CN108596280A - Image identification method for literature search - Google Patents
Image identification method for literature search Download PDFInfo
- Publication number
- CN108596280A CN108596280A CN201810394638.6A CN201810394638A CN108596280A CN 108596280 A CN108596280 A CN 108596280A CN 201810394638 A CN201810394638 A CN 201810394638A CN 108596280 A CN108596280 A CN 108596280A
- Authority
- CN
- China
- Prior art keywords
- picture
- value
- information
- gray
- image identification
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of image identification methods for literature search, are related to field of information processing.In image identification method, the pictorial information of input is obtained first;Then the pictorial information of input and the pictorial information that prestores are subjected to similarity comparison, obtain similarity value;Secondly the pictorial information that similarity value is higher than predetermined threshold value is obtained;Finally it is ranked up by pictorial information of the sequence to similarity value higher than predetermined threshold value of similarity value from high in the end;According to sequence along number output result.Using the above method, whether containing similar picture result then can be sent to user terminal to determine whether two documents are associated by comparing in different documents, the document of needs is found to facilitate user to pass through picture, compensates for the deficiency by text search document.
Description
Technical field
The present invention relates to field of information processing, more particularly to a kind of image identification method for literature search.
Background technology
Literature search (Information Retrieval) refers to the mistake for needing to obtain document according to study and work
Journey.Modern age thinks that document refers to the article and books or important books and reference materials related with a certain subject for having historical value, with
The development of modern network technology, literature search is completed by computer technology.
In the prior art, associated documents are inquired not over the method for input picture.
Invention content
It is an object of the present invention to provide a kind of image identification method for literature search, to solve the prior art
In not over input picture carry out searching document the problem of.
Particularly, the present invention provides a kind of image identification methods for literature search, which is characterized in that including:
Obtain the pictorial information of input;
The pictorial information of the input and the pictorial information that prestores are subjected to similarity comparison, obtain similarity value;
Obtain the pictorial information that similarity value is higher than predetermined threshold value;
Pictorial information by the sequence of similarity value from high in the end to similarity value higher than predetermined threshold value is ranked up;
According to sequence along number output result.
Optionally, after being ranked up by similarity value, the pictorial information for obtaining similarity value higher than predetermined threshold value corresponds to
Field;
It is ranked up again according to the quantity of different field, and exports ranking results.
Optionally, the field includes machinery field, electricity field, chemical field and biological field.
Optionally, the method that the pictorial information of the input is compared with the prestored information includes:
The first picture and second picture compared is obtained respectively;
Text message, coding information and the histogram information of first picture are obtained respectively, and obtain the second figure respectively
Text message, coding information and the histogram information of piece;
Text message, coding information and the histogram information of first picture and the second picture are carried out pair respectively
Than obtaining comparing result.
Optionally, for first picture and the second picture, the mode for obtaining its text message includes:
Noise reduction process is carried out to picture;
By optical character recognition technology, the picture after noise reduction process is scanned, obtains text message therein.
Optionally, described to include to picture progress noise reduction process:
Picture is converted into gray-scale map from cromogram;
Binary conversion treatment is carried out to the gray-scale map being converted to;
Picture is carried out based on binary conversion treatment result to redraw, and obtains the picture after noise reduction process;Wherein, after noise reduction process
Picture is cromogram, and size is identical as the size of the picture before not carrying out noise reduction process.
Optionally, for first picture and the second picture, the mode for obtaining its coding information includes:
Picture is converted into gray-scale map from cromogram;
The gray-scale map being converted to is redrawn into the gray-scale map of predefined size;
Calculate the average value of the value of each pixel in the gray-scale map redrawn;
For each pixel in the gray-scale map redrawn, determines whether the value of the pixel is less than respectively and calculate
Average value otherwise, the value of the pixel is arranged if it is, set the value of the pixel to first predetermined value
For second predetermined value;
The value of set each pixel is cascaded according to predetermined order, the coding information as picture.
