CN115049636A - Computer image processing method - Google Patents
Computer image processing method Download PDFInfo
- Publication number
- CN115049636A CN115049636A CN202210811726.8A CN202210811726A CN115049636A CN 115049636 A CN115049636 A CN 115049636A CN 202210811726 A CN202210811726 A CN 202210811726A CN 115049636 A CN115049636 A CN 115049636A
- Authority
- CN
- China
- Prior art keywords
- image
- processing
- image information
- computer
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20004—Adaptive image processing
-
- 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
- G06T2207/20081—Training; Learning
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种计算机图像处理方法,本发明通过对获取的图像进行预处理操作,预处理包括缺陷检测修正、锐化处理、平滑度处理、光圈修正处理、去噪滤波处理和对比度增强处理,缺陷检测修正通过构建深度卷织神经网络模型对采集的图像进行缺陷识别,并进行缺陷特征提取,然后对其进行修正并与常规锐化处理、平滑度处理、光圈修正处理、去噪滤波处理和对比度增强处理配合,可以消除图像中无关的信息,恢复有用的真实信息,增强有关信息的可检测性和最大限度地简化数据,从而改进特征抽取、图像分割、匹配和识别的可靠性,提高图像的清晰度,使得图像显示质量更高,用户使用体验更好。The invention discloses a computer image processing method. The invention performs preprocessing operations on the acquired images, and the preprocessing includes defect detection correction, sharpening processing, smoothness processing, aperture correction processing, denoising filtering processing and contrast enhancement processing , Defect detection and correction By building a deep convolutional neural network model to identify defects in the collected images, extract defect features, and then correct them and combine them with conventional sharpening, smoothness, aperture correction, and denoising filtering. Combined with contrast enhancement processing, it can eliminate irrelevant information in the image, restore useful real information, enhance the detectability of relevant information and simplify data to the greatest extent, thereby improving the reliability of feature extraction, image segmentation, matching and recognition. The clarity of the image makes the image display quality higher and the user experience better.
Description
技术领域technical field
本发明涉及计图像处理技术领域,具体是一种计算机图像处理方法。The invention relates to the technical field of computer image processing, in particular to a computer image processing method.
背景技术Background technique
计算机图像处理又称为数字图像处理,它是指将图像信号转换成数字信号并利用计算机对其进行处理的过程,随着计算机技术的快速发展,计算机图像处理已经广泛应用到了人类社会生活的各个方面,如:工业检测、医学、智能机器人等,无论在哪个领域中,人们喜欢采用图像的方式来描述和表达事物的特性与逻辑关系,因此,计算机图像处理技术的发展及对其的要求就越来显得重要。Computer image processing, also known as digital image processing, refers to the process of converting image signals into digital signals and using computers to process them. With the rapid development of computer technology, computer image processing has been widely used in all aspects of human social life. For example: industrial testing, medicine, intelligent robots, etc., no matter in which field, people like to use images to describe and express the characteristics and logical relationships of things. Therefore, the development of computer image processing technology and its requirements are increasingly important.
计算机图像处理的过程通常分为图像信息获取与存储、图像信息传送、图像信息预处理、图像信息处理、图像信息输出与显示等,在分析图像问题时,由于环境和拍摄自身因素影响,使得计算机获取的图像存在一定的问题,同时由于操作的要求,需要对图像进行一定的转换,所以在处理图像之前,要对图像做出预处理,方便后期操作,但是,传统的计算机图像处理方法对于图像的预处理效果较差,对于图像拍摄时环境中光线、镜头表面灰尘以及传输信号不稳定对图像导致的图像不清楚甚至图像信息缺失等问题处理效果较差,最终显示的图像往往质量不高,为此,需要发明一种新的计算机图像处理方法,以解决上述存在的问题。The process of computer image processing is usually divided into image information acquisition and storage, image information transmission, image information preprocessing, image information processing, and image information output and display. There are certain problems in the acquired image, and at the same time, due to the requirements of operation, the image needs to be converted to a certain extent, so before processing the image, it is necessary to preprocess the image to facilitate the later operation. However, the traditional computer image processing method The preprocessing effect of the camera is poor, and the processing effect is poor for the problems such as unclear image or even lack of image information caused by the light in the environment, the dust on the lens surface and the unstable transmission signal when the image is taken, and the final displayed image is often of low quality. Therefore, it is necessary to invent a new computer image processing method to solve the above-mentioned problems.
