CN113313652A - Method for removing clutter of security inspection image by adopting morphology - Google Patents
Method for removing clutter of security inspection image by adopting morphology Download PDFInfo
- Publication number
- CN113313652A CN113313652A CN202110672994.1A CN202110672994A CN113313652A CN 113313652 A CN113313652 A CN 113313652A CN 202110672994 A CN202110672994 A CN 202110672994A CN 113313652 A CN113313652 A CN 113313652A
- Authority
- CN
- China
- Prior art keywords
- image
- security inspection
- inspection image
- setting
- clutter
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000001914 filtration Methods 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002592 echocardiography Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 210000000746 body region Anatomy 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a method for removing clutter of a security inspection image by adopting morphology, which comprises the steps of setting a binary threshold value to obtain a binary image of the security inspection image, selecting a wider threshold value, extracting a main part of an echo region in the security inspection image, eliminating most of the clutter, and setting an expansion radius to obtain a complete echo region; the method has the advantages that the background clutter in the security check image is removed by using the image morphology, the complete echo information is kept, the method is simple and feasible, the robustness is good, the quality of the security check image is improved, and the detection and identification effects are guaranteed.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a clutter filtering technology.
Background
The clutter of the active millimeter wave security inspection image is removed, the quality of the security inspection image is improved, the identification rate of dangerous goods targets is improved, and the false alarm rate is reduced. Unlike optical images, security images are grayscale images, and except for human body parts, the background parts should have only noise.
Because the structure of the active millimeter wave security check instrument is front-back double-side scanning, and the frames of most security check equipment are metal structures, the part with stronger echo appears in a clutter form in a security check image. The occurrence of background clutter is not beneficial to target detection and identification, and brings great interference to dangerous goods identification.
And removing background clutter of the security inspection image through image processing, and reserving all information of the human body echo. At present, the processing of security inspection images mainly focuses on the aspect of X-ray images, and is mostly enhancement or denoising processing. In millimeter wave human body security inspection images, the technical achievement of the de-clutter algorithm is less, and the prior art for security inspection image processing comprises the following steps:
enhancing the X-ray image by using a Contourlet transformation enhancing technology on the premise of not amplifying noise; processing the X-ray security inspection image interfered by noise by using an algorithm of a Perona-Malik (P-M) anisotropic diffusion equation; according to the characteristic that the CT security inspection image contains both Gaussian white noise and pulse noise, the Db wavelet transform and the median filtering are combined, and the Gaussian noise and the pulse noise are filtered, so that a better visual effect is obtained.
Disclosure of Invention
The invention provides a method for removing clutter of a security check image by adopting morphology in order to solve the problems in the prior art, an echo area is obtained by image morphology processing, a background clutter signal is removed by an image template, and echo area information is completely reserved.
Security inspection image binarization: and setting a binary threshold value Th, assigning a value of 1 to a pixel in the security inspection image larger than the threshold value, and otherwise, assigning a value of 0 to obtain a binary image of the security inspection image.
If a fixed threshold is chosen, part of the target information is lost and part of the stronger clutter remains. The intensity of background clutter is generally lower than that of human echoes, and a higher threshold value is selected, so that most of the background clutter can be eliminated, and the main part of the echoes is reserved. And a wider threshold is selected, so that the main part of the echo region in the security inspection image can be extracted, and most of clutter is eliminated.
Image expansion: and setting the expansion radius as r, and expanding the part of the binary image with the pixel value of 1 to obtain a complete echo region.
The binarization threshold is relatively large, and although most of background clutter is eliminated, image information of a part of echo areas is lost. And expanding pixels of the echo region by adopting an expansion operation of image morphology, and recovering the excluded information in the echo region.
Further, the expansion radius r is set according to the actual intensity of the echo signal and the binarization result thereof.
Smoothing and filtering: setting radius of two-dimensional Gaussian filter to be rgStandard deviation of σgAnd modifying the pixel value of a transition region of changing the pixel value from 0 to 1 or from 1 to 0 into a decimal between 0 and 1 by adopting a Gaussian filtered binary image.
