CN112308091A - Method and equipment for extracting features of multi-focus sequence image - Google Patents
Method and equipment for extracting features of multi-focus sequence image Download PDFInfo
- Publication number
- CN112308091A CN112308091A CN202011166546.6A CN202011166546A CN112308091A CN 112308091 A CN112308091 A CN 112308091A CN 202011166546 A CN202011166546 A CN 202011166546A CN 112308091 A CN112308091 A CN 112308091A
- Authority
- CN
- China
- Prior art keywords
- image
- extracting
- focus
- focus sequence
- feature extraction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 59
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 16
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
A method and a device for extracting characteristics of a multi-focus sequence image are provided, wherein the extraction method comprises the following steps: firstly, extracting image characteristics of a clear region of a multi-focus sequence image; step two, mapping the image features extracted in the step one to corresponding areas of other images; and step three, combining the image features extracted in the step one and the image features mapped in the step two to finish the extraction of the image features. The invention also provides a multi-focus sequence image feature extraction system, terminal equipment and a computer readable storage medium. The method not only obtains good characteristic extraction effect in the focus clear area, but also obtains good characteristic extraction effect in the defocus fuzzy area. The invention has simple operation, easy realization and outstanding practical value.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a method and equipment for extracting characteristics of a multi-focus sequence image.
Background
The multi-focus sequence image comprises a focus clear area and an out-of-focus fuzzy area, the conventional image feature extraction method has good effect in the focus clear area, the number of extracted features is large, but the effect in the out-of-focus fuzzy area is poor, and the number of extracted features is deficient or even missing. Due to the lack of sufficient characteristics of the out-of-focus fuzzy area, good effect of multi-focus sequence image registration is difficult to achieve.
Disclosure of Invention
The invention aims to provide a method and equipment for extracting characteristics of a multi-focus sequence image, aiming at the problems that the effect in a clear area is good but the effect in a fuzzy area is poor when the characteristics of the multi-focus sequence image are extracted in the prior art, so that the method and the equipment can have good characteristic extraction effects in a focus clear area and a defocus fuzzy area, and the characteristics of the whole image are extracted by combining the characteristics.
In order to achieve the purpose, the invention has the following technical scheme:
a method for extracting characteristics of a multi-focus sequence image comprises the following steps:
firstly, extracting image characteristics of a clear region of a multi-focus sequence image;
step two, mapping the image features extracted in the step one to corresponding areas of other images;
and step three, combining the image features extracted in the step one and the image features mapped in the step two to finish the extraction of the image features.
As a preferred scheme, in the first step, the image features of the clear regions of the multi-focus sequence image are extracted by using a conventional feature extraction method, and the conventional feature extraction method includes a Harris corner detection method, a Shi-Tomas corner extraction method, a FAST feature point detection method, an ORB feature extraction method, and a SIFT feature extraction method.
Preferably, in the second step, the image features extracted in the first step are mapped to corresponding areas of other images through optical flow tracking.
The invention also provides a system for extracting the characteristics of the multi-focus sequence image, which comprises the following steps:
the focusing clear region extraction module is used for extracting the image characteristics of the multi-focusing sequence image clear region;
the image characteristic mapping module is used for mapping the image characteristics extracted by the focusing clear region extraction module to corresponding regions of other images;
and the image feature merging module is used for merging the image features extracted by the focusing clear region extraction module and the image features mapped by the image feature mapping module to finish the image feature extraction.
The invention also provides a terminal device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of the feature extraction method of the multi-focus sequence image when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for feature extraction of multiple focus sequence images.
Compared with the prior art, the invention has the following beneficial effects: the method comprises the steps of extracting the characteristics of a clear area of a multi-focus sequence image by adopting a conventional image characteristic extraction method, mapping the extracted image characteristics to corresponding areas of other images, obtaining the image characteristics of an out-of-focus fuzzy area through mapping, and combining the extracted image characteristics and the mapped image characteristics to realize the extraction of the characteristics of the whole image. The method not only obtains good characteristic extraction effect in the focus clear area, but also obtains good characteristic extraction effect in the defocus fuzzy area. The invention has simple operation, easy realization and outstanding practical value.