发明内容SUMMARY OF THE INVENTION
本发明的目的在于提供一种计算机图像处理方法,以解决上述背景技术中提出的问题。The purpose of the present invention is to provide a computer image processing method to solve the above-mentioned problems in the background art.
为实现上述目的,本发明提供如下技术方案:To achieve the above object, the present invention provides the following technical solutions:
一种计算机图像处理方法,其处理方法包括以下步骤,A computer image processing method, the processing method comprising the following steps:
S1:图像信息获取,首先获取图像信息并将图像信号转换成适合输入计算机或数字设备的数字信号;S1: Image information acquisition, first acquire image information and convert the image signal into a digital signal suitable for input into a computer or digital device;
S2:图像信息存储,然后将获取的图像信息数字信号传输到计算机图像信息储存介质中;S2: image information storage, and then transmit the acquired image information digital signal to the computer image information storage medium;
S3:图像信息传送,再然后将图形信息通过图像信息传送单元传送至图形信息预处理单元中;S3: image information transmission, and then the graphics information is transmitted to the graphics information preprocessing unit through the image information transmission unit;
S4:图像信息预处理,对获取的图像信息进行缺陷检测修正、锐化处理、平滑度处理、光圈修正、去噪滤波和对比度增强处理;S4: image information preprocessing, performing defect detection and correction, sharpening processing, smoothness processing, aperture correction, denoising filtering and contrast enhancement processing on the acquired image information;
S5:图像信息处理,对预处理后的图像信息依次进行几何处理、算术处理、图像增强、图像编码、图像识别和图像理解处理;S5: image information processing, which sequentially performs geometric processing, arithmetic processing, image enhancement, image coding, image recognition and image understanding processing on the preprocessed image information;
S6:图像信息输出,通过硬拷贝或软拷贝的方式将处理后的图像信息输出到存储器中;S6: image information output, the processed image information is output to the memory by means of hard copy or soft copy;
S7:图像信息显示,最后再将输出的图像信息通过计算机显示屏显示出来。S7: Image information display, and finally display the output image information through the computer display screen.
作为本发明进一步的方案:所述图像信息获取设备有电视摄像机、飞点扫描器、扫描鼓、扫描仪和显微光密度计。As a further solution of the present invention: the image information acquisition equipment includes a television camera, a flying spot scanner, a scanning drum, a scanner and a microscopic densitometer.
作为本发明再进一步的方案:所述图像信息存储设备包括磁带、磁盘或光盘,当使用磁带作为图像信息存储设备时,需要将计算机与数码摄像机连接,通过数码摄像机将图像信息保存在磁带中,当使用光盘作为图像信息存储设备时,需要将计算机与VCD、DVD以及其它可播放光盘的电器设备连接。As a further scheme of the present invention: the image information storage device includes a magnetic tape, a magnetic disk or an optical disc, when the magnetic tape is used as the image information storage device, the computer needs to be connected with the digital video camera, and the image information is stored in the magnetic tape by the digital video camera, When using an optical disc as an image information storage device, it is necessary to connect the computer with VCD, DVD and other electrical devices that can play optical discs.
作为本发明再进一步的方案:所述图像信息传送单元包括系统内部传送与远距离传送,系统内部传送采用电信号的方式传送,远距离传送采用互联网方式远程传送。As a further solution of the present invention: the image information transmission unit includes system internal transmission and long-distance transmission, the internal transmission of the system adopts electrical signal transmission, and the long-distance transmission adopts Internet remote transmission.
作为本发明再进一步的方案:所述缺陷检测修正是首先找出图像原始的缺陷数据,并制作缺陷原始图像训练集或者找出没有缺陷的原始图像,并制作无缺陷原始图像训练集,然后进行深度卷织神经网络训练,构建训练后的深度卷织神经网络模型对采集的图像进行缺陷识别,并进行缺陷特征提取,然后对其进行修正。As a further solution of the present invention: the defect detection and correction is to first find out the original defect data of the image, and make a training set of original images with defects or find original images without defects, and make a training set of original images without defects, and then carry out Deep convolutional neural network training, constructing a trained deep convolutional neural network model to identify defects in the collected images, extract defect features, and then correct them.
作为本发明再进一步的方案:所述几何处理主要包括坐标变换,图像的放大、缩小、旋转、移动,多个图像配准,全景畸变校正,扭曲校正,周长、面积和体积计算。As a further solution of the present invention: the geometric processing mainly includes coordinate transformation, image enlargement, reduction, rotation and movement, multiple image registration, panoramic distortion correction, distortion correction, perimeter, area and volume calculation.
作为本发明再进一步的方案:所述算术处理主要对图像施以加、减、乘、除等运算。As a further solution of the present invention: the arithmetic processing mainly applies operations such as addition, subtraction, multiplication, and division to the image.
作为本发明再进一步的方案:所述图像增强处理主要是突出图像中感兴趣的信息,而减弱或去除不需要的信息,从而使有用信息得到加强,便于区分或解释。As a further solution of the present invention: the image enhancement processing mainly highlights the information of interest in the image, and weakens or removes the unnecessary information, thereby enhancing the useful information and facilitating the distinction or interpretation.
作为本发明再进一步的方案:所述图像复原处理的主要目的是去除干扰和模糊,恢复图像的本来面目。As a further solution of the present invention: the main purpose of the image restoration processing is to remove interference and blur and restore the original appearance of the image.
与现有技术相比,本发明的有益效果是:Compared with the prior art, the beneficial effects of the present invention are:
本发明通过对获取的图像进行预处理操作,预处理包括缺陷检测修正、锐化处理、平滑度处理、光圈修正处理、去噪滤波处理和对比度增强处理,缺陷检测修正通过构建深度卷织神经网络模型对采集的图像进行缺陷识别,并进行缺陷特征提取,然后对其进行修正并与常规锐化处理、平滑度处理、光圈修正处理、去噪滤波处理和对比度增强处理配合,可以消除图像中无关的信息,恢复有用的真实信息,增强有关信息的可检测性和最大限度地简化数据,从而改进特征抽取、图像分割、匹配和识别的可靠性,提高图像的清晰度,使得图像显示质量更高,用户使用体验更好。The present invention performs preprocessing operations on the acquired images. The preprocessing includes defect detection and correction, sharpening processing, smoothness processing, aperture correction processing, denoising filtering processing and contrast enhancement processing. The model identifies defects in the collected images, extracts defect features, then corrects them and cooperates with conventional sharpening, smoothness, aperture correction, denoising filtering and contrast enhancement to eliminate irrelevant features in the image. information, recover useful real information, enhance the detectability of relevant information and simplify the data to the greatest extent, thereby improving the reliability of feature extraction, image segmentation, matching and recognition, improving the clarity of the image, and making the image display higher quality , the user experience is better.
具体实施方式Detailed ways
下面对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
本发明实施例中,一种计算机图像处理方法,其处理方法包括以下步骤,In an embodiment of the present invention, a computer image processing method includes the following steps:
S1:图像信息获取,首先获取图像信息并将图像信号转换成适合输入计算机或数字设备的数字信号;S1: Image information acquisition, first acquire image information and convert the image signal into a digital signal suitable for input into a computer or digital device;
S2:图像信息存储,然后将获取的图像信息数字信号传输到计算机图像信息储存介质中;S2: image information storage, and then transmit the acquired image information digital signal to the computer image information storage medium;
S3:图像信息传送,再然后将图形信息通过图像信息传送单元传送至图形信息预处理单元中;S3: image information transmission, and then the graphics information is transmitted to the graphics information preprocessing unit through the image information transmission unit;
S4:图像信息预处理,对获取的图像信息进行缺陷检测修正、锐化处理、平滑度处理、光圈修正、去噪滤波和对比度增强处理;S4: image information preprocessing, performing defect detection and correction, sharpening processing, smoothness processing, aperture correction, denoising filtering and contrast enhancement processing on the acquired image information;
S5:图像信息处理,对预处理后的图像信息依次进行几何处理、算术处理、图像增强、图像编码、图像识别和图像理解处理;S5: image information processing, which sequentially performs geometric processing, arithmetic processing, image enhancement, image coding, image recognition and image understanding processing on the preprocessed image information;
S6:图像信息输出,通过硬拷贝或软拷贝的方式将处理后的图像信息输出到存储器中;S6: image information output, the processed image information is output to the memory by means of hard copy or soft copy;
S7:图像信息显示,最后再将输出的图像信息通过计算机显示屏显示出来。S7: Image information display, and finally display the output image information through the computer display screen.
图像信息获取设备有电视摄像机、飞点扫描器、扫描鼓、扫描仪和显微光密度计。Image information acquisition equipment includes television cameras, flying spot scanners, scanning drums, scanners and micro-densitometers.
图像信息存储设备包括磁带、磁盘或光盘,当使用磁带作为图像信息存储设备时,需要将计算机与数码摄像机连接,通过数码摄像机将图像信息保存在磁带中,当使用光盘作为图像信息存储设备时,需要将计算机与VCD、DVD以及其它可播放光盘的电器设备连接。Image information storage devices include magnetic tapes, magnetic disks or optical discs. When using magnetic tapes as image information storage devices, it is necessary to connect a computer to a digital video camera, and store image information in the magnetic tape through the digital video cameras. When using optical discs as image information storage devices, It is necessary to connect the computer with VCD, DVD and other electrical devices that can play optical discs.
图像信息传送单元包括系统内部传送与远距离传送,系统内部传送采用电信号的方式传送,远距离传送采用互联网方式远程传送。The image information transmission unit includes the internal transmission of the system and the long-distance transmission. The internal transmission of the system adopts the mode of electrical signal transmission, and the long-distance transmission adopts the remote transmission of the Internet.
缺陷检测修正是首先找出图像原始的缺陷数据,并制作缺陷原始图像训练集或者找出没有缺陷的原始图像,并制作无缺陷原始图像训练集,然后进行深度卷织神经网络训练,构建训练后的深度卷织神经网络模型对采集的图像进行缺陷识别,并进行缺陷特征提取,然后对其进行修正。Defect detection and correction is to first find out the original defect data of the image, and create a training set of defective original images or find original images without defects, and create a training set of non-defective original images, and then perform deep convolutional neural network training. The deep convolutional neural network model is used to identify defects in the collected images, extract defect features, and then correct them.
几何处理主要包括坐标变换,图像的放大、缩小、旋转、移动,多个图像配准,全景畸变校正,扭曲校正,周长、面积和体积计算。Geometric processing mainly includes coordinate transformation, image enlargement, reduction, rotation, movement, multiple image registration, panoramic distortion correction, distortion correction, perimeter, area and volume calculation.
算术处理主要对图像施以加、减、乘、除等运算。Arithmetic processing mainly applies operations such as addition, subtraction, multiplication, and division to images.
图像增强处理主要是突出图像中感兴趣的信息,而减弱或去除不需要的信息,从而使有用信息得到加强,便于区分或解释。Image enhancement processing is mainly to highlight the information of interest in the image, and weaken or remove the unwanted information, so that the useful information can be enhanced, which is easy to distinguish or explain.
图像复原处理的主要目的是去除干扰和模糊,恢复图像的本来面目。The main purpose of image restoration processing is to remove interference and blur and restore the original appearance of the image.
图像去噪滤波采用自适应加权均值滤波模块,该模块通过检测滤波窗口内不同方向的方差来确定纹理方向,从而自动生成相应的加权系数,可以对宽度不超过4094像素的图像进行流水线式的加权均值滤波处理,达到去噪保边的目的。The image denoising filter adopts an adaptive weighted mean filter module, which determines the texture direction by detecting the variance in different directions in the filter window, thereby automatically generating the corresponding weighting coefficients, which can perform pipeline weighting on images with a width of no more than 4094 pixels. Mean filter processing to achieve the purpose of denoising and edge preservation.
尽管参照前述实施例对本发明进行了详细的说明,对于本领域的技术人员来说,其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换,凡在本发明的精神和原则之内,所做的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the foregoing embodiments, or to perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210811726.8A CN115049636A (en) | 2022-07-12 | 2022-07-12 | Computer image processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210811726.8A CN115049636A (en) | 2022-07-12 | 2022-07-12 | Computer image processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115049636A true CN115049636A (en) | 2022-09-13 |
Family
ID=83165479
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210811726.8A Pending CN115049636A (en) | 2022-07-12 | 2022-07-12 | Computer image processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115049636A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1753506A (en) * | 2005-10-07 | 2006-03-29 | 南京大学 | Implementation method of real-time enhanced preprocessing of CMOS image |
CN101945196A (en) * | 2009-07-01 | 2011-01-12 | 夏普株式会社 | Image processing apparatus and image processing system |
CN106165390A (en) * | 2014-03-28 | 2016-11-23 | 富士胶片株式会社 | Image processing device, photographing device, image processing method and program |
CN106488117A (en) * | 2015-08-27 | 2017-03-08 | 安讯士有限公司 | The preprocess method of digital picture and digital Image semantic classification system |
CN106875353A (en) * | 2017-01-20 | 2017-06-20 | 飞依诺科技(苏州)有限公司 | The processing method and processing system of ultrasonoscopy |
CN108629744A (en) * | 2018-04-09 | 2018-10-09 | 北京无线电计量测试研究所 | A kind of image enchancing method |
CN110400267A (en) * | 2019-07-03 | 2019-11-01 | 安徽继远软件有限公司 | A Preprocessing Method Based on Inspection Image |
CN111696039A (en) * | 2020-05-28 | 2020-09-22 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
CN112906689A (en) * | 2021-01-21 | 2021-06-04 | 南京航空航天大学 | Image detection method based on defect detection and segmentation depth convolution neural network |
CN114638819A (en) * | 2022-03-29 | 2022-06-17 | 燕山大学 | Defect detection method of 3D printing lattice structure CT image based on deep learning |
-
2022
- 2022-07-12 CN CN202210811726.8A patent/CN115049636A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1753506A (en) * | 2005-10-07 | 2006-03-29 | 南京大学 | Implementation method of real-time enhanced preprocessing of CMOS image |
CN101945196A (en) * | 2009-07-01 | 2011-01-12 | 夏普株式会社 | Image processing apparatus and image processing system |
CN106165390A (en) * | 2014-03-28 | 2016-11-23 | 富士胶片株式会社 | Image processing device, photographing device, image processing method and program |
CN106488117A (en) * | 2015-08-27 | 2017-03-08 | 安讯士有限公司 | The preprocess method of digital picture and digital Image semantic classification system |
CN106875353A (en) * | 2017-01-20 | 2017-06-20 | 飞依诺科技(苏州)有限公司 | The processing method and processing system of ultrasonoscopy |
CN108629744A (en) * | 2018-04-09 | 2018-10-09 | 北京无线电计量测试研究所 | A kind of image enchancing method |
CN110400267A (en) * | 2019-07-03 | 2019-11-01 | 安徽继远软件有限公司 | A Preprocessing Method Based on Inspection Image |
CN111696039A (en) * | 2020-05-28 | 2020-09-22 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
CN112906689A (en) * | 2021-01-21 | 2021-06-04 | 南京航空航天大学 | Image detection method based on defect detection and segmentation depth convolution neural network |
CN114638819A (en) * | 2022-03-29 | 2022-06-17 | 燕山大学 | Defect detection method of 3D printing lattice structure CT image based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111209952A (en) | Underwater target detection method based on improved SSD and transfer learning | |
CN112085728B (en) | Submarine pipeline and leakage point detection method | |
CN110097522B (en) | Single outdoor image defogging method based on multi-scale convolution neural network | |
CN113034401B (en) | Video denoising method and device, storage medium and electronic device | |
CN109509163B (en) | A method and system for multi-focus image fusion based on FGF | |
Liu et al. | Pd-gan: Perceptual-details gan for extremely noisy low light image enhancement | |
Guo et al. | Joint raindrop and haze removal from a single image | |
Thiruvikraman et al. | A survey on haze removal techniques in satellite images | |
Wang et al. | Single-image dehazing using color attenuation prior based on haze-lines | |
CN108416756B (en) | A region-aware image denoising method based on machine learning | |
CN113592738A (en) | Underwater distorted image restoration method | |
CN114693548B (en) | Dark channel defogging method based on bright area detection | |
CN116228550A (en) | Image self-enhancement defogging algorithm based on generation of countermeasure network | |
CN111275642A (en) | Low-illumination image enhancement method based on significant foreground content | |
CN108257105B (en) | A joint learning deep network model for optical flow estimation and denoising for video images | |
CN112927151B (en) | Image denoising method based on edge enhancement and convolutional neural network | |
Yang et al. | Learning to see low-light images via feature domain adaptation | |
CN115049636A (en) | Computer image processing method | |
CN115222606A (en) | Image processing method, image processing device, computer readable medium and electronic equipment | |
Huang et al. | Single image dehazing via color balancing and quad-decomposition atmospheric light estimation | |
CN117788325A (en) | Transformer-based Laplacian Pyramid Augmentation Network for Dark Object Detection | |
CN117788297A (en) | A method of depth image enhancement based on super-resolution | |
Siddiqua et al. | MCCGAN: an all-in-one image restoration under adverse conditions using multidomain contextual conditional gan | |
Wang et al. | Underwater image enhancement and restoration techniques: A comprehensive review, challenges, and future trends | |
Chavan et al. | Various approaches for video inpainting: A survey |
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 |