Optionally, for first picture and the second picture, the mode for obtaining its histogram information includes:
Picture is converted into gray-scale map from cromogram, and obtains the grey level histogram information for the gray-scale map being converted to;
Three primary colours separation is carried out to the picture before converting, and the three primary colours for getting according to separating resulting picture are straight
Square figure information.
The image identification method for literature search of the present invention, obtains the pictorial information of input first;It then will input
Pictorial information and prestore pictorial information carry out similarity comparison, obtain similarity value;Secondly similarity value is obtained higher than default
The pictorial information of threshold value;Finally press the sequence of similarity value from high in the end to similarity value higher than predetermined threshold value pictorial information into
Row sequence;According to sequence along number output result.It, can be by whether comparing in different documents containing similar using the above method
Then result is sent to user terminal by picture to determine whether two documents are associated, found with facilitating user to pass through picture
The document needed compensates for the deficiency by text search document.
According to the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will be brighter
The above and other objects, advantages and features of the present invention.
Description of the drawings
Some specific embodiments that the invention will be described in detail by way of example and not limitation with reference to the accompanying drawings hereinafter.
Identical reference numeral denotes same or similar component or part in attached drawing.It should be appreciated by those skilled in the art that these
What attached drawing was not necessarily drawn to scale.In attached drawing:
Fig. 1 is the schematic flow chart of image identification method according to an embodiment of the invention.
Specific implementation mode
Fig. 1 is the schematic flow chart of image identification method according to an embodiment of the invention.As shown in Figure 1, this hair
The bright image identification method for literature search, obtains the pictorial information of input first;Then by the pictorial information of input with
The pictorial information that prestores carries out similarity comparison, obtains similarity value;Secondly the picture for obtaining similarity value higher than predetermined threshold value is believed
Breath;Finally it is ranked up by pictorial information of the sequence to similarity value higher than predetermined threshold value of similarity value from high in the end;According to
Sequence is along number output result., can be by comparing in different documents whether contain similar picture, to determine using the above method
Whether two documents are associated, and result is then sent to user terminal, and the document of needs is found to facilitate user to pass through picture,
Compensate for the deficiency by text search document.
Further, after being ranked up by similarity value, the pictorial information pair that similarity value is higher than predetermined threshold value is obtained
The field answered;
It is ranked up again according to the quantity of different field, and exports ranking results.
Further, field includes machinery field, electricity field, chemical field and biological field.
Further, the method that the pictorial information with prestored information of input compare includes:
The first picture and second picture compared is obtained respectively;
Text message, coding information and the histogram information of the first picture are obtained respectively, and obtain second picture respectively
Text message, coding information and histogram information;
The text message of the first picture and second picture, coding information and histogram information are compared respectively, obtained
Comparing result.
Further, for the first picture and second picture, the mode for obtaining its text message includes:
Noise reduction process is carried out to picture;
By optical character recognition technology, the picture after noise reduction process is scanned, obtains text message therein.
Further, carrying out noise reduction process to picture includes:
Picture is converted into gray-scale map from cromogram;
Binary conversion treatment is carried out to the gray-scale map being converted to;
Picture is carried out based on binary conversion treatment result to redraw, and obtains the picture after noise reduction process;Wherein, after noise reduction process
Picture is cromogram, and size is identical as the size of the picture before not carrying out noise reduction process.
Further, for the first picture and second picture, the mode for obtaining its coding information includes:
Picture is converted into gray-scale map from cromogram;
The gray-scale map being converted to is redrawn into the gray-scale map of predefined size;
Calculate the average value of the value of each pixel in the gray-scale map redrawn;
For each pixel in the gray-scale map redrawn, determines whether the value of the pixel is less than respectively and calculate
Average value otherwise, the value of the pixel is arranged if it is, set the value of the pixel to first predetermined value
For second predetermined value;
The value of set each pixel is cascaded according to predetermined order, the coding information as picture.
Further, for the first picture and second picture, the mode for obtaining its histogram information includes:
Picture is converted into gray-scale map from cromogram, and obtains the grey level histogram information for the gray-scale map being converted to;
Three primary colours separation is carried out to the picture before converting, and the three primary colours for getting according to separating resulting picture are straight
Square figure information.
So far, although those skilled in the art will appreciate that present invention has been shown and described in detail herein multiple shows
Example property embodiment still without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (8)
1. a kind of image identification method for literature search, which is characterized in that including:
Obtain the pictorial information of input;
The pictorial information of the input and the pictorial information that prestores are subjected to similarity comparison, obtain similarity value;
Obtain the pictorial information that similarity value is higher than predetermined threshold value;
Pictorial information by the sequence of similarity value from high in the end to similarity value higher than predetermined threshold value is ranked up;
According to sequence along number output result.
2. image identification method according to claim 1, which is characterized in that
After being ranked up by similarity value, the corresponding field of pictorial information that similarity value is higher than predetermined threshold value is obtained;
It is ranked up again according to the quantity of different field, and exports ranking results.
3. image identification method according to claim 2, which is characterized in that
The field includes machinery field, electricity field, chemical field and biological field.
4. image identification method according to claim 3, which is characterized in that the pictorial information of the input prestores with described
Information comparison method include:
The first picture and second picture compared is obtained respectively;
Text message, coding information and the histogram information of first picture are obtained respectively, and obtain second picture respectively
Text message, coding information and histogram information;
Text message, coding information and the histogram information of first picture and the second picture are compared respectively,
Obtain comparing result.
5. image identification method according to claim 4, which is characterized in that be directed to first picture and second figure
Piece, the mode for obtaining its text message include:
Noise reduction process is carried out to picture;
By optical character recognition technology, the picture after noise reduction process is scanned, obtains text message therein.
6. image identification method according to claim 5, which is characterized in that described to include to picture progress noise reduction process:
Picture is converted into gray-scale map from cromogram;
Binary conversion treatment is carried out to the gray-scale map being converted to;
Picture is carried out based on binary conversion treatment result to redraw, and obtains the picture after noise reduction process;Wherein, the picture after noise reduction process
For cromogram, and size is identical as the size of the picture before not carrying out noise reduction process.
7. image identification method according to claim 4, which is characterized in that
For first picture and the second picture, the mode for obtaining its coding information includes:
Picture is converted into gray-scale map from cromogram;
The gray-scale map being converted to is redrawn into the gray-scale map of predefined size;
Calculate the average value of the value of each pixel in the gray-scale map redrawn;
For each pixel in the gray-scale map redrawn, it is calculated flat to determine whether the value of the pixel is less than respectively
Otherwise the value of the pixel, is set as by mean value if it is, setting the value of the pixel to first predetermined value
Two predetermined values;
The value of set each pixel is cascaded according to predetermined order, the coding information as picture.
8. image identification method according to claim 4, which is characterized in that
For first picture and the second picture, the mode for obtaining its histogram information includes:
Picture is converted into gray-scale map from cromogram, and obtains the grey level histogram information for the gray-scale map being converted to;
Three primary colours separation is carried out to the picture before converting, and gets the three primary colours histogram of picture according to separating resulting
Information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810394638.6A CN108596280A (en) | 2018-04-27 | 2018-04-27 | Image identification method for literature search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810394638.6A CN108596280A (en) | 2018-04-27 | 2018-04-27 | Image identification method for literature search |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108596280A true CN108596280A (en) | 2018-09-28 |
Family
ID=63610875
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810394638.6A Pending CN108596280A (en) | 2018-04-27 | 2018-04-27 | Image identification method for literature search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108596280A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112423016A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Optimization method and system for improving live broadcast audience rating of television station |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101777064A (en) * | 2009-01-12 | 2010-07-14 | 鸿富锦精密工业(深圳)有限公司 | Image searching system and method |
CN103136228A (en) * | 2011-11-25 | 2013-06-05 | 阿里巴巴集团控股有限公司 | Image search method and image search device |
CN105551044A (en) * | 2015-12-16 | 2016-05-04 | 北京京东尚科信息技术有限公司 | Picture comparing method and device |
CN105630915A (en) * | 2015-12-21 | 2016-06-01 | 山东大学 | Method and device for classifying and storing pictures in mobile terminals |
CN106445995A (en) * | 2016-07-18 | 2017-02-22 | 腾讯科技(深圳)有限公司 | Picture classification method and apparatus |
CN107577687A (en) * | 2016-07-20 | 2018-01-12 | 北京陌上花科技有限公司 | Image search method and device |
CN107807979A (en) * | 2017-10-27 | 2018-03-16 | 朱秋华 | The searching method and device of a kind of similar pictures |
-
2018
- 2018-04-27 CN CN201810394638.6A patent/CN108596280A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101777064A (en) * | 2009-01-12 | 2010-07-14 | 鸿富锦精密工业(深圳)有限公司 | Image searching system and method |
CN103136228A (en) * | 2011-11-25 | 2013-06-05 | 阿里巴巴集团控股有限公司 | Image search method and image search device |
CN105551044A (en) * | 2015-12-16 | 2016-05-04 | 北京京东尚科信息技术有限公司 | Picture comparing method and device |
CN105630915A (en) * | 2015-12-21 | 2016-06-01 | 山东大学 | Method and device for classifying and storing pictures in mobile terminals |
CN106445995A (en) * | 2016-07-18 | 2017-02-22 | 腾讯科技(深圳)有限公司 | Picture classification method and apparatus |
CN107577687A (en) * | 2016-07-20 | 2018-01-12 | 北京陌上花科技有限公司 | Image search method and device |
CN107807979A (en) * | 2017-10-27 | 2018-03-16 | 朱秋华 | The searching method and device of a kind of similar pictures |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112423016A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Optimization method and system for improving live broadcast audience rating of television station |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10108856B2 (en) | Data entry from series of images of a patterned document | |
CN109583438B (en) | The recognition methods of the text of electronic image and image processing apparatus | |
US20200134382A1 (en) | Neural network training utilizing specialized loss functions | |
EP2797031A3 (en) | Optical character recognition of text in an image according to a prioritized processing sequence | |
CN114862845B (en) | Defect detection method, device and equipment for mobile phone touch screen and storage medium | |
CN111898520A (en) | Certificate authenticity identification method and device, computer readable medium and electronic equipment | |
CN110096589A (en) | A kind of examination question feedback and recommendation explanation method and system based on image recognition technology | |
CN103530625A (en) | Optical character recognition method based on digital image processing | |
CN111460782A (en) | Information processing method, device and equipment | |
CN105335453A (en) | image file dividing method | |
CN111915635A (en) | Test question analysis information generation method and system supporting self-examination paper marking | |
Brisinello et al. | Optical Character Recognition on images with colorful background | |
US8195626B1 (en) | Compressing token-based files for transfer and reconstruction | |
CN109741273A (en) | A kind of mobile phone photograph low-quality images automatically process and methods of marking | |
CN108052918A (en) | A kind of person's handwriting Compare System and method | |
US20220269898A1 (en) | Information processing device, information processing system, information processing method, and non-transitory computer readable medium | |
CN108596280A (en) | Image identification method for literature search | |
CN108090728B (en) | Express information input method and system based on intelligent terminal | |
CN111191716A (en) | Method and device for classifying printed pictures | |
CN111126273A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
CN111797922B (en) | Text image classification method and device | |
Wu et al. | An effective texture spectrum descriptor | |
CN114332898A (en) | Automatic correcting method and device for connection test questions and storage medium | |
CN109460701B (en) | Font identification method based on longitudinal and transverse histograms | |
US11164035B2 (en) | Neural-network-based optical character recognition using specialized confidence functions |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180928 |