CN110222763B - Histogram matching method, mobile terminal and computer storage medium - Google Patents
Histogram matching method, mobile terminal and computer storage medium Download PDFInfo
- Publication number
- CN110222763B CN110222763B CN201910483396.2A CN201910483396A CN110222763B CN 110222763 B CN110222763 B CN 110222763B CN 201910483396 A CN201910483396 A CN 201910483396A CN 110222763 B CN110222763 B CN 110222763B
- Authority
- CN
- China
- Prior art keywords
- histogram
- pixel values
- probability
- matching method
- similarity
- 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.)
- Active
Links
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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a histogram matching method, a mobile terminal and a computer storage medium, wherein the histogram matching method comprises the following steps: acquiring a first histogram and a second histogram, wherein the histograms include a plurality of pixel values and probability values corresponding to the pixel values; sorting the plurality of pixel values based on the probability values of the first histogram to obtain a corresponding third histogram; sorting the plurality of pixel values based on the probability values of the second histogram to obtain a corresponding fourth histogram; and calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and a preset rule. By the histogram matching method, the two histograms can be matched quickly, and the illumination robustness and the accuracy are high.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a histogram matching method, a mobile terminal, and a computer storage medium.
Background
The problem of similarity measurement is encountered in the problems of target tracking and identification in the intelligent monitoring system. In the target tracking process, the similarity degree of the extracted target between two frames of images needs to be compared, and then inter-frame target identity judgment is carried out, so that inter-frame target association is realized. The image feature-based target identification problem is more directly applied to similarity measurement, and target classification is realized by judging and extracting the similarity between a target and a template.
In the target tracking and target identification process based on images and videos, when histogram matching is carried out, similarity measure calculation is directly applied to histograms needing to be compared, and similarity judgment of targets is achieved. However, the current histogram application similarity measure calculation methods have various problems, for example, the histogram may be shifted by a certain amount due to the influence of light, the similarity of the histogram becomes very low, and the histogram does not accord with human cognition, thereby influencing the histogram matching result.
Disclosure of Invention
In order to solve the above problems, the present application provides a histogram matching method, a mobile terminal, and a computer storage medium, which can solve the problem that the histogram matching method in the prior art is inaccurate.
The technical scheme adopted by the application is as follows: there is provided a histogram matching method, including: acquiring a first histogram and a second histogram, wherein the histograms include a plurality of pixel values and probability values corresponding to the pixel values; sorting the plurality of pixel values based on the probability values of the first histogram to obtain a corresponding third histogram; sorting the plurality of pixel values based on the probability values of the second histogram to obtain a corresponding fourth histogram; and calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and preset rules.
Another technical scheme adopted by the application is as follows: there is provided a mobile terminal, comprising: the device comprises an acquisition module, a calculation module and a processing module, wherein the acquisition module is used for acquiring a first histogram and a second histogram, and the histograms comprise a plurality of pixel values and probability values corresponding to the pixel values; a processing module, configured to rank the plurality of pixel values based on the probability value of the first histogram to obtain a corresponding third histogram; the histogram module is further configured to order a plurality of the pixel values based on the probability value magnitudes of the second histogram to obtain a corresponding fourth histogram; and the similarity calculation module is further used for calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and preset rules.
Another technical solution adopted by the present application is to provide a mobile terminal, where the terminal device includes a processor and a memory coupled to the processor; the memory is used for storing program data and the processor is used for executing the program data to realize the histogram matching method.
Another technical scheme adopted by the application is as follows: there is provided a computer storage medium having stored therein program data for implementing the histogram matching method as described above when executed by a processor.