Drawings
FIG. 1 is an exemplary diagram of the effect of a conventional image feature extraction method in near focus;
FIG. 2 is an exemplary diagram of the effect of the conventional image feature extraction method in far focus;
FIG. 3 is a diagram illustrating the effect of the image feature extraction method of the present invention in near focus;
FIG. 4 is a diagram illustrating an exemplary effect of the image feature extraction method of the present invention in far focus;
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The invention provides a method for extracting characteristics of a multi-focus sequence image, which comprises the following steps:
the method comprises the following steps of firstly, extracting image features of a clear region of a multi-focus sequence image by adopting a conventional image feature extraction method; the conventional image feature extraction method can be one or more of a conventional Harris corner detection method, a Shi-Tomas corner extraction method, a FAST feature point detection method, an ORB feature extraction method and a SIFT feature extraction method;
step two, mapping the image features extracted in the step one to corresponding areas of other images through optical flow tracking;
and step three, combining the image features extracted in the step one and the image features mapped in the step two to finish the extraction of the image features.
Fig. 1 and 2 are the results of feature extraction of two multi-focus images using a conventional Shi-Tomas corner extraction method. In the figure 1, the clear areas on the near books have more feature points, and the fuzzy areas of the distant buildings lack feature points; in fig. 2, the clear areas of the building at the far distance have more characteristic points, and the fuzzy areas on the near book lack characteristic points.
The conventional Shi-Tomas corner point extraction method has poor effect in the out-of-focus fuzzy area from the image characteristics.
Fig. 3 and 4 show feature points obtained by the feature extraction method of the present invention, and in order to ensure that the result is comparable to that of fig. 1 and 2, the conventional image feature extraction method adopted in the first step of the present invention is the same as that adopted in fig. 1 and 2, and is also the Shi-Tomas corner point extraction method. In fig. 3, there are many feature points in the clear area on the near book and the fuzzy area on the distant building, and in fig. 4, there are many feature points in the clear area on the distant building and the fuzzy area on the near book.
Compared with the prior art, the method has good characteristic extraction effect in both the focus clear area and the defocus fuzzy area.
The invention also provides a system for extracting the characteristics of the multi-focus sequence image, which comprises the following steps:
the focusing clear region extraction module is used for extracting the image characteristics of the multi-focusing sequence image clear region;
the image characteristic mapping module is used for mapping the image characteristics extracted by the focusing clear region extraction module to corresponding regions of other images;
and the image feature merging module is used for merging the image features extracted by the focusing clear region extraction module and the image features mapped by the image feature mapping module to finish the image feature extraction.
The invention also provides a terminal device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the feature extraction method of the multi-focus sequence image.
The present invention also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for feature extraction of multiple focus sequence images.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to perform the method of the invention.
The terminal device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices, and can also be a processor and a memory. The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of feature extraction for multiple focus sequence images by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory.
The above description is only one specific example of the present invention and should not be construed as limiting the invention in any way. It will be apparent to persons skilled in the art that various modifications and variations in form and detail can be made therein without departing from the spirit and principles of the invention, and these modifications and variations will fall within the scope of the invention as defined by the appended claims.
Claims (6)
1. A method for extracting characteristics of a multi-focus sequence image is characterized by comprising the following steps:
firstly, extracting image characteristics of a clear region of a multi-focus sequence image;
step two, mapping the image features extracted in the step one to corresponding areas of other images;
and step three, combining the image features extracted in the step one and the image features mapped in the step two to finish the extraction of the image features.
2. The method for extracting features of a multi-focus sequence image according to claim 1, wherein: the first step is to extract image features of clear areas of the multi-focus sequence image by using a conventional feature extraction method, wherein the conventional feature extraction method comprises a Harris corner detection method, a Shi-Tomas corner extraction method, a FAST feature point detection method, an ORB feature extraction method and a SIFT feature extraction method.
3. The method for extracting features of a multi-focus sequence image according to claim 1, wherein: and step two, mapping the image features extracted in step one to corresponding areas of other images through optical flow tracking.
4. A system for extracting features of multiple focus sequence images, comprising:
the focusing clear region extraction module is used for extracting the image characteristics of the multi-focusing sequence image clear region;
the image characteristic mapping module is used for mapping the image characteristics extracted by the focusing clear region extraction module to corresponding regions of other images;
and the image feature merging module is used for merging the image features extracted by the focusing clear region extraction module and the image features mapped by the image feature mapping module to finish the image feature extraction.
5. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: the processor, when executing the computer program, implements the steps of the method for feature extraction of multiple focus sequence images according to any one of claims 1 to 3.