The pixel values of the binary image are only 0 and 1, and the pixel values are multiplied by the security check image, so that the edge of an echo area has a large step, and the security check quality is influenced. And (3) after the binary image is subjected to Gaussian filtering, keeping the pixels with the echo region value of 1 unchanged, and keeping the pixels with the background region value of 0 unchanged.
Clutter removal: and multiplying the filtered binary image by the corresponding element of the security inspection image.
After elements of the two images are correspondingly multiplied, the echo area is completely reserved, the background clutter is effectively inhibited, and the transition part realizes the smooth transition of numerical values due to smooth filtering processing.
The invention has the beneficial effects that: the method has the advantages that the background clutter in the security check image is removed by using the image morphology, the complete echo information is kept, the method is simple and feasible, the robustness is good, the quality of the security check image is improved, and the detection and identification effects are guaranteed.
Drawings
Fig. 1 is a security inspection image, fig. 2 is a binary image, fig. 3 is an expansion image, fig. 4 is a filter image, and fig. 5 is a culled image.
Detailed Description
The technical scheme of the invention is specifically explained in the following by combining the attached drawings.
As shown in fig. 1, a binary segmentation threshold 40 is set for the human body security inspection image, and binarization processing is performed on the security inspection image to obtain a binary image of the security inspection image, as shown in fig. 2.
And (3) performing image expansion operation on the security check binary image, wherein the expansion radius is 40, circular expansion is selected, and the image expansion result is shown in figure 3.
The expanded image is subjected to gaussian smoothing filtering with a gaussian filter radius of 50 and a standard deviation of 30, and the smoothing filtering result is shown in fig. 4.
It can be seen from the figure that the value of 1 is still maintained in the interior of the human body region, the value of 0 is still maintained in the background portion, and the value of the transition region between 1 and 0 is smoothly transited.
And multiplying the filtered image by the corresponding element of the security inspection image to obtain an image without the background clutter, as shown in fig. 5.
The above-described embodiments are not intended to limit the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the present invention.
Claims (2)
1. A method for removing noise in a security inspection image by adopting morphology is characterized by comprising the following steps:
security inspection image binarization: setting a binary threshold value Th, assigning a value of 1 to a pixel in the security inspection image larger than the threshold value, and otherwise, assigning a value of 0 to obtain a binary image of the security inspection image;
image expansion: setting the expansion radius as r, and expanding the part of the binary image with the pixel value of 1 to obtain a complete echo region;
smoothing and filtering: setting radius of two-dimensional Gaussian filter to be rgStandard deviation of σgAdopting a Gaussian filtered binary image to modify the pixel value of a transition region of which the pixel value is changed from 0 to 1 or from 1 to 0 into a decimal number between 0 and 1;
clutter removal: and multiplying the filtered binary image by the corresponding element of the security inspection image.
2. The method for removing noise from security image by morphology according to claim 1, wherein setting the dilation radius to r comprises: and setting the expansion radius r according to the actual intensity of the echo signal and the binarization result thereof.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110458436 | 2021-04-27 | ||
| CN2021104584365 | 2021-04-27 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113313652A true CN113313652A (en) | 2021-08-27 |
| CN113313652B CN113313652B (en) | 2024-07-02 |
Family
ID=77379360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110672994.1A Active CN113313652B (en) | 2021-04-27 | 2021-06-17 | Method for removing clutter of security inspection image by adopting morphology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313652B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226033A1 (en) * | 2007-10-15 | 2009-09-10 | Sefcik Jason A | Method of object recognition in image data using combined edge magnitude and edge direction analysis techniques |
| CN106791663A (en) * | 2016-12-28 | 2017-05-31 | 天津天地伟业生产力促进有限公司 | A kind of tracking focusing algorithm based on background modeling |
| CN107240081A (en) * | 2017-06-20 | 2017-10-10 | 长光卫星技术有限公司 | The denoising of night scene image and enhancing processing method |
| CN110211086A (en) * | 2018-02-28 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Image partition method, device and storage medium |
| CN110458012A (en) * | 2019-07-05 | 2019-11-15 | 南京邮电大学 | Multi-angle human face recognition method and device, storage medium and terminal |
-
2021
- 2021-06-17 CN CN202110672994.1A patent/CN113313652B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226033A1 (en) * | 2007-10-15 | 2009-09-10 | Sefcik Jason A | Method of object recognition in image data using combined edge magnitude and edge direction analysis techniques |
| CN106791663A (en) * | 2016-12-28 | 2017-05-31 | 天津天地伟业生产力促进有限公司 | A kind of tracking focusing algorithm based on background modeling |
| CN107240081A (en) * | 2017-06-20 | 2017-10-10 | 长光卫星技术有限公司 | The denoising of night scene image and enhancing processing method |
| CN110211086A (en) * | 2018-02-28 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Image partition method, device and storage medium |
| CN110458012A (en) * | 2019-07-05 | 2019-11-15 | 南京邮电大学 | Multi-angle human face recognition method and device, storage medium and terminal |
Non-Patent Citations (3)
| Title |
|---|
| 王春歆;周晓东;张玉叶;: "基于疑似目标区域提取的空间图像降噪", 电光与控制, no. 09 * |
| 赵春晖;王佳;王玉磊;: "采用背景抑制和自适应阈值分割的高光谱异常目标检测", 哈尔滨工程大学学报, no. 02 * |
| 高士博;闵锦忠;黄丹莲;: "贝叶斯膨胀算法对EnSRF雷达资料同化的影响研究", 大气科学, no. 05, 15 September 2016 (2016-09-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113313652B (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Srivastava et al. | Combination of wavelet transform and morphological filtering for enhancement of magnetic resonance images | |
| CN104616255B (en) | Self-adapting enhancement method based on mammography X | |
| CN106096491B (en) | Automatic identification method for microaneurysms in fundus color photographic image | |
| CN102270340B (en) | Method and system for enhancing text image based on stroke operator | |
| Koundal et al. | Neutrosophic based Nakagami total variation method for speckle suppression in thyroid ultrasound images | |
| Sahu et al. | Minimum time delay and more efficient image filtering brain tumour detection with the help of MATLAB | |
| Shedbalkar et al. | A comparative analysis of filters for noise reduction and smoothening of brain MRI images | |
| Lbachir et al. | A new mammogram preprocessing method for Computer-Aided Diagnosis systems | |
| CN103927715A (en) | Ultrasound image speckle noise suppression method | |
| CN106910166B (en) | Image processing method and device | |
| Rajabi et al. | Non-local adaptive hysteresis despeckling approach for medical ultrasound images | |
| Valliammal et al. | A hybrid method for enhancement of plant leaf recognition | |
| Das et al. | Medical image enhancement techniques by bottom hat and median filtering | |
| CN113313652B (en) | Method for removing clutter of security inspection image by adopting morphology | |
| Sevani et al. | Implementation of image processing techniques for identifying different stages of lung cancer | |
| Sivakumar et al. | Computed radiography skull image enhancement using Wiener filter | |
| EP2328124B1 (en) | Method of enhancing the contrast of spatially-localized phenomena in an image | |
| CN113940702B (en) | Thyroid nodule echo analysis device | |
| Wu et al. | Bi-lateral filtering based edge detection on hexagonal architecture | |
| CN114022879B (en) | Squamous cell structure enhancement method based on optical fiber microscopy endoscope image | |
| Keerthivasan et al. | Speckle noise reduction in ultrasound images using fuzzy logic based on histogram and directional differences | |
| Lee et al. | Enhancement of blood vessels in retinal imaging using the nonsubsampled contourlet transform | |
| CN114913099A (en) | Method and system for processing video file | |
| CN113052833A (en) | Non-vision field imaging method based on infrared thermal radiation | |
| Ghatwary et al. | Liver CT enhancement using fractional differentiation and integration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |