CN111611907A - Image-enhanced infrared target detection method - Google Patents
Image-enhanced infrared target detection method Download PDFInfo
- Publication number
- CN111611907A CN111611907A CN202010419589.4A CN202010419589A CN111611907A CN 111611907 A CN111611907 A CN 111611907A CN 202010419589 A CN202010419589 A CN 202010419589A CN 111611907 A CN111611907 A CN 111611907A
- Authority
- CN
- China
- Prior art keywords
- image
- target detection
- target
- follows
- infrared
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 91
- 238000006243 chemical reaction Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 15
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000005855 radiation Effects 0.000 abstract description 3
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract 1
- 238000000605 extraction Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image-enhanced infrared target detection method, which belongs to the technical field of infrared target attribute identification, and is characterized in that a clear infrared image data set is established, and relevant parameters of a target detection network, such as learning rate, momentum and the like, are set; training a target detection algorithm network; carrying out self-adaptive gamma conversion on the infrared image to increase the contrast of the infrared image; enhancing the details of the image by using a Sobel operator edge enhancement method; and inputting the infrared image subjected to the image enhancement algorithm into a target detection algorithm to extract features, and detecting and classifying the features. By introducing the image enhancement algorithm, the invention effectively avoids the problem that the convolution neural network target detection algorithm is not obvious in the extraction characteristics of the infrared image, and makes up the problem that the infrared image target and the target with small environmental heat radiation intensity difference or far small target are detected to generate false identification and missing identification.
Description
Technical Field
The invention relates to the technical field of infrared target attribute identification, in particular to an image-enhanced infrared target detection method.
Background
The infrared target detection has the main functions of positioning targets in which people are interested according to input infrared image information, specifically classifying the positioned targets and finally giving confidence scores; at present, an infrared target detection technology is widely applied to the field of intelligent traffic management, and can remarkably improve the performance of traffic supervision and vehicle management and control in an intelligent traffic management system; in recent years, scholars at home and abroad carry out a great deal of research on target detection, including methods such as target detection based on pixel point characteristics, target detection based on characteristic descriptors, target detection based on a gray singular value method, target detection based on a magnetoresistive sensor, target detection based on a BP neural network and the like, and the scholars use the target detection method based on a convolutional neural network to detect infrared targets interested in people, so that the scholars can achieve very excellent effect under certain conditions; however, under the condition that the input infrared image is not clear enough and the characteristics of the target to be recognized are not obvious enough, the target detection algorithm of the convolutional neural network is easy to generate the problems of false recognition and missing recognition; meanwhile, a lot of scholars improve the target detection algorithm based on the convolutional neural network, such as: the method for extracting the infrared image target features deepens the layer number of the convolutional neural network, changes the activation function of the convolutional neural network, combines a multilayer feature map and the like, increases the diversity of the extracted features, but under the condition that the features of the infrared image target to be identified are not obvious, the phenomenon that the extracted features cannot well distinguish the target attributes and repeatedly extract irrelevant features still occurs.
For the shot infrared image, due to the limitation of the shooting equipment, the quality of the infrared image is uneven, the contrast of the shot infrared image is low, and the long-distance target is not clear in imaging. For infrared images with gray scales, the influence of contrast on visual effect is very critical, and generally, the higher the contrast is, the sharper the image is. The self-adaptive gamma conversion can automatically select a proper gamma value according to the brightness of the shot infrared image, perform gamma conversion on the input infrared image, and stretch the dark area or the bright area of the image to different degrees, so that the contrast of the image is enhanced, namely the image can be clearer. Meanwhile, under the condition that the shot target is far away or small in distance, the shot target is low in thermal radiation intensity and unclear in imaging, and the edge detection method based on the Sobel operator is used for extracting and enhancing the edge of the input infrared image, so that the definition degree of the target is increased, the problem of target feature blurring caused by gray scale compression due to gamma conversion is weakened, and the image is clearer.
Currently, researchers have proposed using gamma transformation or Sobel operator edge detection in the field of image processing. Meanwhile, a learner uses an image enhancement algorithm to enhance the infrared image, and combines a traditional target attribute algorithm to detect the target, so that the defect that the extracted features are not obvious due to the fact that the infrared image is not clear can be overcome, and the accuracy of target detection is improved.
Because the development time of the target detection algorithm based on the convolutional neural network is not long, the theoretical basis and the application and popularization need further deep research, the gamma value is adaptively selected according to the image condition at home and abroad to carry out the gamma transformation and the research of edge enhancement by using a Sobel operator, and related documents are few. Meanwhile, the method is combined with a target detection algorithm based on a convolutional neural network and applied to infrared target detection, and related research is few.
It is therefore desirable to devise an image enhanced infrared target detection method that overcomes or at least mitigates the above-mentioned deficiencies of the prior art.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an image enhancement infrared target detection method, which introduces an image enhancement algorithm into a convolution neural network infrared target detection algorithm, and enhances the image contrast by using self-adaptive gamma conversion; meanwhile, the image is enhanced by using an edge enhancement method based on a Sobel operator, the problems of false recognition and missing recognition caused by the fact that a convolutional neural network infrared target detection algorithm detects a target with small difference of thermal radiation intensity with the environment or a far small target are solved, and the confidence coefficient and the accuracy of convolutional neural network infrared target detection are improved.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: an image-enhanced infrared target detection method, the flow of which is shown in fig. 1, includes the following steps:
step 1: acquiring a target detection image and carrying out gray level transformation according to a gray level i;
step 2: performing gamma conversion on the gray level image detected by the target based on a self-adaptive gamma conversion method to obtain a converted image s;
step 2.1: determining the gamma value of the self-adaptive gamma conversion according to the number of the pixel points of each gray level;
step 2.1.1: counting the number num of pixels corresponding to each gray level of the target detection image after gray level transformationi；
Step 2.1.2: based on a self-adaptive gamma conversion method, acquiring a gray level gray corresponding to the maximum value of the number of accumulated pixel points of 15 adjacent gray levels in a target detection image, wherein the calculation formula is as follows:
step 2.1.3: determining the gamma value of the adaptive gamma conversion, wherein the calculation formula is as follows:
step 2.2: carrying out gamma conversion on the target detection image, wherein the process is as follows:
s＝crγ,(c,γ＞0)(s,r∈[0,1])
wherein r is the value of the normalized gray value of the pixel point of the input image, s is the value of the normalized gray value of the pixel point of the output image, and c and gamma are constants.
And step 3: performing edge enhancement on the image s subjected to the self-adaptive gamma transformation based on a Sobel operator to obtain an enhanced image G;
step 3.1: based on a Sobel operator, solving an X-direction edge image of the image s after the self-adaptive gamma transformation, wherein a calculation formula is as follows:
wherein G isxIs an X-direction edge image of the s-image;
step 3.2: and (3) solving a Y-direction edge image of the image s after the self-adaptive gamma conversion, wherein the calculation formula is as follows:
wherein G isyIs the Y-direction edge image of the s-image;
step 3.3: and calculating the image G after the edge enhancement of the s image, wherein the calculation formula is as follows:
G*＝a×G+b×s，(a+b＝1)
wherein, a and b are weighted values.
And 4, step 4: and inputting the image G subjected to edge enhancement into a target detection algorithm based on a convolutional neural network for target detection.
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in:
(1) the self-adaptive gamma conversion which automatically selects a proper gamma value according to the brightness condition of the picture is designed on the basis of the gamma conversion, so that the infrared enhancement efficiency of the gamma conversion is improved, and the problem that the proper gamma value needs to be manually adjusted due to different brightness conditions of the picture is effectively solved;
(2) an edge enhancement method based on a Sobel operator is designed on the basis of Sobel operator edge detection, which can increase image details, improve the details of the target of an infrared image and effectively avoid the problem of gray scale disappearance caused by gamma conversion;
(3) an image-enhanced infrared target detection method is designed, self-adaptive gamma transformation and an edge enhancement method based on a Sobel operator are introduced into a convolutional neural network target detection algorithm, the image definition degree and the target characteristic saliency are improved, the problem that the characteristic extracted by a convolutional neural network is not obvious is effectively avoided, and the confidence coefficient and the accuracy of convolutional neural network infrared target detection are improved.
Drawings
FIG. 1 is a flow chart of a method for image-enhanced infrared target detection in accordance with the present invention;
FIG. 2 is a comparison graph of infrared target detection before and after introduction of the method of the present invention in an embodiment of the present invention;
FIG. 3 is a comparison chart of confidence level conditions of infrared target detection before and after the method of the present invention is introduced in the embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
As shown in fig. 1, the method of the present embodiment is as follows.
Step 1: acquiring a target detection image and carrying out gray level transformation according to a gray level i;
step 2: performing gamma conversion on the gray level image detected by the target based on a self-adaptive gamma conversion method to obtain a converted image s;
step 2.1: determining the gamma value of the self-adaptive gamma conversion according to the number of the pixel points of each gray level;
step 2.1.1: counting the number num of pixels corresponding to each gray level of the target detection image after gray level transformationi；
Step 2.1.2: based on a self-adaptive gamma conversion method, acquiring a gray level gray corresponding to the maximum value of the number of accumulated pixel points of 15 adjacent gray levels in a target detection image, wherein the calculation formula is as follows:
step 2.1.3: determining the gamma value of the adaptive gamma conversion, wherein the calculation formula is as follows:
step 2.2: carrying out gamma conversion on the target detection image, wherein the process is as follows:
s＝crγ,(c,γ＞0)(s,r∈[0,1])
where r is a value obtained by normalizing the gray scale value of the pixel of the input image, s is a value obtained by normalizing the gray scale value of the pixel of the output image, c and γ are constants, and c is 1 in this embodiment.
And step 3: performing edge enhancement on the image s subjected to the self-adaptive gamma transformation based on a Sobel operator to obtain an enhanced image G;
step 3.1: based on a Sobel operator, solving an X-direction edge image of the image s after the self-adaptive gamma transformation, wherein a calculation formula is as follows:
wherein G isxIs an X-direction edge image of the s-image;
step 3.2: and (3) solving a Y-direction edge image of the image s after the self-adaptive gamma conversion, wherein the calculation formula is as follows:
wherein G isyIs the Y-direction edge image of the s-image;
step 3.3: and calculating the image G after the edge enhancement of the s image, wherein the calculation formula is as follows:
G*＝a×G+b×s，(a+b＝1)
in this embodiment, a is 0.3, and b is 0.7.
And 4, step 4: and inputting the image G subjected to edge enhancement into a target detection algorithm based on a convolutional neural network for target detection.
In order to verify the effectiveness and feasibility of the self-adaptive gamma conversion (namely, the AGT-Enhance algorithm) and the image-enhanced infrared target detection method (namely, the AE-Enhance algorithm), a comparison test is respectively designed by using Tensorflow-Linux. For the AGT-Enhance algorithm, a single gamma value is designed to Enhance an infrared image, gamma is 1, 0.5, 2 and 3.5 (namely GT-Enhance-a, b, c and d), the enhanced infrared image is detected by selecting a Mask R-CNN target detection algorithm, and the detection result is compared with the detection result enhanced by the algorithm for adaptively selecting the gamma value; for AE-Enhance algorithm, and infrared image detection result without enhancement (i.e. No-Enhance algorithm) and infrared image detection result with common image processing method, such as global histogram equalization (i.e. GHE-Enhance algorithm), local histogram equalization (i.e. LHE-Enhance algorithm), contrast-limited adaptive histogram equalization (i.e. CLAHE-Enhance algorithm), multi-scale Retinex enhancement (i.e. MSR-Enhance algorithm), bilateral filtering (i.e. BF-Enhance algorithm) and median filtering (i.e. MF-Enhance algorithm), improved adaptive gamma transformation (i.e. AGT-Enhance algorithm) and edge enhancement method based on Sobel operator improvement (i.e. EEBS-Enhance algorithm), the image processing method is put into the infrared image enhancement, and Mask R-CNN target detection method is used for detection, compared with the AE-Enhance algorithm of the invention, the experimental results are shown in tables 1 and 2:
TABLE 1 adaptive Gamma transform experiment
As can be seen from the statistical data in table 1, when γ is 0.5 or 2, that is, GT-Enhance-b and GT-Enhance-c, the detection results of the infrared images after gamma conversion are both higher than those of the infrared images without gamma conversion GT-Enhance-a, and are respectively higher than AP values by 1.52% and 2.01%. And when gamma is 3.5, namely GT-Enhance-d, the detection result of the infrared image after gamma conversion is 1.65% lower than that of GT-Enhance-a. When the self-adaptive gamma transformation is adopted, namely AGT-Enhance is higher than the detection effect of the gamma transformation which adopts fixed values, and the AP value is respectively higher than GT-Enhance-a, GT-Enhance-b, GT-Enhance-c and GT-Enhance-d by 2.87%, 1.35%, 0.86% and 4.52%.
TABLE 2 detection results of infrared images after different enhancement algorithms
As can be seen from the statistical data in Table 2, only CLAHE-Enhance and MF-Enhance have positive effects on infrared image target detection in other selected image processing methods. Compared with the detection result of No-Enhance without any enhancement method, the AP value is higher by 0.39 percent and 1.19 percent, and the enhancement effect is not obvious. The detection effect of the infrared image is 2.87% higher than that of No-Enhance without any image enhancement method by only adopting the image enhancement method AGT-Enhance of adaptive gamma conversion. Similarly, the detection effect of EEBS-Enhance is 2.36% higher than that of No-Enhance only by adopting the edge enhancement method based on the Sobel operator. The image enhancement method AGT-Enhance of self-adaptive gamma conversion has the best effect in a single image enhancement method. The AE-Enhance is the image-enhanced infrared target detection method, the detection effect is best, the AP value is 54.10%, and the detection effects are respectively 4.48% and 1.61% higher than those of No-Enhance and AGT-Enhance.
The AP value is an evaluation index of the target detection algorithm, and this embodiment continues to use an evaluation system in the COCO challenge match: AP, AP @50, AP @ 75. The calculation formula of the AP value is as follows:
wherein Precision is Precision, Recall is Recall, m is the number of detected images in the detection result, and i is the ith detected image; TP is the detection result of correctly detecting the foreground target as the foreground target, FP is the detection result of incorrectly detecting the background as the foreground target, TN is the detection result of correctly detecting the background as the background, and FN is the detection result of incorrectly detecting the foreground target as the background.
In the target detection algorithm, IoU (interaction-over-Unit) is a threshold for evaluating whether the detection algorithm identifies a foreground target, that is, when the detection confidence of the foreground target is higher than IoU threshold, the foreground target is determined as Positive. Therefore, different IoU are set, and the number of Positive samples and the AP value calculated by the same will be different, and the calculation formula of IoU is as follows:
wherein, among them,
wherein S isAIs the area of the label box (Ground Truth), SBThe area of the orientation box is predicted.
(1) AP: in this example, the main evaluation index was that when IoU was in the range of 0.5 to 0.95, the AP value was calculated every 0.05,
and averaging all the AP values;
(2) AP @ 50: AP value when IoU takes 0.5;
(3) AP @ 75: an AP value when IoU takes 0.75;
(4) AP @ S: less than 32 pixel points2The target of (1) calculates the AP value;
(5) AP @ M: for the number of pixel points greater than 322And less than 962The target of (1) calculates the AP value;
(6) AP @ L: for the number of pixel points greater than 962The target of (1) calculates the AP value.
As can be seen from fig. 2 and 3, the missing recognition phenomenon of the AE-Enhance algorithm is significantly reduced compared with the No-Enhance algorithm, and the confidence of detection is significantly improved. The missing identification phenomenon of the AE-Enhance algorithm infrared target detection effectively improves the confidence coefficient and the identification accuracy of the detection, and provides a new method and a new approach for the infrared target detection problem based on the convolutional neural network.
Claims (5)
1. An image-enhanced infrared target detection method is characterized by comprising the following steps:
step 1: acquiring a target detection image and carrying out gray level transformation according to a gray level i;
step 2: performing gamma conversion on the gray level image detected by the target based on a self-adaptive gamma conversion method to obtain a converted image s;
and step 3: performing edge enhancement on the image s subjected to the self-adaptive gamma transformation based on a Sobel operator to obtain an enhanced image G;
and 4, step 4: and inputting the image G subjected to edge enhancement into a target detection algorithm based on a convolutional neural network for target detection.
2. The image-enhanced infrared target detection method according to claim 1, characterized in that the process of step 2 is as follows:
step 2.1: determining the gamma value of the self-adaptive gamma conversion according to the number of the pixel points of each gray level;
step 2.2: and carrying out gamma conversion on the target detection image.
3. An image-enhanced infrared target detection method according to claim 2, characterized in that the procedure of step 2.1 is as follows:
step 2.1.1: counting the number num of pixels corresponding to each gray level of the target detection image after gray level transformationi；
Step 2.1.2: based on a self-adaptive gamma conversion method, acquiring a gray level gray corresponding to the maximum value of the number of accumulated pixel points of 15 adjacent gray levels in a target detection image, wherein the calculation formula is as follows:
step 2.1.3: determining the gamma value of the adaptive gamma conversion, wherein the calculation formula is as follows:
4. the image-enhanced infrared target detection method of claim 2, wherein the gamma conversion of the target detection image is performed as follows:
s＝crγ,(c,γ＞0)(s,r∈[0,1])
wherein r is the value of the normalized gray value of the pixel point of the input image, s is the value of the normalized gray value of the pixel point of the output image, and c and gamma are constants.
5. The image-enhanced infrared target detection method according to claim 1, characterized in that the procedure of step 3 is as follows:
step 3.1: based on a Sobel operator, solving an X-direction edge image of the image s after the self-adaptive gamma transformation, wherein a calculation formula is as follows:
wherein G isxIs an X-direction edge image of the s-image;
step 3.2: and (3) solving a Y-direction edge image of the image s after the self-adaptive gamma conversion, wherein the calculation formula is as follows:
wherein G isyIs the Y-direction edge image of the s-image;
step 3.3: and calculating the image G after the edge enhancement of the s image, wherein the calculation formula is as follows:
G*＝a×G+b×s，(a+b＝1)
wherein, a and b are weighted values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010419589.4A CN111611907B (en) | 2020-05-18 | 2020-05-18 | Image-enhanced infrared target detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010419589.4A CN111611907B (en) | 2020-05-18 | 2020-05-18 | Image-enhanced infrared target detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111611907A true CN111611907A (en) | 2020-09-01 |
| CN111611907B CN111611907B (en) | 2023-10-31 |
Family
ID=72204982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010419589.4A Active CN111611907B (en) | 2020-05-18 | 2020-05-18 | Image-enhanced infrared target detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611907B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200788A (en) * | 2020-10-16 | 2021-01-08 | 清华大学 | High-temperature deformation measuring device and method |
| CN112287772A (en) * | 2020-10-10 | 2021-01-29 | 深圳市中达瑞和科技有限公司 | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium |
| CN112365426A (en) * | 2020-11-25 | 2021-02-12 | 兰州理工大学 | Infrared image edge enhancement method based on double-branch convolutional neural network |
| CN112700386A (en) * | 2020-12-30 | 2021-04-23 | 江苏奥格视特信息科技有限公司 | Fuzzy image ultrahigh-definition transformation method and system based on artificial intelligence |
| CN115330644A (en) * | 2022-10-13 | 2022-11-11 | 极限人工智能有限公司 | Adaptive edge enhancement method and system for endoscope image |
| CN116030052A (en) * | 2023-03-27 | 2023-04-28 | 惠州威尔高电子有限公司 | Etching quality detection method for lamination process of computer display panel |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574435A (en) * | 2014-09-24 | 2015-04-29 | 中国人民解放军国防科学技术大学 | Motion camera foreground segmentation method based on block clustering |
| CN110599415A (en) * | 2019-08-29 | 2019-12-20 | 西安电子科技大学 | Image contrast enhancement implementation method based on local adaptive gamma correction |
| CN110930390A (en) * | 2019-11-22 | 2020-03-27 | 郑州智利信信息技术有限公司 | Chip pin missing detection method based on semi-supervised deep learning |
-
2020
- 2020-05-18 CN CN202010419589.4A patent/CN111611907B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574435A (en) * | 2014-09-24 | 2015-04-29 | 中国人民解放军国防科学技术大学 | Motion camera foreground segmentation method based on block clustering |
| CN110599415A (en) * | 2019-08-29 | 2019-12-20 | 西安电子科技大学 | Image contrast enhancement implementation method based on local adaptive gamma correction |
| CN110930390A (en) * | 2019-11-22 | 2020-03-27 | 郑州智利信信息技术有限公司 | Chip pin missing detection method based on semi-supervised deep learning |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287772A (en) * | 2020-10-10 | 2021-01-29 | 深圳市中达瑞和科技有限公司 | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium |
| CN112200788A (en) * | 2020-10-16 | 2021-01-08 | 清华大学 | High-temperature deformation measuring device and method |
| CN112365426A (en) * | 2020-11-25 | 2021-02-12 | 兰州理工大学 | Infrared image edge enhancement method based on double-branch convolutional neural network |
| CN112700386A (en) * | 2020-12-30 | 2021-04-23 | 江苏奥格视特信息科技有限公司 | Fuzzy image ultrahigh-definition transformation method and system based on artificial intelligence |
| CN115330644A (en) * | 2022-10-13 | 2022-11-11 | 极限人工智能有限公司 | Adaptive edge enhancement method and system for endoscope image |
| CN116030052A (en) * | 2023-03-27 | 2023-04-28 | 惠州威尔高电子有限公司 | Etching quality detection method for lamination process of computer display panel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111611907B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111611907B (en) | Image-enhanced infrared target detection method | |
| CN111611905B (en) | Visible light and infrared fused target identification method | |
| CN109145872B (en) | CFAR and Fast-RCNN fusion-based SAR image ship target detection method | |
| CN110490914A (en) | It is a kind of based on brightness adaptively and conspicuousness detect image interfusion method | |
| CN112200143A (en) | Road disease detection method based on candidate area network and machine vision | |
| CN109255326B (en) | Traffic scene smoke intelligent detection method based on multi-dimensional information feature fusion | |
| CN107944354B (en) | Vehicle detection method based on deep learning | |
| CN108898132A (en) | A kind of terahertz image dangerous material recognition methods based on Shape context description | |
| WO2021118463A1 (en) | Defect detection in image space | |
| CN108335294A (en) | The power distribution room abnormality image-recognizing method of complex condition | |
| CN112561899A (en) | Electric power inspection image identification method | |
| CN109190455A (en) | Black smoke vehicle recognition methods based on Gaussian Mixture and autoregressive moving-average model | |
| CN110689003A (en) | Low-illumination imaging license plate recognition method and system, computer equipment and storage medium | |
| CN111507391A (en) | Intelligent identification method for nonferrous metal broken materials based on machine vision | |
| CN111027564A (en) | Low-illumination imaging license plate recognition method and device based on deep learning integration | |
| CN113205494B (en) | Infrared small target detection method and system based on adaptive scale image block weighting difference measurement | |
| CN116823756A (en) | Pile leg weld defect detection method | |
| CN117197064A (en) | Automatic non-contact eye red degree analysis method | |
| CN113221603A (en) | Method and device for detecting shielding of monitoring equipment by foreign matters | |
| US20230386023A1 (en) | Method for detecting medical images, electronic device, and storage medium | |
| CN114998186B (en) | Method and system for detecting surface scab defect of copper starting sheet based on image processing | |
| CN104408430B (en) | License plate positioning method and device | |
| CN114612333B (en) | Microscopic image-based micro-capsule algae cell statistical method | |
| CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
| CN114694090A (en) | Campus abnormal behavior detection method based on improved PBAS algorithm and YOLOv5 |
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 | ||
| GR01 | Patent grant |