6. A computer-readable storage medium storing a computer program, characterized in that: the computer program, when executed by a processor, implements the steps of the method for feature extraction of multiple focus sequence images as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011166546.6A CN112308091B (en) | 2020-10-27 | Feature extraction method and device for multi-focus sequence image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011166546.6A CN112308091B (en) | 2020-10-27 | Feature extraction method and device for multi-focus sequence image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112308091A true CN112308091A (en) | 2021-02-02 |
| CN112308091B CN112308091B (en) | 2024-04-26 |
Family
ID=
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182952A (en) * | 2014-08-19 | 2014-12-03 | 中国科学院西安光学精密机械研究所 | Multi-focus sequence image fusion method |
| US20150077325A1 (en) * | 2013-09-13 | 2015-03-19 | Ron Ferens | Motion data based focus strength metric to facilitate image processing |
| US20190014255A1 (en) * | 2014-06-27 | 2019-01-10 | Nubia Technology Co., Ltd. | Focusing state prompting method and shooting device |
| CN109829396A (en) * | 2019-01-16 | 2019-05-31 | 广州杰赛科技股份有限公司 | Recognition of face motion blur processing method, device, equipment and storage medium |
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150077325A1 (en) * | 2013-09-13 | 2015-03-19 | Ron Ferens | Motion data based focus strength metric to facilitate image processing |
| US20190014255A1 (en) * | 2014-06-27 | 2019-01-10 | Nubia Technology Co., Ltd. | Focusing state prompting method and shooting device |
| CN104182952A (en) * | 2014-08-19 | 2014-12-03 | 中国科学院西安光学精密机械研究所 | Multi-focus sequence image fusion method |
| CN109829396A (en) * | 2019-01-16 | 2019-05-31 | 广州杰赛科技股份有限公司 | Recognition of face motion blur processing method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 毕春艳;吴晓红;王正勇;何小海;程潇;: "Curvelet变换在多聚焦岩心图像融合中的应用", 计算机工程与应用, no. 16 * |
| 海洁;: "小波变换图像多聚焦模糊特征自动增强仿真", 计算机仿真, no. 11 * |
| 王宏, 敬忠良, 李建勋: "一种基于图像块分割的多聚焦图像融合方法", 上海交通大学学报, no. 11 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016119117A1 (en) | Localization and mapping method | |
| CN109766925B (en) | Feature fusion method and device, electronic equipment and storage medium | |
| CN111340077B (en) | Attention mechanism-based disparity map acquisition method and device | |
| US11354883B2 (en) | Image processing method and apparatus, and electronic device | |
| WO2022127912A1 (en) | Image segmentation method, network training method, electronic equipment and storage medium | |
| CN104036259A (en) | Face similarity recognition method and system | |
| CN112149583A (en) | Smoke detection method, terminal device and storage medium | |
| CN116452631A (en) | Multi-target tracking method, terminal equipment and storage medium | |
| CN110009664B (en) | Infrared target tracking method and device based on response map fusion | |
| KR102421604B1 (en) | Image processing methods, devices and electronic devices | |
| CN112308091B (en) | Feature extraction method and device for multi-focus sequence image | |
| CN110956131B (en) | Single-target tracking method, device and system | |
| CN114493988A (en) | Image blurring method, image blurring device and terminal equipment | |
| CN112308091A (en) | Method and equipment for extracting features of multi-focus sequence image | |
| CN112528978A (en) | Face key point detection method and device, electronic equipment and storage medium | |
| CN108780572A (en) | The method and device of image rectification | |
| CN110660091A (en) | Image registration processing method and device and photographing correction operation system | |
| CN114359932B (en) | Text detection method, text recognition method and device | |
| CN109816709B (en) | Monocular camera-based depth estimation method, device and equipment | |
| Singh et al. | An effective approach for noise robust and rotation invariant handwritten character recognition using zernike moments features and optimal similarity measure | |
| CN113469017A (en) | Image processing method and device and electronic equipment | |
| US11288776B2 (en) | Method and apparatus for image processing | |
| CN114119990A (en) | Method, apparatus and computer program product for image feature point matching | |
| CN112102404B (en) | Object detection tracking method and device and head-mounted display equipment | |
| CN110147462A (en) | The verification method and Related product of the short-sighted frequency of religion |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240318 Address after: 518000 1104, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province Applicant after: Shenzhen Hongyue Information Technology Co.,Ltd. Country or region after: China Address before: 710064 middle section, south two ring road, Shaanxi, Xi'an Applicant before: CHANG'AN University Country or region before: China |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20240328 Address after: 518000 A306, Building A, Huafeng International Robot Industry Park, Hangcheng Avenue, Nanchang Community, Xixiang Street, Bao'an District, Shenzhen, Guangdong Province Applicant after: Shenzhen Hello Times Network Co.,Ltd. Country or region after: China Address before: 518000 1104, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province Applicant before: Shenzhen Hongyue Information Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |