CN103617619A - Image segmentation method for cup noodles in which forks are thrown through throwing machine - Google Patents
Image segmentation method for cup noodles in which forks are thrown through throwing machine Download PDFInfo
- Publication number
- CN103617619A CN103617619A CN201310648933.7A CN201310648933A CN103617619A CN 103617619 A CN103617619 A CN 103617619A CN 201310648933 A CN201310648933 A CN 201310648933A CN 103617619 A CN103617619 A CN 103617619A
- Authority
- CN
- China
- Prior art keywords
- fork
- region
- forks
- thrown
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to digital image processing and relates to an image segmentation method for cup noodles in which forks are thrown through a throwing machine. The method includes the steps that for acquired images of cup noodles, the edge points of noodle cups are determined in a mode of search from left to right and from right to left; a detection area is determined through the found edge points; binarization processing is performed; according to the characteristics that the forks are distributed densely in a concentrated mode in the area but noise points are scattered in various areas of noodle cakes and small in area, a screening threshold value is set, all the communication areas in the binary images are extracted, the communication areas with the area larger than the screening threshold value are reserved and taken as potential fork communication areas, and thus the images of the cup noodles in which the forks have been thrown through the throwing machine are segmented. The forks of the cup noodles can be detected online fast with the method. The images of the cup noodles in which the forks have been thrown through the throwing machine can be segmented fast and accurately so as to adapt to fast online detection of a high speed production line.
Description
Affiliated technical field
The invention belongs to Digital Image Processing, relate to a kind of image partition method.
Background technology
In barreled instant noodle production run, fork is to be shipped in bucket by cast fork machine, the inaccurate situation that causes occurring lacking in barreled instant noodle fork of throwing in due to cast fork machine.For scarce fork situation, adopt at present the mode of artificial cognition.But because fork color and face cake color are near and line speed is very fast, people has great difficulty for having judged whether fork.Be necessary to propose a kind of image partition method for instant noodles fork on-line quick detection.
Summary of the invention
The object of the invention is to overcome the above-mentioned deficiency of prior art, a kind of image partition method for barreled face fork on-line quick detection is provided.Technical scheme of the present invention is as follows:
A barreled instant noodle image partition method after dispenser is thrown in fork, comprises the following steps:
(1) to the barreled instant noodle image gathering, adopt way of search from left to right and from right to left, each gray-scale value is face cylinder marginal point by the black point bleaching for the first time;
(2) utilize the marginal point find, by the least square fitting cylinder circle of appearing, and then try to achieve the face cylinder center of circle and detection radius r, then determine surveyed area according to the face bucket center of circle and detection radius r;
(3) according to the gray scale in fork region compared with the brighter characteristic in face cake region, choose suitable threshold value, to having determined that surveyed area carries out binary conversion treatment, the binary map in Yu Mianbing region, fork region that obtained initial gross separation;
(4) according to intensive and concentrated and assorted face cake regional and the less feature of area of being dispersed in of selecting of fork areal distribution, set screening threshold value A reaThres, extract each connected region in binary map, Retention area is greater than the connected region of screening threshold value A reaThres, using it as potential fork connected region, the barreled instant noodle image completing after dispenser is thrown in fork is cut apart.
The present invention tries to achieve the center of circle according to barreled face urceolus, and then definite fork surveyed area, by gray difference, carry out binaryzation again and isolate fork and face cake, with connected region area, filter out assorted point, the present invention can be quickly and accurately to the barreled instant noodle Image Segmentation Using after dispenser is thrown in fork, to adapt to the quick online detection of high-speed production lines.
Accompanying drawing explanation
Fig. 1 marginal point search schematic diagram;
Fig. 2 surveyed area (r-detection radius);
Fig. 3 binary picture;
Fig. 4 fork region.
Embodiment
Below in conjunction with drawings and Examples, the present invention will be further described.
(1) surveyed area
Face cylinder is circular, therefore can try to achieve the face cylinder center of circle according to face cylinder, and then determines surveyed area according to the detection radius r of user's input.The outer gradation of image of face cylinder edge and face cylinder has good contrast as seen from Figure 1, therefore adopts way of search from left to right, from right to left, and each gray-scale value is face cylinder marginal point (shown in Fig. 1) by the black point bleaching for the first time.By these points by appear cylinder circle and then try to achieve the face cylinder center of circle of least square fitting.According to the face bucket center of circle and detection radius r, determine surveyed area (region as shown in Fig. 2 inner circle).
(2) image is cut apart
Contrast Yu Mianbing region, fork region, finds that fork area grayscale is brighter compared with face cake region, therefore can adopt binarization method release yoke subregion and face cake region.But because gray-scale value between fork and face cake has certain overlapping region, when detecting, can, by face cake region as fork region, therefore need to get rid of the assorted point (Fig. 3) on face cake region.By binary image, can be found out, fork areal distribution is intensive and concentrated and assorted select be dispersed in face cake regional and area less, so we can adopt the mode of judgement connected region area to arrange impurity point.
Extract each black connected region in image, if this connected region area is greater than setting threshold AreaThres, retain so connected region (Fig. 4).
Claims (1)
1. the barreled instant noodle image partition method after dispenser is thrown in fork, comprises the following steps:
(1) to the barreled instant noodle image gathering, adopt way of search from left to right and from right to left, each gray-scale value is face cylinder marginal point by the black point bleaching for the first time;
(2) utilize the marginal point find, by the least square fitting cylinder circle of appearing, and then try to achieve the face cylinder center of circle and detection radius r, then determine surveyed area according to the face bucket center of circle and detection radius r;
(3) according to the gray scale in fork region compared with the brighter characteristic in face cake region, choose suitable threshold value, to having determined that surveyed area carries out binary conversion treatment, the binary map in Yu Mianbing region, fork region that obtained initial gross separation;
(4) according to intensive and concentrated and assorted face cake regional and the less feature of area of being dispersed in of selecting of fork areal distribution, set screening threshold value A reaThres, extract each connected region in binary map, Retention area is greater than the connected region of screening threshold value A reaThres, using it as potential fork connected region, the barreled instant noodle image completing after dispenser is thrown in fork is cut apart.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310648933.7A CN103617619A (en) | 2013-12-04 | 2013-12-04 | Image segmentation method for cup noodles in which forks are thrown through throwing machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310648933.7A CN103617619A (en) | 2013-12-04 | 2013-12-04 | Image segmentation method for cup noodles in which forks are thrown through throwing machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103617619A true CN103617619A (en) | 2014-03-05 |
Family
ID=50168323
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310648933.7A Pending CN103617619A (en) | 2013-12-04 | 2013-12-04 | Image segmentation method for cup noodles in which forks are thrown through throwing machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103617619A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106583271A (en) * | 2016-12-28 | 2017-04-26 | 天津普达软件技术有限公司 | Method for removing defective packing box with first line of ink-jet printed characters lacked |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130223673A1 (en) * | 2011-08-30 | 2013-08-29 | Digimarc Corporation | Methods and arrangements for identifying objects |
CN103345743A (en) * | 2013-06-18 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Image segmentation method for intelligent flaw detection of cell tail end |
-
2013
- 2013-12-04 CN CN201310648933.7A patent/CN103617619A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130223673A1 (en) * | 2011-08-30 | 2013-08-29 | Digimarc Corporation | Methods and arrangements for identifying objects |
CN103345743A (en) * | 2013-06-18 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Image segmentation method for intelligent flaw detection of cell tail end |
Non-Patent Citations (1)
Title |
---|
高建伟: "基于机器视觉的方便面包装检测系统开发", 《中国优秀硕士论文全文数据库》, no. 12, 15 December 2011 (2011-12-15), pages 21 - 33 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106583271A (en) * | 2016-12-28 | 2017-04-26 | 天津普达软件技术有限公司 | Method for removing defective packing box with first line of ink-jet printed characters lacked |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104156951B (en) | A kind of white blood cell detection method for BAL fluid smear | |
CN108549874B (en) | Target detection method, target detection equipment and computer-readable storage medium | |
CN102184552B (en) | Moving target detecting method based on differential fusion and image edge information | |
EP2811423B1 (en) | Method and apparatus for detecting target | |
CN104651462B (en) | Method for detecting magnaporthe grisea spore based on microscopic image analysis | |
CN102043950B (en) | Vehicle outline recognition method based on canny operator and marginal point statistic | |
CN103366170B (en) | Image binaryzation processing unit and its method | |
CN103778627B (en) | A kind of marine site based on SAR image oil spilling detection method | |
WO2016014930A3 (en) | A vision-based system for dynamic weather detection | |
CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
CN103226829A (en) | Image edge detection method based on edge enhancement operator | |
CN103345743B (en) | A kind of image partition method for battery tail end smart flaw detection | |
CN103528534A (en) | Image monitoring based method for detecting thickness of icing on power transmission line | |
US20120207379A1 (en) | Image Inspection Apparatus, Image Inspection Method, And Computer Program | |
CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
WO2015024257A8 (en) | Unstructured road boundary detection | |
CN102509095B (en) | Number plate image preprocessing method | |
CN105719275A (en) | Parallel combination image defect segmentation method | |
CN105139391A (en) | Edge detecting method for traffic image in fog-and-haze weather | |
JP2012190258A (en) | Edge point extraction device, lane detection device, and program | |
CN102663781A (en) | Sub-pixel level welding center extraction method based on visual sense | |
CN108171693B (en) | Method for automatically detecting inferior mushrooms | |
CN103500451B (en) | A kind of independent floating ice extracting method for satellite data | |
CN105654468B (en) | A kind of tealeaves tender shoots detection method based on deep learning and image edge information | |
CN114155241A (en) | Foreign matter detection method and device and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140305 |