The histogram matching method provided by the application comprises the following steps: acquiring a first histogram and a second histogram, wherein the histograms include a plurality of pixel values and probability values corresponding to the pixel values; sorting the plurality of pixel values based on the probability values of the first histogram to obtain a corresponding third histogram; sorting the plurality of pixel values based on the probability values of the second histogram to obtain a corresponding fourth histogram; and calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and a preset rule. The histogram matching method sequences pixel values of a first histogram and a second histogram to generate a third histogram and a fourth histogram which correspond to each other; and calculating the similarity of the first histogram and the second histogram through the pixel values of the third histogram and the fourth histogram and the corresponding probability values, thereby avoiding the influence of illumination factors on histogram matching and further improving the accuracy of the histogram matching method.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a histogram matching method provided herein;
FIG. 2 is a schematic flow chart diagram illustrating another embodiment of a histogram matching method provided in the present application;
FIG. 3 is a schematic structural diagram of an embodiment of a mobile terminal provided in the present application;
fig. 4 is a schematic structural diagram of another embodiment of a mobile terminal provided in the present application;
FIG. 5 is a schematic structural diagram of an embodiment of a computer storage medium provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first", "second", etc. in this application are used to distinguish between different objects and not to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In the histogram statistical process, a certain deviation occurs for the same target in different frame images. For example, the shadow part in one frame of image is at the edge of two subintervals in the histogram, and in the histogram of the frame of image, the statistics is the ith subinterval; in another frame of image, due to the imaging sensor or the change of ambient light, the shadow part pixels are counted as the (i-1) th subinterval, which causes the difference of the two histograms in morphology, and causes difficulty for matching as a target in the comparison process, and this phenomenon is called histogram boundary effect.
To reduce the influence of illumination on histogram matching accuracy, the present application provides a histogram matching method, and specifically refer to fig. 1, where fig. 1 is a schematic flowchart of an embodiment of the histogram matching method provided in the present application.
The histogram matching method of fig. 1 is applied to a terminal device with a processing function, where the terminal device may be a video monitor, a PC computer, or the like, and may also be a mobile terminal such as a smart phone, a notebook, a tablet computer, or the like. The mobile terminal can acquire the related data of the monitoring video through wireless transmission or wired transmission and the like, and execute the histogram matching method through the processing module.
The histogram matching method of the present embodiment specifically includes the following steps:
s101: the method comprises the steps of obtaining a first histogram and a second histogram, wherein the histograms comprise a plurality of pixel values and probability values corresponding to the pixel values.
The mobile terminal acquires two frames of images or video frames to be compared, and performs image preprocessing on the two acquired frames of images respectively to acquire a first histogram and a second histogram corresponding to the two frames of images respectively.
The histogram can effectively represent the statistical relationship of the occurrence frequency of each gray level in the digital image, and meanwhile, the histogram can give the general description of the gray level range of the image, the frequency and the distribution of the gray level of each gray level, the average brightness and the contrast of the whole image and the like. In the embodiment, the histogram corresponding to the image includes pixel values of the image and a probability value of occurrence of each pixel value, wherein the range of the pixel values of the image is 0 to 255.
Further, since a plurality of pixel values are included in one frame image, frequency value distribution in the histogram is more dispersed; if the image is illuminated, the histogram changes greatly, which may result in inaccurate histogram matching results. Therefore, the mobile terminal can also quantize the pixel values of the first histogram and the second histogram to a preset number of groups, and recalculate the probability value corresponding to each group of pixel values.
For example, two histograms whose similarity is to be calculated are histogram a and histogram b, and the pixel value group of histogram a is a1,a2...anThe pixel value groups of the histogram b are b1,b2...bn. Where n is a quantization level in the histogram a and the histogram b, that is, the preset number of groups is n, and specifically, the mobile terminal may set the preset number of groups to 16 groups or 32 groups.
S102: the plurality of pixel values are ordered based on the probability values of the first histogram to obtain a corresponding third histogram.
And the mobile terminal sorts the first histogram from large to small according to the plurality of probability values to obtain a new third histogram.
S103: the plurality of pixel values are ordered based on the probability values of the second histogram to obtain a corresponding fourth histogram.
And the mobile terminal sorts the second histogram from large to small according to the plurality of probability values to obtain a new fourth histogram.
Further, if the mobile terminal does not perform the quantization process on the first histogram and the second histogram in S101 described above, the mobile terminal may further perform the quantization process on the third histogram and the fourth histogram in S102 and S103. The specific operation of the quantization process is the same as the operation of S101, and is not described herein again.
S104: and calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and a preset rule.
The mobile terminal calculates the pixel values and the corresponding probability values of the third histogram and the fourth histogram according to a preset rule, so that the similarity between the third histogram and the fourth histogram is obtained, and the similarity is used as the similarity between the first histogram and the second histogram. In the whole histogram matching process, the mobile terminal does not need to directly calculate the first histogram and the second histogram, but calculates the similarity of the first histogram and the second histogram by using the information of the third histogram and the fourth histogram; because the third histogram and the fourth histogram are respectively obtained by the first histogram and the second histogram through probability value sequencing, the influence of illumination on the information presentation of the histograms can be reduced, and the accuracy of the histogram matching process is improved.
In this embodiment, the mobile terminal sorts the pixel values of the first histogram and the second histogram to generate a third histogram and a fourth histogram corresponding to the first histogram and the second histogram; and calculating the similarity of the first histogram and the second histogram through the pixel values of the third histogram and the fourth histogram and the corresponding probability values, thereby avoiding the influence of illumination factors on histogram matching and further improving the accuracy of the histogram matching method.
For S104 in the embodiment shown in fig. 1, another specific method is further proposed by the present application. Referring to fig. 2 in detail, fig. 2 is a schematic flowchart illustrating another embodiment of a histogram matching method according to the present application.
Specifically, the histogram matching method of the present embodiment specifically includes the following steps:
s201: and respectively taking the pixel value of the third histogram and the pixel value of the fourth histogram as weights, calculating weighted probability values corresponding to the pixel values of the third histogram and the fourth histogram, and calculating a difference value between the weighted probability values corresponding to the pixel values in the same order of the third histogram and the fourth histogram.
And the mobile terminal takes the pixel value of the third histogram as the weight of the corresponding probability value, takes the pixel value of the fourth histogram as the weight of the corresponding probability value, and calculates the difference value of each weighted probability value in the third histogram and each weighted probability value in the fourth histogram.
For example, the third histogram and the fourth histogram, which are to be calculated for the similarity, are histogram a 'and histogram b', respectively. The pixel value groups of the histogram a 'are each a'1,a'2...a'nEach pixel value group corresponding to a probability value of
The pixel value groups of the histogram b 'are b'1,b'2...b'nEach pixel value group corresponding to a probability value of
The difference between the weighted probability values in the third histogram and the weighted probability values in the fourth histogram is
S202: and calculating the square sum of weighted probability values corresponding to a plurality of pixel values of the third histogram, and carrying out root number taking operation on the square sum to obtain a first histogram parameter.
And the mobile terminal calculates the square sum of weighted probability values corresponding to a plurality of pixel values of the third histogram, and performs root operation on the square sum to obtain a first histogram parameter. Specifically, the first histogram parameter is
S203: and calculating the square sum of weighted probability values corresponding to a plurality of pixel values of the fourth histogram, and carrying out root number operation on the square sum to obtain a second histogram parameter.
And the mobile terminal calculates the square sum of weighted probability values corresponding to a plurality of pixel values of the fourth histogram, and performs root operation on the square sum to obtain a second histogram parameter. Specifically, the second histogram parameter is
Further, the histogram matching method of this embodiment further provides a specific calculation formula of cosine similarity of the third histogram and the fourth histogram:
wherein p is the cosine similarity of the third histogram and the fourth histogram,
is the pixel value of the third histogram, a'iThe probability values corresponding to the pixel values of the third histogram,
is the pixel value of the fourth histogram, b'iThe probability value corresponding to the pixel value of the fourth histogram.
Further, the calculation method of the similarity between the third histogram and the fourth histogram in the above embodiment is not limited to the above method, and other distance calculation methods such as the euclidean distance algorithm and the minkowski distance algorithm may be used to calculate the similarity between the third histogram and the fourth histogram.
Specifically, the calculation formula of the euclidean distance algorithm is as follows:
the calculation formula for the minkowski distance algorithm is:
wherein, the above
Is the pixel value of the third histogram, a'iThe probability values corresponding to the pixel values of the third histogram,
is the pixel value of the fourth histogram, b'iThe probability value corresponding to the pixel value of the fourth histogram.
To implement the histogram matching method of the foregoing embodiment, the present application further provides a mobile terminal, and specifically refer to fig. 3, where fig. 3 is a schematic structural diagram of an embodiment of the mobile terminal provided in the present application.
The mobile terminal 300 comprises an acquisition module 31 and a processing module 32, wherein the acquisition module 31 is coupled with the processing module 32.
The obtaining module 31 is configured to obtain a first histogram and a second histogram, where the histograms include a plurality of pixel values and probability values corresponding to each pixel value.
The processing module is used for sequencing the pixel values based on the probability value of the first histogram to obtain a corresponding third histogram; the histogram sorter is further configured to sort the plurality of pixel values based on the probability value of the second histogram to obtain a corresponding fourth histogram; and the similarity calculation module is also used for calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and preset rules.
To implement the histogram matching method of the foregoing embodiment, the present application further provides another mobile terminal, and specifically refer to fig. 4, where fig. 4 is a schematic structural diagram of another embodiment of the mobile terminal provided in the present application.
The mobile terminal 400 comprises a memory 41 and a processor 42, wherein the memory 41 is coupled to the processor 42.
The memory 41 is used for storing program data and the processor 42 is used for executing the program data to implement the histogram matching method of the above-described embodiment.
In the present embodiment, the processor 42 may also be referred to as a CPU (Central Processing Unit). The processor 42 may be an integrated circuit chip having signal processing capabilities. The processor 42 may also be a 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. A general purpose processor may be a microprocessor or the processor 42 may be any conventional processor or the like.
Please refer to fig. 5, wherein fig. 5 is a schematic structural diagram of an embodiment of the computer storage medium provided in the present application, the computer storage medium 50 stores program data 51, and the program data 51 is used to implement the histogram matching method of the above embodiment when being executed by a processor.
Embodiments of the present application may be implemented in software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (9)
1. A histogram matching method, characterized in that the histogram matching method comprises:
acquiring a first histogram and a second histogram, wherein the histograms include a plurality of pixel values and probability values corresponding to the pixel values;
sorting the plurality of pixel values based on the probability values of the first histogram to obtain a corresponding third histogram;
sorting the plurality of pixel values based on the probability values of the second histogram to obtain a corresponding fourth histogram;
calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and a preset rule;
wherein the step of calculating the similarity between the first histogram and the second histogram according to the third histogram and the fourth histogram and a preset rule further includes: respectively taking the pixel values of the third histogram and the fourth histogram as weights, and calculating weighted probability values corresponding to the pixel values of the third histogram and the fourth histogram; calculating a difference value between weighted probability values corresponding to pixel values in the same order of the third histogram and the fourth histogram; and obtaining the similarity between the third histogram and the fourth histogram according to the difference value so as to obtain the similarity between the first histogram and the second histogram.
2. The histogram matching method of claim 1, wherein said step of sorting a plurality of said pixel values based on said probability values of said second histogram to obtain a corresponding fourth histogram further comprises:
and quantizing a plurality of pixel values of the first histogram and the second histogram to preset groups, and calculating a probability value corresponding to each group of pixel values.
3. The histogram matching method of claim 1, wherein said step of sorting the plurality of pixel values based on the probability value magnitudes of the second histogram to obtain a corresponding fourth histogram further comprises:
and quantizing a plurality of pixel values of the third histogram and the fourth histogram to preset groups, and calculating a probability value corresponding to each group of pixel values.
4. The histogram matching method according to claim 2 or 3, wherein the preset number of groups is set to 16 groups or 32 groups.
5. The histogram matching method of claim 1, wherein the step of calculating the difference between the weighted probability values corresponding to the pixel values in the same order as the third histogram and the fourth histogram further comprises:
calculating the square sum of weighted probability values corresponding to a plurality of pixel values of the third histogram, and carrying out root number taking operation on the square sum to obtain a first histogram parameter;
and calculating the square sum of weighted probability values corresponding to a plurality of pixel values of the fourth histogram, and carrying out root number operation on the square sum to obtain a second histogram parameter.
6. The histogram matching method according to claim 5, wherein the preset rule includes a similarity calculation formula, the similarity calculation formula is:
wherein p is the cosine similarity of the third histogram and the fourth histogram,
is the pixel value of the third histogram, a'iA probability value corresponding to a pixel value of the third histogram,
is the pixel value, b 'of the fourth histogram'iAnd the probability value is corresponding to the pixel value of the fourth histogram.
