponding baking parameters of the reference image, thereby further ensuring the product quality.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic flowchart of a baking control method according to an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of a baking oven provided in an embodiment of the present application;

FIG. 3 is a schematic diagram of a baking curve provided in the embodiments of the present application;

FIG. 4 is a schematic flowchart of a process for calculating an image difference between a baking target image and a sample image according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of another baking oven provided in the embodiment of the present application;

FIG. 6 is a schematic flow chart of determining a reference image from a sample image library according to an embodiment of the present disclosure;

FIG. 7 is a schematic flowchart illustrating a process for adjusting baking parameters of a baking target according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a toasting control device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a baking apparatus according to an embodiment of the present application.

Detailed Description

The technical scheme of the embodiment of the application is suitable for the application scene of controlling the baking state, and by adopting the technical scheme of the embodiment of the application, the automatic adjustment of the baking parameters can be realized, the influence of the baking experience and level of baking personnel on the baking quality is reduced, and the quality of baked products is ensured.

For example, the technical solution of the embodiment of the present application may be applied to hardware devices such as a hardware processor, or may be packaged into a software program to be executed, and when the hardware processor executes the processing procedure of the technical solution of the embodiment of the present application, or the software program is executed, the baking state may be controlled. The embodiment of the present application only introduces the specific processing procedure of the technical scheme of the present application by way of example, and does not limit the specific execution form of the technical scheme of the present application, and any technical implementation form that can execute the processing procedure of the technical scheme of the present application may be adopted by the embodiment of the present application.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The present embodiment proposes a baking control method, as shown in fig. 1, the method includes:

s101, calculating the image difference degree between the baking target image and a sample image in a preset sample image library.

The above-mentioned roasting target refers to an object to be roasted. The baking target can be placed in the baking box, and the baking of the baking target is realized by controlling the parameters such as temperature, humidity, wind speed and heating speed in the baking box. Tobacco is, for example, an important baking target in the production of cigarettes, and tobacco can be used as a baking target in the production of cigarettes.

The baking target image refers to an image of a baking target, and the baking target image can be acquired through a camera. Specifically, in order to guarantee the definition of the baking target image, the camera can be arranged on the inner wall of the baking oven, and the baking target image is shot from the inside of the baking oven.

Fig. 2 is a schematic structural diagram of a baking oven provided in an embodiment of the present application. For example, as shown in fig. 2, in order to prevent the camera 21 from being damaged by high temperature in the oven, a heat insulation shield 22 may be provided outside the camera 21. Specifically, the heat-insulating protective cover 22 is fastened to the inner wall 20 of the baking oven to form a heat-insulating protective space, and the camera 21 is installed in the heat-insulating protective space. Moreover, the heat insulation protective cover 22 is arranged, so that a certain distance is kept between the camera 21 and the baking target, the situation that the image is fuzzy due to the fact that the distance between the camera 21 and the baking target is too short is avoided, and the definition of the image is improved.

In addition, in order to avoid the situation that the image of the baking target is blurred due to the too close distance between the camera 21 and the baking target in the prior art, a mode that the baking target is not placed near the camera 21 is generally adopted, but in such a mode, a part of vacant space exists in the baking oven, the vacant space inside the baking oven is easy to form air vortex, and the flowability of the air is poor. However, in the baking process, parameters such as temperature and humidity in the baking oven need to be changed continuously to achieve the purpose of improving the baking quality, and since the fluidity of air in the partial vacant space is poor, the baking parameters such as temperature and humidity are changed slowly, when the baking parameters such as temperature and humidity in the baking oven are adjusted, the parameters such as temperature and humidity near the vacant space cannot be adjusted to values required by the current baking state of the baking target quickly, so that the baking quality of the baking target near the vacant space is low.

The embodiment of this application, through setting up thermal-insulated protection casing 22, can satisfy camera 21's minimum focus distance, needn't reserve the spare space in addition for guaranteeing camera 21's minimum focus distance and as taking the space, avoid toasting the condition that the spare space formed the air swirl in-process, guarantee the toasting quality of the target of toasting near the spare space.

The sample image library refers to a database which is provided in advance for storing images. The sample image library stores a large number of sample images. The sample image comprises an image of a sample baking target in the baking process, the sample image is used for comparing with a currently acquired baking target image, and a reference image matched with the baking target image is selected from a sample image library so as to adjust the baking parameter of the current baking target according to the baking parameter of the reference image.

The sample baking target refers to an object to be baked for acquiring a sample image before baking control is performed on the baking target by the baking control method of the embodiment. In order to improve the baking quality of the baking target, a large number of sample baking targets can be collected, and images of each group of sample baking targets in the baking process are collected. In order to guarantee the definition of the image of the sample baking target, an isolation protective cover can be arranged inside the baking oven to form a heat insulation protective space, the camera is placed in the heat insulation protective space, and the image of the sample baking target is collected.

When the sample baking target is baked, a conventional baking method in the prior art may be adopted for baking, and this embodiment is not limited.

In the embodiment of the application, the image difference degree between the baking target image and all the sample images in the preset sample image library is calculated.

For example, when a sample image library is formed, in the baking process of a sample baking target, a camera acquires a sample image at the same fixed position in each photographing period, and then the sample images acquired by a plurality of photographing periods of a plurality of sample baking targets in the baking process are stored in the sample image library. Correspondingly, when the baking target is baked, an image of the baking target can be acquired at the fixed position in each photographing period. And calculating the image difference degree between the baking target image and each sample image in the sample image library.

Parameters such as temperature, humidity, wind speed and heating speed of different parts in the baking box may have certain differences, so that baking states of baking targets at different parts in the baking box are different, and the baking states of all the baking targets cannot be accurately determined through a single baking target image.

Based on this, in another example, when the sample baking target is baked during the formation of the sample image library, the camera takes a corresponding number of sample image sets at a plurality of fixed positions in each photographing period, and then the sample images obtained by a plurality of groups of sample baking targets during a plurality of photographing periods during the baking process are stored in the sample image library. Correspondingly, when the baking target is baked, in each photographing period, the camera can also obtain the baking target images in corresponding quantity at the plurality of fixed positions. The plurality of fixing positions may be set according to actual conditions, and it is preferable that the shooting area of the camera covers all or part of the baking target on the outermost layer, and the embodiment is not limited. And calculating the image difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

It should be noted that the camera is generally disposed on the inner wall of the baking oven, so that the camera can acquire an image of a baking target disposed on the outermost layer in the baking oven. Therefore, in the embodiment of the present application, it is preferable that the shooting area of the camera can cover all or part of the baking target on the outermost layer.

The image difference degree refers to the degree of difference between the baking target image and the sample image, and the greater the image difference degree between the baking target image and the sample image, the lower the image similarity degree between the baking target image and the sample image. The image difference between the baking target image and the sample image may be calculated by extracting a feature vector, which is not limited in this embodiment.

S102, selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image.

The baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters of the target moment and the baking state determined according to the sample image; the target time is a time when the sample image is captured.

Specifically, the baking parameters corresponding to the moment of shooting the sample image include parameters such as temperature and baking time corresponding to the moment of shooting the sample image. Based on parameters such as temperature and baking time corresponding to the sample image, and appearance of the sample baking target, the baking state corresponding to the time when the sample image is taken can be obtained.

For example, fig. 3 shows a three-stage tobacco curing temperature curve, wherein the X-axis represents the curing time and the Y-axis represents the curing temperature. The three-stage tobacco baking temperature curve divides tobacco into three baking stages, wherein the first stage is yellow fixation, the second stage is color fixation, and the third stage is dry ribs. The three baking stages are required to achieve the target, and the baking temperatures of the different baking stages at different times are shown in fig. 3. Therefore, by checking the figure 3, the baking state corresponding to the moment of shooting the sample image can be determined by combining the baking temperature and the baking time of the sample baking target at the moment of shooting the sample image.

For another example, on the premise of the three baking stages of yellowing, color fixing and tendon drying shown in fig. 3, the tobacco baking process may be further refined, and the whole baking process of the tobacco is divided into 7 stages, including a pre-yellowing stage, a mid-yellowing stage, a post-yellowing stage, a pre-fixing stage, a post-fixing stage, a pre-drying tendon stage and a post-drying tendon stage. Then, on the basis of fig. 3, the temperatures and drying times corresponding to the earlier stage of yellowing, the middle stage of yellowing, the later stage of yellowing, the earlier stage of fixing color, the later stage of fixing color, the earlier stage of dry tendon and the later stage of dry tendon can be divided to obtain the subdivided temperature curve. Therefore, even if the whole tobacco baking process is divided into 7 stages, the baking state corresponding to the time when the sample image is shot can be determined by referring to the subdivided temperature curve in combination with the baking temperature and the baking time of the sample baking target at the time when the sample image is shot.

Specifically, the baking states determined according to the sample images may be all the sample images sent to a professional, and the professional marks the baking states corresponding to the sample images one by one. If the number of sample images is large, the labeling by professional technicians possibly has low efficiency, under the condition, the deep learning network model can be established, the labeling training of the baking state is carried out on the deep learning network model, the converged deep learning network model is further obtained, and the automatic labeling is carried out through the deep learning network model, so that the labeling efficiency can be improved.

In this embodiment, the baking state reliability is determined by a difference between the baking state determined according to the baking parameter at the target time and the baking state determined according to the sample image. The closer the baking state determined according to the baking parameter at the target time is to the baking state determined according to the sample image, the smaller the difference between the baking states determined by the two methods is, and the higher the baking state reliability of the sample image is.

For example, if the determined baking states of the sample baking targets at the time of taking the sample images are the same through the two completely different modes, it indicates that the sample baking targets at the time of taking the sample images are indeed in the determined states, and the baking state reliability of the sample images is high; if the determined baking states of the sample baking target at the moment of shooting the sample image are completely different and have larger differences through the two completely different modes, for example, if the baking state of the sample baking target at the moment of shooting the sample image is determined to be a yellow early stage through one mode, and the baking state of the sample baking target at the moment of shooting the sample image is determined to be a dry early stage through the other mode, it indicates that one mode of determining the baking states has a problem, and the baking state reliability of the sample image is lower.

In this embodiment, the baking state reliability corresponding to the sample image is predetermined based on the above manner. After the baking target image is acquired, a reference image matched with the baking target image can be selected from the sample image library based on the baking state reliability of the sample image and the image difference determined in the step.

In the embodiment, consideration is performed on the basis of two angles of image difference and baking state reliability, and the purpose is to select a reference image with small image difference and high baking state reliability from the sample image library.

S103, adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

If the image difference degree of the sample image and the baking target image is small, the similarity of the sample image and the baking target image is high; if the baking state credibility of the sample image is high, it means that the difference degree between the baking state determined by the baking parameter at the target moment and the baking state determined by the sample image is small, and the baking parameter of the sample baking target at the moment of shooting the sample image is a relatively accurate baking parameter.

A sample image having a small degree of difference from an image of a baking target image is selected from a sample image library in order to select a sample image close to the baking state of the baking target when the baking target image is captured as a reference image. And selecting a sample image with high baking state reliability from the sample image library, wherein the purpose is to select the sample image of which the baking parameter of the sample baking target at the target moment is relatively accurate as a reference image. When the baking parameters of the baking target are automatically adjusted according to the baking parameters corresponding to the reference image, the baking parameters can be adjusted according to a more accurate adjustment direction, and the product quality is further ensured.

In this embodiment, a baking target image corresponding to a current baking target may be compared with a sample image in a sample image library, and a reference image matching the baking target image may be determined from the sample image based on an image difference between the baking target image and the sample image and a baking state reliability of the sample image. According to the method and the device, the baking parameters of the baking target are adjusted according to the baking parameters corresponding to the reference image matched with the baking target image, so that the automatic adjustment of the baking parameters is realized, the influence of the experience and level of baking personnel on the baking quality is avoided, and the product quality is ensured.

Furthermore, the image difference degree can represent the difference degree between the baking target image and the sample image; the baking state reliability is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image, and the reliability of the baking state of the sample image can be represented, namely, the smaller the baking state difference determined by the two methods, the higher the reliability of the baking state of the sample image. The method and the device consider based on two angles of image difference and baking state credibility, select a reference image with small difference degree with the baking target image and high baking state reliability from the sample image library, and can adjust according to a more accurate adjustment direction when automatically adjusting the baking parameters of the baking target according to the corresponding baking parameters of the reference image, thereby further ensuring the product quality.

As an alternative implementation manner, as shown in fig. 4, in another embodiment of the present application, it is disclosed that the baking target image of the above embodiment includes an image group obtained by shooting the baking target from each shooting position; the sample image library includes a plurality of sample image groups each including an image obtained by photographing a sample baking target from a respective photographing position.

The step of the above embodiment of calculating the image difference between the baking target image and the sample image in the preset sample image library may specifically include the following steps:

s401, calculating the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

Because parameters such as different position temperature, humidity, wind speed and the programming rate of rising in the case of toasting probably have certain difference, lead to toasting the target toasting state of different positions in the case of toasting and be different, toasting the state of all targets of toasting through single target image of toasting accurately to confirm, the embodiment of this application when obtaining toasting the target image, shoots and obtain the image group to toasting the target from a plurality of shooting positions. Correspondingly, when a sample image library is formed, in the process of baking a sample baking target, the camera also acquires a sample image at the shooting position in each shooting period, the sample images acquired in each shooting period form a group of sample image groups, and the acquired groups of sample image groups are stored in the sample image library.

Based on this, the baking target images acquired in the present embodiment are the same in number as the images in any one set of sample image groups in the sample image library, and the shooting positions of the images are in one-to-one correspondence.

The actual shooting position can be determined according to the volume of the baking oven, the type of the baking target, the placing density of the baking target in the baking oven and the like in the actual baking process, the specific position of the shooting position is not limited in the embodiment, and as long as the camera shoots at all shooting positions, the obtained baking target image or sample image group can cover all or part of the baking target at the outermost layer.

Illustratively, as shown in fig. 2, a guide rail 23 and a moving device 24 may be provided on the inner wall of the oven chamber, the guide rail 23 passing through the above-described photographing position. The camera 21 is arranged on the guide rail 23 and connected with the moving device 24, and the camera 21 can perform moving shooting at preset time intervals to obtain a baking target image or a sample image group. The specific moving shooting steps are as follows: the camera 21 is driven by the moving device 24 to move along the guide rail 23, the camera 21 is suspended at the shooting position when passing through the shooting position in the moving process, and the moving device 24 drives the camera to continuously move after the shooting is finished until the camera 21 finishes shooting at all the shooting positions. The preset time may be determined according to actual conditions, for example, set to 10 minutes, and this embodiment is not limited.

The moving device 24 and the guide rail 23 can be arranged in the heat insulation protective cover 22 which is buckled on the inner wall 20 of the baking box to form a heat insulation protective space, so that the influence of high temperature in the baking box on the moving device 24 and the guide rail 23 is avoided.

Exemplarily, the moving device 24 may include a motor, a transmission device and a roller, the camera 21 is mounted on the guide rail 23 through the roller, the roller is connected to the motor through the transmission device, and when the motor rotates, the roller can be driven by the transmission device to move on the guide rail 23, so that the camera 21 can move on the guide rail 23.

The guide rail 23 includes a first guide rail perpendicular to the ground and a second guide rail having a circular shape. Specifically, if the width of the inner wall of the baking oven is smaller than or equal to the preset width, a first guide rail perpendicular to the ground is arranged on the inner wall of the baking oven. The value of the preset width is related to the width of a scene that can be irradiated by the camera 21 at the shooting position, and for example, the value of the preset width may be set as a value of the width of the scene that can be irradiated by the camera 21 at the current position. The height of the first guide rail is matched with the placing height of the baking target in the baking box, so that when the camera 21 moves on the first guide rail for shooting, all or most of the baking target opposite to the camera 21 can be shot. As shown in fig. 2, the width of the inner wall on which the camera 21 is mounted is less than or equal to a preset width, and a first guide rail perpendicular to the ground is provided on the inner wall so that the camera 21 can move up and down along the guide rail in a direction perpendicular to the ground to capture an image of the corresponding baking target.

If the width of the inner wall of the baking box is larger than the preset width, an annular second guide rail is arranged on the inner wall of the baking box. The height of the second guide rail should also be matched with the placing height of the baking target in the baking box, and the length of the second guide rail should be matched with the placing length of the baking target in the baking box, so that when the camera 21 moves on the second guide rail to shoot, all or most of the baking targets relative to the camera 21 can be shot. Fig. 5 is a schematic structural diagram of another baking oven provided in the embodiment of the present application, and as shown in fig. 5, if the width of the inner wall 20 on which the camera 21 is mounted is greater than the preset width, the inner wall is provided with an annular second guide rail of the guide rail 23, so that the camera 21 can be driven by the moving device 24 to move along the annular second guide rail, and capture an image of the corresponding baking target.

As another example, if the target to be baked is tobacco and the baking oven is a tobacco curing barn, the width of the inner wall formed by the smoke inlet door of the tobacco curing barn and the width of the inner wall opposite to the smoke inlet door are small, the distance is long, and the first guide rail perpendicular to the ground can be arranged on both the inner wall of the smoke inlet door and the inner wall opposite to the smoke inlet door; the inner walls of the two remaining sides of the tobacco curing room are longer in width and short in distance, and an annular second guide rail can be arranged on one side of the tobacco curing room. Moreover, three layers of tobacco are hung up and down in a common tobacco curing barn, so that the first guide rail can be provided with three shooting positions corresponding to the three layers of tobacco, and the camera can acquire images corresponding to the layers of tobacco at each shooting position. And the parts of the second guide rail, which are vertical to the ground, can also be respectively provided with three shooting positions, and the parts, which are parallel to the ground, can be respectively provided with five shooting positions, so that the camera can shoot images of all or most of the baking targets.

In this embodiment, the degree of difference between the baking target image and the image corresponding to the same shooting position in each sample image group is calculated. So as to determine the image difference degree of the baking target image and each sample image group according to the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

S402, determining the image difference degree between the baking target image and each sample image group based on the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

If the difference degrees between the baking target image and the images corresponding to the same shooting positions in the sample image group are smaller, the difference degrees between the baking target image and the images corresponding to the sample image group are smaller; if the difference degree between the baking target image and the image corresponding to the same shooting position in the sample image group is large, the difference degree between the baking target image and the image corresponding to the sample image group is large.

For example, the image difference degree between the baking target image and each sample image group can be determined by the following formula:

in the above formula, M _(X，T) Representing the image difference degree of the baking target image and the sample image group of the Xth turn and the T turn in the sample image library; if all the shooting positions are sorted from 1 to n, K _L Representing the difference degree between the baking target image and the image corresponding to the shooting position with the sequence number L in the sample image group; n represents the number of the baking target images.

In this embodiment, considering the influence of parameters such as temperature, humidity, wind speed and heating rate of different parts in the baking oven, it may cause different baking states of the baking target at different parts in the baking oven, and set up a plurality of shooting positions in the baking oven, so as to shoot a plurality of images at different shooting positions, provide richer data base for calculating the image difference between the baking target image and each sample image group, so as to select the sample image close to the baking state of the baking target when shooting the baking target image as a reference image.

As an optional implementation manner, the step of calculating the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group in the above embodiment may specifically include the following steps:

Specifically, the present embodiment calculates an image feature distance between the baking target image and the image corresponding to the same photographing position in each sample image group, and determines the image feature distance between the baking target image and the image corresponding to the same photographing position in each sample image group as a degree of difference between the baking target image and the image corresponding to the same photographing position in each sample image group.

The image characteristic distance refers to a difference value between characteristic values corresponding to the two images, if the images contain various characteristics, various characteristic values corresponding to the two images are extracted, the difference value of each characteristic value of the two images is calculated, and the sum of the difference values of all the characteristic values is determined as the image characteristic distance of the two images.

The steps of extracting characteristic values from the baking target image and the sample image are as follows:

the image is preprocessed, and the preprocessing comprises filtering, denoising, region of interest extraction and the like. After the preprocessing is completed, feature values can be extracted from the preprocessed image through a feature extraction algorithm. The feature extraction algorithm comprises a deep learning mode, such as a convolution neural network; the method may further include a histogram method, a statistical feature method, and other conventional feature extraction algorithms, which are not limited in this embodiment.

For example, if the baking target is tobacco, the steps of extracting the feature values from the baking target image and the sample image are as follows:

tobacco includes mesophyll regions and vein regions, which are different in color change during the baking process, and thus it is necessary to preprocess the image to separate the mesophyll regions from the vein regions. Firstly, filtering and denoising an image; then, segmenting the region of interest, wherein the image may contain a large amount of background information, which has influence on feature extraction, so that the region of interest can be segmented by adopting the traditional algorithm segmentation, such as HSV threshold segmentation, feature value cluster analysis and other modes; after the region of interest is obtained, the mesophyll region and the vein region of the tobacco can be segmented, and in some stages, the change of the vein region is obvious, and the change of the mesophyll is not obvious, which is an important characteristic basis for judging the baking stage.

And after the preprocessing is finished, extracting the characteristic value of the image by adopting a mode of combining a traditional algorithm and deep learning. Specifically, feature extraction is performed on a vein region and a mesophyll region in two ways, for example, a convolutional neural network and a histogram method are used to extract feature values of the vein region, including color feature values, texture feature values and the like of the vein region; and extracting characteristic values of the mesophyll region, including color characteristic values, texture characteristic values and the like of the mesophyll region by adopting a convolution neural network and a histogram method. Gathering the characteristic values of the vein region extracted by a convolutional neural network and a histogram method to obtain the characteristic values of the vein region; and (4) collecting the characteristic values of the mesophyll region extracted by adopting a convolutional neural network and a histogram method to obtain the characteristic values of the mesophyll region.

When calculating the image characteristic distance between the baking target image and the image corresponding to the same shooting position in each sample image group, calculating the characteristic value difference of the mesophyll region of the image at the same shooting position, calculating the characteristic value difference of the vein region of the image at the same shooting position, and determining the difference as the image characteristic distance between the images at the same shooting position. The calculation formula is as follows:

K _L ＝|DR _L -DC _L |+|FR _L -FC _L |

in the above formula, K _L Expressing the degree of difference DR between the baking target image and the image corresponding to the shooting position with the sequence number L in the sample image group _L The characteristic value of the mesophyll of the image corresponding to the shooting position with the sequence number L in the baking target image is obtained; DC (direct current) _L The characteristic value of the mesophyll corresponding to the shooting position with the sequence number L in the sample image group is obtained; FR _L The vein characteristic value of the image corresponding to the shooting position with the sequence number L in the baking target image is obtained; FC _L The characteristic value of the vein of the image corresponding to the shooting position with the sequence number L in the sample image group is obtained.

In the embodiment of the application, the image characteristic distance between the baking target image and the image corresponding to the same shooting position in each sample image group is calculated, so that the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group can be effectively determined.

As an optional implementation manner, the steps in the above embodiment are based on the image difference and the baking state reliability of the sample image, and the step of selecting the reference image matched with the baking target image from the sample image library may specifically include the following steps:

and selecting a sample image group matched with the baking target image from the sample image library as a reference image based on the image difference degree and the baking state credibility of the sample image group.

As described in the above embodiments, since parameters such as temperature, humidity, wind speed, and temperature rise speed of different portions in the baking oven may have certain differences, which causes different baking states of the baking target at different portions in the baking oven, in order to provide a richer data base for a calculation process of selecting a reference image matched with the baking target image from the sample image library, the embodiment of the present application photographs the baking target from a plurality of photographing positions when acquiring the baking target image and the sample image.

And selecting a sample image group matched with the baking target image from the sample image library as a reference image according to the image difference degree between the baking target image and each sample image group in the sample image library and the baking state reliability of each sample image group.

According to the embodiment, a richer data basis is provided for the calculation process of selecting the reference image matched with the baking target image from the sample image library, so that the sample image which is close to the baking state of the baking target when the baking target image is shot and the baking parameter of the sample baking target at the target moment is relatively accurate baking parameter is selected as the reference image.

As an alternative implementation manner, as shown in fig. 6, the steps of the foregoing embodiment select a sample image group matching the baking target image from the sample image library based on the image difference degree and the baking status reliability of the sample image group, and use the sample image group as a reference image, which may specifically include the following steps:

s601, calculating the product of the image difference degree and the baking state difference degree of each sample image group.

The baking state difference degree of each sample image group represents a difference between a baking state determined based on the baking parameter at the time of capturing the group of sample images and a baking state determined based on the group of sample images, and the baking state difference degree and the baking state reliability have a negative correlation.

The closer the baking state determined from the baking parameter at the time of capturing the group of sample images and the baking state determined from the group of sample images, the smaller the degree of difference between the baking states determined by the above two methods, and the higher the baking state reliability of the sample image. Conversely, the greater the difference between the baking state determined from the baking parameters at the time of capturing the group of sample images and the baking state determined from the group of sample images, the greater the degree of difference between the baking states determined by the above two methods, and the lower the baking state reliability of the sample image.

In the embodiment of the present application, the purpose is to select a reference image having a small degree of difference from a baking target image and a high degree of reliability of a baking state from a sample image library, that is, select a reference image having a small degree of difference from a baking target image and a small degree of difference from a baking state from a sample image library. Based on this, the reference image may be determined from the sample image library by comparing the magnitude of the product of the image difference between the baking target image and each sample image group in the preset sample image library and the baking state difference of the sample image group in a manner of calculating the product of the image difference and the baking state difference of each sample image group.

S602, according to the product corresponding to each sample image group, determining a sample image group matched with the baking target image from the sample image library as a reference image.

In this embodiment, the purpose is to select a reference image having a small degree of difference from the baking target image and a small degree of difference from the baking state from the sample image library, and then after obtaining a product corresponding to each sample image group, select a sample image group corresponding to the smallest product value from the sample image groups as a reference image. The specific calculation formula is as follows:

in the above formula, M _(X，T) Representing the image difference degree of the baking target image and the sample image group of the Xth turn and the T turn in the sample image library; s. the _(X，T) And the baking state difference degree of the sample image group of the Xkang T round in the sample image library is represented.

In the implementation, the sample image group with small difference degree with the baking target image and small difference degree of the baking state is selected from the sample image library to be used as the reference image, and the baking parameters of the baking target can be adjusted according to a more accurate adjustment direction when the baking parameters are automatically adjusted according to the corresponding baking parameters of the reference image, so that the product quality is further ensured.

As an optional implementation manner, the determination process of the baking status reliability of the sample image group in the above embodiment includes the following steps:

acquiring a first baking state and a second baking state corresponding to each image in each sample image group; calculating the baking state difference between the first baking state and the second baking state corresponding to each image; and determining the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group.

Specifically, the first baking state is determined according to baking parameters when each image is shot, and the second state is determined according to each image. The process of specifically obtaining the first baking status and the second baking status corresponding to each image in each sample image group has been described in detail in the above embodiments, and details are not repeated herein, and those skilled in the art may refer to the description of the above embodiments.

Further, in the present embodiment, the difference in the baking state between the first baking state and the second baking state corresponding to each image is calculated. The baking states corresponding to the baking targets can be sorted according to the baking processes of the baking targets. And calculating the difference value of the sequence number of the first baking state and the sequence number of the second baking state corresponding to each image, and taking the difference value as the baking state difference between the first baking state and the second baking state corresponding to the image.

Illustratively, if the baking sample is tobacco, according to the baking process of the tobacco, 7 baking states of the tobacco are sequenced in the early yellow stage, the middle yellowing stage, the later yellowing stage, the early color fixing stage, the later color fixing stage, the early dry rib stage and the later dry rib stage, wherein the early yellow stage corresponds to a serial number 1, the middle yellowing stage corresponds to a serial number 2, the later yellow stage corresponds to a serial number 3, the early color fixing stage corresponds to a serial number 4, the later color fixing stage corresponds to a serial number 5, the early dry rib stage corresponds to a serial number 6, the later dry rib stage corresponds to a serial number 7, and the states which should not appear in the whole baking process correspond to a serial number 0.

If a certain sample image in the sample image group has the determined first baking state that the tobacco is at the middle stage of yellowing corresponding to the serial number 2 and the determined second baking state that the tobacco is at the later stage of fixing color corresponding to the serial number 5, the value of the baking state difference between the first baking state and the second baking state corresponding to the certain sample image is 3.

If a certain sample image in the sample image group has the determined first baking state that the tobacco is at the sequence number 2 corresponding to the middle stage of turning yellow, and the determined second baking state that the tobacco is at the sequence number 2 corresponding to the middle stage of turning yellow, the value of the baking state difference between the first baking state and the second baking state corresponding to the certain sample image is 0.

Furthermore, after the baking state difference corresponding to each image in each sample image group is determined, the baking state reliability of the sample image group can be determined according to the baking state difference corresponding to each image in each sample image group.

Specifically, the smaller the baking state difference corresponding to the image in each sample image group is, the higher the baking state reliability of the sample image group is. The greater the baking state difference corresponding to the image in each sample image group, the lower the baking state reliability of the sample image group.

In the embodiment of the application, the baking state reliability of each sample image group can be effectively determined by calculating the baking state difference between the first baking state and the second baking state corresponding to each image in the sample image group, so that the sample image of which the baking parameter of the sample baking target at the target moment is relatively accurate baking parameter can be selected as the reference image, and when the baking parameter of the baking target is automatically adjusted according to the baking parameter corresponding to the reference image, the adjustment can be performed according to a more accurate adjustment direction, and the product quality is further ensured.

