CN104384106A - Automatic sunflower seed sorting system - Google Patents

Abstract

The invention relates to an automatic sorting method and equipment for sunflower seeds. The equipment includes a feeding device, a transmission device, an image acquisition device, an image processing device and an electric control device, wherein the feeding device is used to provide sunflower seeds to be sorted; Transported to another device; the image acquisition device is used to collect images of sunflower seeds to be processed; the image processing device is used to sort the collected images of sunflower seeds, record the location information of unqualified sunflower seeds, and notify other The device removes unqualified sunflower seeds; the electric control device is used to remove unqualified sunflower seeds.

Description

Sunflower Seed Automatic Sorting System

technical field

The invention relates to a transmission device and an electric control device, in particular to an automatic sorting method and equipment for sunflower seeds. the

Background technique

At present, the traditional manual sorting method of sunflower seeds is time-consuming and laborious, which can no longer meet the needs of social development. With the rapid development of digital image processing and recognition technology, its application is gradually entering our daily life. Therefore, it is of great significance to study the automatic sorting system based on machine vision technology to realize the automatic sorting of sunflower seeds. the

The previous manual sorting has the following disadvantages that are difficult to overcome: (1) The efficiency of manual sorting is very low, and the per capita daily sorting volume is only about tens of catties; (2) Manual sorting is very subjective, and workers are Sorting is basically based on personal supervisor experience; (3) Due to the small size of individual sunflower seeds, workers are prone to visual fatigue after sorting for a period of time, which greatly reduces the accuracy of the sorting results . the

With the rapid development of computer technology and image recognition technology, compared with manual observation and recognition, the automatic sorting system based on machine vision technology will obviously have huge market advantages and development prospects. In recent years, the combination of machine vision and artificial intelligence is gradually entering our daily life, and it is very possible to apply image recognition algorithms to the sorting and grading of large-scale agricultural products. Automatic sorting equipment not only has fast sorting speed and high accuracy, but also has good repeatability. Therefore, it is of great significance to study automatic sorting equipment based on machine vision technology. the

In view of the above-mentioned defects of manual sorting and the prospect of automatic sorting, the designer actively researches and innovates, in order to create a new type of automatic sorting equipment for sunflower seeds, so that it has more industrial value. the

Contents of the invention

In order to solve the above technical problems, the object of the present invention is to provide an automatic sorting method and equipment for sunflower seeds that improve sorting efficiency. the

The automatic sorting equipment for sunflower seeds of the present invention includes a feeding device, a transmission device, an image acquisition device, an image processing device and an electric control device, wherein the feeding device is used to provide sunflower seeds to be sorted; the transmission device is used to transport The sunflower seeds are transported from one device to another; the image acquisition device is used to collect images of sunflower seeds to be processed; the image processing device is used to sort the collected images of sunflower seeds and record unqualified sunflower seeds Seed position information, through delay notification to other devices to remove unqualified sunflower seeds; electronic control device, used to remove unqualified sunflower seeds. the

Further, the transmission device includes various transmission components, wherein the various transmission components work together to realize the normal operation of the transmission device. the

Further, the transmission device includes a transparent transmission belt, wherein the transparent transmission belt is used as a carrier for the transmission of the sunflower seeds, and the image acquisition device can collect images of the sunflower seeds from both sides. the

Further, the transmission device includes a tensioning device, wherein the tensioning device is used for tensioning the transmission belt. the

Further, the transmission device includes large and small rollers, wherein the large and small rollers are used to move the belt to the transparent conveyor belt. the

Further, the transmission device includes a motor device, wherein the motor device is used to provide power to the transmission device to drive the large roller to move. the

The present invention also discloses an automatic analysis method for sunflower seeds, comprising:

The feeding device vibrates to scatter the sunflower seeds to be sorted on the transmission device without overlapping; the transmission device transports the sunflower seeds to be sorted to the electronic control device, and passes through the image acquisition device in the process; The front and back images of the sorted sunflower seeds; the image processing device analyzes the collected images, and through a series of image processing, identifies the position of the unqualified sunflower seeds, and sends the electronic control information through a delay; the electronic control device receives the electronic control message, And drive the solenoid valve at the corresponding position, so as to achieve the purpose of removing unqualified melon seeds. the

Further, the transmission device includes a transparent transmission belt, a tensioning device, a large and small roller and a motor device. the

Further, a series of image processing includes coarse positioning of sunflower seeds, edge detection of sunflower seeds and recognition of sunflower seeds. the

Further, a series of image processing methods specifically include: coarse positioning of sunflower seeds roughly locates the region of each sunflower seed from the sampled image; sunflower seed edge detection detects effective and complete edges from a single sunflower seed region; sunflower seed recognition The feature vector is extracted from the edge information of sunflower seeds, and whether the sunflower seeds are qualified or not is judged by pattern recognition. the

Further, the electric control device includes a certain number of relays and corresponding pneumatic valves. the

By means of the above scheme, the present invention has at least the following advantages:

The image of sunflower seeds on the conveyor belt is captured in real time for a series of image processing, and the position information of unqualified seeds is notified to the electronic control device, so as to realize the real-time and repeated automatic sorting of sunflower seeds, thereby improving the sorting efficiency. the

The above description is only an overview of the technical solutions of the present invention. In order to understand the technical means of the present invention more clearly and implement them according to the contents of the description, the preferred embodiments of the present invention and accompanying drawings are described in detail below. the

Description of drawings

Fig. 1 is the schematic diagram of sunflower seed automatic sorting equipment system of the present invention;

Fig. 2 is the flowchart of sunflower seed automatic sorting method of the present invention;

Fig. 3 is a block diagram of image processing of the present invention;

Detailed ways

The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention. the

Referring to Fig. 1, an automatic sorting device for sunflower seeds includes: feeding device 1, transparent conveyor belt 2, large roller 3, fine-tuning device 4, small roller 5, tensioning device 6, motor device 7, image acquisition Device 8, frame 9, electrical device 10, unqualified sunflower seeds collection area 11, qualified sunflower seeds collection area 12, image processing device 13, wherein feeding device 1 is used to provide sunflower seeds to be sorted; transparent conveyor belt 2 , used to transport sunflower seeds from one device to another device; the large roller 3 and the small roller 5 are used to move the transparent conveyor belt, wherein the large roller is the driving wheel and the small roller is the driven wheel; The fine-tuning device 4 is used to adjust the position of the large roller; the tension device 6 is used to adjust the tightness of the transparent transmission belt; the motor device 7 is used to provide power to the transmission device to drive the movement of the large roller; the image acquisition device 8 is used to Collect images of sunflower seeds to be processed; frame 9, used to provide support for the entire equipment; electrical device 9, used to remove unqualified sunflower seeds; unqualified sunflower seed collection area 11, used to collect unqualified sunflower seeds; qualified melon seeds collection Area 12 is used to collect qualified sunflower seeds; image processing device 13 is used to sort the collected images of sunflower seeds, record the location information of unqualified sunflower seeds, and notify other devices to remove unqualified sunflower seeds by delaying time. the

As shown in Figure 2, the specific process of the sunflower seed automatic sorting equipment sorting method of the present invention includes:

Step 21: Collect sunflower seed images, and collect RGB images of a certain size through a CCD or CMOS camera for subsequent image processing. In order to improve the sorting rate without increasing the image processing time, it is recommended that the sampling image size be 1600*1200. the

Step 22: Coarse positioning of the sunflower seed area, through a series of image processing to obtain the approximate location of the sunflower seed target area. the

Step 23: Sunflower seed edge detection, through edge detection methods such as Canny operator, to detect the precise edge of the sunflower seed area. the

Step 24: Sunflower seed target recognition, based on the edge extraction feature vector of the sunflower seed target, judge whether the currently sorted sunflower seed target is qualified through a series of pattern recognition methods. the

Step 25: Store the position of unqualified melon seeds, determine the exact time delay of each unqualified sunflower seed based on the position of the sunflower seeds based on the absolute time axis, and sort based on the delay time, and update the delay queue;

Step 26: Air valve action, when the first delay in the delay queue arrives, control the action of the air valve at the corresponding position, for example, the air valve group selects the valve island. the

As shown in Figure 3, the image processing block diagram of the sunflower seed automatic sorting equipment of the present invention includes:

Step 31: Region positioning: This step is the first step in the trilogy of image sorting. The specific details probably include: subsampling, Sobel edge detection, binarization, erosion, dilation, extracting contours, thinning and target shape detection and rough positioning. Through rough positioning, each target area of sunflower seeds to be sorted is segmented from the entire sampling image. the

Step 32: Edge detection: This step is the second step of the image sorting trilogy. The specific details probably include: improved Canny edge detection, edge extension and fine positioning of the target area. Through precise positioning, the effective edge of each sunflower seed to be sorted is determined. the

Step 33: Pattern recognition: This step is the third step in the image sorting trilogy. The specific details probably include: edge-based feature vector extraction, target pattern recognition and location of unqualified sunflower seeds. The most critical part is the feature vector extraction, through the SVM support vector machine to judge whether the sunflower seeds are qualified, and save the position of unqualified sunflower seeds. the

The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention. It should be pointed out that for those of ordinary skill in the art, some improvements can be made without departing from the technical principle of the present invention. and modifications, these improvements and modifications should also be considered as the protection scope of the present invention. the

Claims (2)

1. a sunflower seeds automatic sorting apparatus, is characterized in that, comprising: pay-off, transmitting device, image collecting device, image processing apparatus and electric control gear, wherein

Pay-off, for providing sunflower seeds to be sorted;

Transmitting device, for transporting sunflower seeds, is transported to another device place by it from a device;

Image collecting device, for gathering sunflower seeds image to be sorted;

Image processing apparatus, for carrying out sunflower seeds sorting to the image gathered, and recording defective sunflower seeds positional information, removing defective sunflower seeds by other devices of delay notification;

Electric control gear, for removing defective sunflower seeds.

1), sunflower seeds automatic sorting apparatus as claimed in claim 1, it is characterized in that, described transmitting device comprises transparent transmission band, and wherein, the carrier that transparent transmission band transmits as sunflower seeds, image collecting device can gather sunflower seeds image from tow sides.

2), sunflower seeds automatic sorting apparatus as claimed in claim 1, it is characterized in that, described transmitting device comprises tensioning apparatus, and wherein, tensioning apparatus is used for tensioning transport tape.

3), sunflower seeds automatic sorting apparatus as claimed in claim 1, it is characterized in that, described transmitting device comprises large doffer, and wherein, large doffer is used for taking the motion of transparent transmission band to.

4), sunflower seeds automatic sorting apparatus as claimed in claim 1, it is characterized in that, described transmitting device comprises electric machine, and wherein electric machine is used for providing power to transmitting device, drives swift motion.

2. a sunflower seeds automatic sorting analytical method, is characterized in that, comprising:

Pay-off, by vibration, is scattered on transmitting device by nonoverlapping for sunflower seeds to be sorted;

Sunflower seeds to be sorted is transported to electric control gear place, during the course through image collecting device by transmitting device;

The positive and negative image of the sunflower seeds that image acquisition device is to be sorted;

The image that image processing apparatus analysis gathers, by a series of image procossing, identifies defective sunflower seeds position, and sends automatically controlled information by time delay;

Electric control gear receives automatically controlled message, and drives the magnetic valve action of relevant position, thus realizes the object removing defective melon seeds.

1), sunflower seeds automatic sorting analytical method as claimed in claim 2, it is characterized in that, described transmitting device comprises transparent transmission band, tensioning apparatus, large doffer and electric machine.

2), sunflower seeds automatic sorting analytical method as claimed in claim 2, it is characterized in that, described a series of images process comprises sunflower seeds coarse positioning, sunflower seeds rim detection and sunflower seeds identification.

3), sunflower seeds automatic sorting analytical method as claimed in claim 2, it is characterized in that, described a series of images processing method, specifically comprises:

Sunflower seeds coarse positioning coarse positioning from sampled images goes out the region of each sunflower seeds; Sunflower seeds rim detection detects effectively complete edge from single sunflower seeds region; Sunflower seeds identification extracts characteristic vector from the marginal information of sunflower seeds, judges that whether this sunflower seeds is qualified by pattern-recognition.

4), sunflower seeds automatic sorting analytical method as claimed in claim 2, it is characterized in that, described electric control gear comprises the relay of some and corresponding pneumatic operated valve.