7. A mobile terminal, characterized in that the mobile terminal comprises:
the device comprises an acquisition module, a calculation module and a processing module, wherein the acquisition module is used for acquiring a first histogram and a second histogram, and the histograms comprise a plurality of pixel values and probability values corresponding to the pixel values;
a processing module, configured to rank the plurality of pixel values based on the probability value of the first histogram to obtain a corresponding third histogram; the histogram module is further configured to order a plurality of the pixel values based on the probability value magnitudes of the second histogram to obtain a corresponding fourth histogram; the histogram calculation module is further used for calculating the similarity of the first histogram and the second histogram according to the third histogram and the fourth histogram and preset rules;
the processing module is further configured to calculate weighted probability values corresponding to the pixel values of the third histogram and the fourth histogram by using the pixel values of the third histogram and the pixel values of the fourth histogram as weights; calculating a difference value between weighted probability values corresponding to pixel values in the same order of the third histogram and the fourth histogram; and obtaining the similarity between the third histogram and the fourth histogram according to the difference value so as to obtain the similarity between the first histogram and the second histogram.
8. A mobile terminal, characterized in that the terminal device comprises a processor and a memory coupled to the processor; the memory is used for storing program data, and the processor is used for executing the program data to realize the histogram matching method of any one of claims 1 to 6.
9. A computer storage medium having stored therein program data for implementing the histogram matching method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910483396.2A CN110222763B (en) | 2019-06-04 | 2019-06-04 | Histogram matching method, mobile terminal and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910483396.2A CN110222763B (en) | 2019-06-04 | 2019-06-04 | Histogram matching method, mobile terminal and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222763A CN110222763A (en) | 2019-09-10 |
| CN110222763B true CN110222763B (en) | 2021-08-03 |
Family
ID=67819727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910483396.2A Active CN110222763B (en) | 2019-06-04 | 2019-06-04 | Histogram matching method, mobile terminal and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222763B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008269471A (en) * | 2007-04-24 | 2008-11-06 | Sony Corp | Similar image decision device, similar image decision method, program, and recording medium |
| CN101404086B (en) * | 2008-04-30 | 2012-05-09 | 浙江大学 | Target tracking method and device based on video |
| CN108846319A (en) * | 2018-05-25 | 2018-11-20 | 平安科技（深圳）有限公司 | Iris image Enhancement Method, device, equipment and storage medium based on histogram |
| CN108805214B (en) * | 2018-06-19 | 2021-07-23 | 太原学院 | Similar image matching method and system based on fuzzy weighted histogram |
-
2019
- 2019-06-04 CN CN201910483396.2A patent/CN110222763B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222763A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108337551B (en) | Screen recording method, storage medium and terminal equipment | |
| KR101912748B1 (en) | Scalable Feature Descriptor Extraction and Matching method and system | |
| CN103295022A (en) | Image similarity calculation system and method | |
| CN103870828A (en) | System and method for judging image similarity degree | |
| CN103353881B (en) | Method and device for searching application | |
| CN109447023B (en) | Method for determining image similarity, and method and device for identifying video scene switching | |
| CN108230412B (en) | Infrared image compression method and device | |
| Xie et al. | Bag-of-words feature representation for blind image quality assessment with local quantized pattern | |
| CN111783805A (en) | Image retrieval method and device, electronic equipment and readable storage medium | |
| CN111199186A (en) | Image quality scoring model training method, device, equipment and storage medium | |
| CN111815668A (en) | Target tracking method, electronic device and storage medium | |
| CN108197638B (en) | Method and device for classifying sample to be evaluated | |
| US9286217B2 (en) | Systems and methods for memory utilization for object detection | |
| US20150139551A1 (en) | Cascaded Object Detection | |
| CN117496560B (en) | Fingerprint line identification method and device based on multidimensional vector | |
| CN111062927A (en) | Method, system and equipment for detecting image quality of unmanned aerial vehicle | |
| Vu et al. | Main subject detection via adaptive feature refinement | |
| CN112070682A (en) | Method and device for compensating image brightness | |
| CN112307934B (en) | Image detection method, and training method, device, equipment and medium of related model | |
| CN110222763B (en) | Histogram matching method, mobile terminal and computer storage medium | |
| CN107423739B (en) | Image feature extraction method and device | |
| CN115690747B (en) | Vehicle blind area detection model test method and device, electronic equipment and storage medium | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| TWI689893B (en) | Method of background model update and related device | |
| CN112214639A (en) | Video screening method, video screening device and terminal equipment |
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 |