As an optional implementation manner, the step of the above embodiment determines the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group, and specifically may include the following steps:

Specifically, the baking state reliability corresponding to each sample image group can be calculated according to the following formula:

in the above formula, S _(X，T) And expressing the baking state difference degree of the sample image group of the Xth turn and the Tth turn in the sample image library. If all the shooting positions are sorted from 1 to n, P _L A first baking state Q of an image corresponding to a photographing position with a sequence number L in the sample image group _L Representing a set of sample imagesIn (3), a indicates a correction parameter, and a indicates a second baking state of the image corresponding to the shooting position with the sequence number L.

Wherein the purpose of setting the correction parameter is to ensure S _(X，T) Is not zero. This is because once P is present _L And Q _L Are the same so that S _(X，T) When the product of the image difference degree and the baking state difference degree of each sample image group is calculated, the obtained product value is 0 no matter how the value of the image difference degree is, namely, the parameter of the image difference degree does not play any role, and the purpose of selecting a sample image with small image difference degree with a baking target image from a sample image library, namely selecting a sample image close to the baking state of the baking target when the baking target image is shot as a reference image cannot be realized. Therefore, the correction parameter a is set in this embodiment to avoid the above situation.

The correction parameter a is a positive number, and the value of a may be 1, for example.

Exemplarily, if the value of a is 1, the baking sample is tobacco, the sequence number 1 is corresponding to the early stage of yellowing, the sequence number 2 is corresponding to the middle stage of yellowing, the sequence number 3 is corresponding to the later stage of yellowing, the sequence number 4 is corresponding to the early stage of fixing color, the sequence number 5 is corresponding to the later stage of fixing color, the sequence number 6 is corresponding to the early stage of dry tendon, the sequence number 7 is corresponding to the later stage of dry tendon, the sequence number 0 is corresponding to the state that should not appear in the whole baking process, and the shooting position is 22, then S _(X，T) Has a maximum value of 155 and a minimum value of 1.

In the embodiment, the baking state reliability of each sample image group is determined by calculating the baking state differences corresponding to all the images in each sample image group and the preset correction parameter sum, so that the calculation is simple, and the image processing speed can be effectively improved.

As an optional implementation manner, as shown in fig. 7, the step of the foregoing embodiment adjusts the baking parameter of the baking target according to the baking parameter corresponding to the reference image, and may specifically include the following steps:

s701, judging whether the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image; if the baking parameters of the baking target are different from the baking parameters corresponding to the reference image, executing step S702; and if the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image, ending the execution.

In the embodiment of the application, after the sample image is acquired, the baking parameters in the baking oven for shooting the sample image are correspondingly stored. Wherein the baking parameters at least comprise temperature, humidity, wind speed and heating speed. Detecting whether the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image or not when the baking target image is acquired, if the baking parameters of the baking target are not the same as the baking parameters corresponding to the reference image, executing the step S702, adjusting the baking parameters of the baking target, if the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image, not adjusting the baking parameters of the baking target, and ending the execution of the step.

It should be noted that, the determining whether the baking parameter of the baking target is the same as the baking parameter corresponding to the reference image refers to determining whether the temperature of the baking target is the same as the temperature corresponding to the reference image, determining whether the wind speed of the baking target is the same as the wind speed corresponding to the reference image, determining whether the temperature rise speed of the baking target is the same as the temperature rise speed corresponding to the reference image, and determining that the baking parameter of the baking target is the same as the baking parameter corresponding to the reference image when the temperature, the humidity, the wind speed, and the temperature rise speed are all the same; and when at least one of the temperature, the humidity, the wind speed and the temperature rise speed is different, determining that the baking parameters of the baking target are different from the baking parameters corresponding to the reference image.

Moreover, the above identity does not limit that the parameter values are completely the same, that is, the difference value of the corresponding parameter values is within a preset range, which means that the parameters are the same. For example, if the temperature value of the temperature difference between the temperature of the baking target and the temperature corresponding to the reference image is within the preset temperature range, it indicates that the temperature of the baking target is the same as the temperature corresponding to the reference image; if the humidity value of the difference between the humidity of the baking target and the humidity corresponding to the reference image is within the preset humidity range, indicating that the humidity of the baking target is the same as the humidity corresponding to the reference image; if the wind speed difference between the wind speed of the baking target and the wind speed corresponding to the reference image is within a preset wind speed range, the wind speed of the baking target is the same as the wind speed corresponding to the reference image; and if the temperature rise speed value of the difference between the temperature rise speed of the baking target and the temperature rise speed corresponding to the reference image is within the preset temperature rise speed range, the temperature rise speed of the baking target is the same as the temperature rise speed corresponding to the reference image.

The temperature range, the wind speed range, and the temperature rise speed range may be set according to actual conditions, and this embodiment is not limited.

S702, adjusting the baking parameters of the baking target until the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image.

If the baking parameters of the baking target are different from the baking parameters corresponding to the reference image, the baking parameters of the baking target need to be adjusted according to the baking parameters corresponding to the reference image until the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image.

In the embodiment of the application, the baking parameters of the baking target can be adjusted according to more accurate adjustment directions when the baking parameters corresponding to the reference image are automatically adjusted, and the product quality is further ensured.

As an alternative implementation, the target of the curing includes tobacco. The baking control method is applied to the baking treatment of the tobacco, can automatically adjust the baking parameters of the tobacco, and avoids the influence of the experience and level of baking personnel on the baking quality of the tobacco. In addition, in the embodiment, the reference image with small difference degree with the tobacco image and high reliability of the baking state is selected from the sample image library based on the consideration of two angles of the image difference degree and the baking state reliability, and the baking parameters of the tobacco can be adjusted according to a more accurate adjustment direction when being automatically adjusted according to the corresponding baking parameters of the reference image, so that the baking quality of the tobacco is further ensured.

Corresponding to the above baking control method, the embodiment of the present application further discloses a baking control device, as shown in fig. 8, the device includes:

the calculation module 100 is configured to calculate an image difference between the baking target image and a sample image in a preset sample image library; wherein the sample image comprises an image of the sample baking target in the baking process;

the selection module 110 is configured to select a reference image matched with the baking target image from the sample image library based on the image difference and the baking state reliability of the sample image; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters of the target moment and the baking state determined according to the sample image; the target moment is the moment of shooting the sample image;

and the adjusting module 120 is configured to adjust the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

The baking control device of the embodiment adjusts the baking parameters of the baking target according to the baking parameters corresponding to the reference image matched with the baking target image, realizes the automatic adjustment of the baking parameters, avoids the influence of the experience and level of baking personnel on the baking quality, and ensures the product quality. Furthermore, in the embodiment, the reference image with a small difference degree from the baking target image and a high reliability of the baking state is selected from the sample image library based on two angles of the image difference degree and the baking state reliability, and the baking parameters of the baking target can be adjusted according to a more accurate adjustment direction when the baking parameters are automatically adjusted according to the corresponding baking parameters of the reference image, so that the product quality is further ensured.

Optionally, in another embodiment of the present application, the baking target image includes an image group obtained by shooting the baking target from each shooting position; the sample image library comprises a plurality of sample image groups, and each sample image group comprises images obtained by shooting the sample baking target from each shooting position;

the computing module 100 of the above embodiment includes:

the calculating unit is used for calculating the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group;

and a determining unit for determining the image difference degree between the baking target image and each sample image group based on the difference degree between the baking target image and the image corresponding to the same shooting position in each sample image group.

Optionally, in another embodiment of the present application, when the calculating unit of the above embodiment calculates the degree of difference between the baking target image and the image corresponding to the same shooting position in each sample image group, the calculating unit is specifically configured to:

Optionally, in another embodiment of the present application, when the determining unit selects a reference image matched with the baking target image from the sample image library based on the image difference and the baking state reliability of the sample image, the determining unit is specifically configured to:

and selecting a sample image group matched with the baking target image from the sample image library as a reference image based on the image difference degree and the baking state reliability of the sample image group.

Optionally, in another embodiment of the present application, the determining unit of the above embodiment includes:

the calculating subunit is used for calculating the product of the image difference degree and the baking state difference degree of each sample image group; a baking state difference degree of each sample image group representing a difference between a baking state determined from the baking parameter at the time of photographing the group of sample images and a baking state determined from the group of sample images; the baking state difference degree and the baking state reliability are in a negative correlation relationship;

and the determining subunit is used for determining the sample image group matched with the baking target image from the sample image library according to the product corresponding to each sample image group, and the sample image group is used as a reference image.

Optionally, in another embodiment of the present application, the baking control device further includes:

the acquisition module is used for acquiring a first baking state and a second baking state corresponding to each image in each sample image group; the first baking state is determined according to baking parameters when each image is shot, and the second state is determined according to each image;

the state difference calculating module is used for calculating the baking state difference between the first baking state and the second baking state corresponding to each image;

and the determining module is used for determining the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group.

Optionally, in another embodiment of the present application, when the determining module in the above embodiment determines the baking state reliability of each sample image group according to the baking state difference corresponding to each image in each sample image group, the determining module is specifically configured to:

determining the baking state difference corresponding to all the images in each sample image group and the sum of preset correction parameters as the baking state credibility of each sample image group; wherein the correction parameter is a positive number.

Optionally, in another embodiment of the present application, the adjusting module 120 of the foregoing embodiment includes:

the judging unit is used for judging whether the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image or not;

and the adjusting unit is used for adjusting the baking parameters of the baking target if the baking parameters of the baking target are different from the baking parameters corresponding to the reference image until the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image.

Optionally, in another embodiment of the present application, the target of the toasting comprises tobacco.

Specifically, please refer to the contents of the above method embodiments for the specific working contents of each unit of the baking control device, which are not described herein again.

Another embodiment of the present application further provides a toasting apparatus, as shown in fig. 9, comprising:

a memory 200, a processor 210, and a camera 220; the memory 200 and the camera 220 are respectively connected to the processor 210.

The camera 220 is used as an input device for acquiring a baking target image;

the memory 200 is used for storing a computer program and a sample image library, wherein the sample image library stores a sample image and baking state credibility information of the sample image; wherein the sample image comprises an image of the sample baking target in the baking process; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image; the target moment is the moment of shooting the sample image;

a processor 210 for calculating an image difference degree between the baking target image acquired from the camera and the sample image stored in the memory by running the computer program stored in the memory 200; selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; and adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image.

Specifically, the above baking apparatus may further include: a bus, a communication interface 230, and an output device 240.

The processor 210, the memory 200, the communication interface 230, and the output device 240 are connected to each other through a bus. Wherein:

a bus may comprise a path that transfers information between components of a computer system.

The processor 210 may be a general-purpose processor, such as a general-purpose Central Processing Unit (CPU), microprocessor, etc., an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with the present disclosure. But may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

The processor 210 may include a main processor and may also include a baseband chip, modem, and the like.

The memory 200 stores a computer program for executing the technical solution of the present application, and may also store an operating system and other key services. In particular, the program may include program code including computer operating instructions. More specifically, memory 200 may include a read-only memory (ROM), other types of static storage devices that may store static information and instructions, a Random Access Memory (RAM), other types of dynamic storage devices that may store information and instructions, a disk storage, a flash, and so forth.

The input device may include means for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, a gravity sensor, etc., in addition to the camera 220 described above, and the input device, the processor 210, the memory 200, the communication interface 230, and the output device 240 are connected to each other through a bus.

Output device 240 may include equipment that allows output of information to a user, such as a display screen, a printer, speakers, and the like.

Communication interface 230 may include any device that uses any transceiver or the like to communicate with other devices or communication networks, such as an ethernet network, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), etc.

The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the steps of the baking control method provided by the above-mentioned embodiments of the present application.

Optionally, in another embodiment of the present application, the baking target image of the above embodiment includes an image group obtained by shooting the baking target from each shooting position; the sample image library comprises a plurality of sample image groups, and each sample image group comprises images obtained by shooting the sample baking target from each shooting position;

the processor 210 of the above embodiment calculates the image difference degree between the baking target image and the sample image in the preset sample image library, including:

Optionally, in another embodiment of the present application, the processor 210 of the above embodiment calculates the degree of difference between the baking target image and the image corresponding to the same shooting position in each sample image group, including:

Optionally, in another embodiment of the present application, the selecting, by the processor 210 of the above embodiment, a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state reliability of the sample image includes:

Optionally, in another embodiment of the present application, the processor 210 of the above embodiment selects, based on the image difference degree and the baking status reliability of the sample image group, a sample image group matched with the baking target image from the sample image library, as a reference image, and includes:

calculating the product of the image difference degree and the baking state difference degree of each sample image group; a baking state difference degree of each sample image group representing a difference between a baking state determined from the baking parameter at the time of photographing the group of sample images and a baking state determined from the group of sample images; the baking state difference degree and the baking state reliability are in a negative correlation relationship;

Optionally, in another embodiment of the present application, the processor 210 of the above embodiment is further configured to:

Optionally, in another embodiment of the present application, the processor 210 in the above embodiment determines the baking status reliability of each sample image group according to the baking status difference corresponding to each image in each sample image group, including:

Optionally, in another embodiment of the present application, the adjusting, by the processor 210 of the above embodiment, the baking parameter of the baking target according to the baking parameter corresponding to the reference image includes:

judging whether the baking parameters of the baking target are the same as the baking parameters corresponding to the reference image;

Optionally, in another embodiment of the present application, the target of the above embodiment comprises tobacco.

The baking device provided in this embodiment, which belongs to the same application concept as the baking control method provided in the above embodiments of the present application, can execute the baking control method provided in any of the above embodiments of the present application, has the corresponding functional modules and the technical details which are not described in detail in this embodiment of the beneficial effects of the above baking control method, and may refer to the specific processing contents of the baking control method provided in the above embodiments of the present application, and are not described again here.

In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by the processor 210, cause the processor 210 to perform the various steps of the baking control method provided by the above-described embodiments.

The computer program product may include program code for carrying out operations for embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, cause the processor 210 to perform the steps of the baking control method provided by the above-described embodiments.

The computer readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present application is not limited by the order of acts or acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the application. Further, those skilled in the art will recognize that the embodiments described in this specification are preferred embodiments and that acts or modules referred to are not necessarily required for this application.

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The steps in the method of each embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and technical features described in each embodiment may be replaced or combined.

The modules and sub-modules in the device and the terminal in the embodiments of the application can be combined, divided and deleted according to actual needs.

In the several embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described terminal embodiments are merely illustrative, and for example, the division of a module or a sub-module is only one logical division, and there may be other divisions when the terminal is actually implemented, for example, a plurality of sub-modules or modules may be combined or integrated into another module, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules or sub-modules described as separate parts may or may not be physically separate, and parts that are modules or sub-modules may or may not be physical modules or sub-modules, may be located in one place, or may be distributed over a plurality of network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional module or sub-module in the embodiments of the present application may be integrated into one processing module, or each module or sub-module may exist alone physically, or two or more modules or sub-modules may be integrated into one module. The integrated modules or sub-modules may be implemented in the form of hardware, or may be implemented in the form of software functional modules or sub-modules.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software cells may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

The foregoing description of the disclosed embodiments will enable those skilled in the art to make or use the invention as described herein will be readily apparent to those skilled in the art from the following detailed description, wherein it is shown and described that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A baking control method, comprising:

selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters of the target moment and the baking state determined according to the sample image; the target moment is the moment when the sample image is shot;

2. The method according to claim 1, wherein the baking target image includes an image group obtained by photographing the baking target from each photographing position; the sample image library comprises a plurality of sample image groups, and each sample image group comprises images obtained by shooting a sample baking target from each shooting position;

the calculating the image difference degree between the baking target image and the sample image in the preset sample image library comprises the following steps:

3. The method according to claim 2, wherein the calculating of the degree of difference between the baking target image and the image corresponding to the same capturing position in each of the sample image groups comprises:

4. The method according to claim 2, wherein the selecting a reference image matching the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image comprises:

5. The method according to claim 4, wherein the selecting a sample image group matching the baking target image from the sample image library as a reference image based on the image difference degree and the baking state credibility of the sample image group comprises:

6. The method of claim 4, wherein the determining process of the baking status reliability of the sample image group comprises:

7. The method according to claim 6, wherein the determining the baking status reliability of each sample image group according to the baking status difference corresponding to each image in each sample image group comprises:

8. The method of claim 1, wherein the adjusting the baking parameters of the baking target according to the baking parameters corresponding to the reference image comprises:

9. The method of any of claims 1-8, wherein the target of baking comprises tobacco.

10. A roasting control apparatus, comprising:

the selection module is used for selecting a reference image matched with the baking target image from the sample image library based on the image difference degree and the baking state credibility of the sample image; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters at the target moment and the baking state determined according to the sample image; the target moment is the moment when the sample image is shot;

11. The baking equipment is characterized by comprising a processor, a memory and a camera, wherein the memory and the camera are connected with the processor;

the camera is used for acquiring a baking target image;

the memory is used for storing a computer program and a sample image library, wherein the sample image library stores a sample image and baking state credibility information of the sample image; wherein the sample image comprises an image of a sample baking target during baking; the baking state credibility of the sample image is determined by the difference degree between the baking state determined according to the baking parameters of the target moment and the baking state determined according to the sample image; the target moment is the moment when the sample image is shot;

12. A storage medium, comprising: the storage medium has stored thereon a computer program which, when executed by a processor, carries out the individual steps of the baking control method according to any one of claims 1 to 9.