CN112990216A - Automatic book searching system and method for household bookshelf based on image and character recognition - Google Patents
Automatic book searching system and method for household bookshelf based on image and character recognition Download PDFInfo
- Publication number
- CN112990216A CN112990216A CN202110278642.8A CN202110278642A CN112990216A CN 112990216 A CN112990216 A CN 112990216A CN 202110278642 A CN202110278642 A CN 202110278642A CN 112990216 A CN112990216 A CN 112990216A
- Authority
- CN
- China
- Prior art keywords
- book
- database
- chip processor
- image
- definition camera
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/28—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet
- G06V30/287—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet of Kanji, Hiragana or Katakana characters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic book searching system and method of a household bookshelf based on image and character recognition, and the automatic book searching system comprises a high-definition camera, a chip processor, a database, input equipment and output equipment, wherein the high-definition camera is connected with the chip processor and is used for shooting a high-definition picture of the bookshelf facing outward from a spine of a book and transmitting the shot picture to the chip processor; the chip processor is connected with the high-definition camera and the database and is used for carrying out image segmentation and character extraction on the pictures transmitted by the high-definition camera so as to obtain book names with position information and transmitting the book name information to the database; the database is connected with the chip processor and is used for storing the book name information extracted by the chip processor; the input equipment is connected with the database and is used for inputting the name of the book to be searched by a user; the output equipment is connected with the database and used for displaying the book name and the position information of the book. The system can rapidly realize image segmentation, book position positioning, book name and character recognition and book name query, and has the advantages of high flexibility and accurate and rapid positioning.
Description
Technical Field
The invention relates to the field of image recognition, in particular to an automatic book searching system and method of a household bookshelf based on image and character recognition.
Background
With the development of national economy, the demand of people on mental culture is increased, more and more books are stored in families, and the problem of difficult book searching is caused. Book searching is no longer a unique requirement of libraries, and a requirement for solving the difficulty of book searching at home is urgent.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an automatic book searching system and method for a household bookshelf based on image and character recognition, so as to solve the problem that the household bookshelf proposed in the background is too much in book collection and inconvenient to search books.
In order to achieve the above purpose, the technical solution for solving the technical problem is as follows:
the invention discloses an automatic book searching system of a household bookshelf based on image and character recognition, which comprises a high-definition camera, a chip processor, a database, input equipment and output equipment, wherein the high-definition camera comprises:
the high-definition camera is connected with the chip processor and is used for shooting a high-definition picture of the bookshelf facing the spine outwards and transmitting the shot picture to the chip processor;
the chip processor is connected with the high-definition camera and the database and is used for carrying out image segmentation and character extraction on the pictures transmitted by the high-definition camera so as to obtain book names with position information and transmitting the book name information to the database;
the database is connected with the chip processor and is used for storing the book name information extracted by the chip processor;
the input equipment is connected with the database and is used for inputting the name of the book to be searched by a user;
the output equipment is connected with the database and used for displaying the book name and the position information of the book.
Further, the chip processor is used for obtaining the image edge by applying a Canny edge detection algorithm, completing the segmentation of the book spine by using an LSD (least squares) straight line detection algorithm, sequentially numbering the segmented images by using a recursive marking algorithm, extracting characters of the segmented images by using a CRNN (recursive mean square distribution) and CTC (central control unit) algorithm, and finally sequentially sending the extracted character information into a database for storage.
Preferably, the chip processor adopts TMS320DM642 and other series chip processors.
Preferably, the high-definition camera adopts a CMOS high-definition camera.
Preferably, the database is a MYSQL database.
Preferably, the output device is a display screen.
The invention also discloses an automatic book searching method of the household bookshelf based on image and character recognition, which is used for searching books by using the automatic book searching system and comprises the following steps:
step 1: the high-definition camera shoots a high-definition picture from the bookshelf with the spine facing outwards, and the shot picture is sent to the chip processor for processing;
step 2: obtaining the image edge by applying a Canny edge detection algorithm, and completing the segmentation of the book spine by using an LSD (least squares) straight line detection algorithm;
and step 3: sequentially numbering the segmented images by using a recursive marking algorithm;
and 4, step 4: performing character extraction on the segmented image by using a deep learning CRNN algorithm and a CTC algorithm;
and 5: sequentially sending the extracted character information into a database for storage;
step 6: the user inputs the name of the book from the input device, and the book searching system returns the position information of the book on the bookshelf and displays the position information on the output device.
Further, the step 2 specifically comprises the following steps:
step 21: carrying out noise reduction processing on the image by Gaussian filtering;
step 22: calculating the magnitude and direction of the gradient by using the finite difference of the first-order partial derivatives;
step 23: carrying out non-maximum suppression on the gradient amplitude;
step 24: edges are detected and continued using a dual threshold algorithm.
Further, step 4 specifically includes the following steps:
step 41: CNN is RNN extraction characteristics;
step 42: the RNN converts the characteristic sequence output by the CNN into output;
step 43: CTC is a translation layer, and a final prediction result is obtained.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
the automatic book searching system of the household bookshelf based on image and character recognition only needs to enable the spine of the book to face outwards when the book is placed; the images are taken by shooting, after the images are processed by a series of chip processors such as TMS320DM642 and the like, the results are stored in a MYSQL database, the position of a book can be displayed on a display screen by inputting the book name, and image segmentation, book position positioning, book name and character recognition and book name query can be rapidly realized. The method has the advantages of high flexibility, high real-time performance, low cost and accurate and rapid positioning.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a schematic diagram of an overall structure of an automatic book searching system of a household bookshelf based on image and character recognition according to the invention;
FIG. 2 is a logic block diagram of an implementation of an automatic book searching system of a household bookshelf based on image and character recognition according to the present invention;
FIG. 3 is a logic block diagram of an automatic book searching method for a household bookshelf based on image and character recognition according to the invention.
[ description of main symbols ]
1-a high-definition camera; 2-a chip processor; 3-a database; 4-an input device; 5-output device.
Detailed Description
While the embodiments of the present invention will be described and illustrated in detail with reference to the accompanying drawings, it is to be understood that the invention is not limited to the specific embodiments disclosed, but is intended to cover various modifications, equivalents, and alternatives falling within the scope of the invention as defined by the appended claims.
Example one
As shown in fig. 1-2, the invention discloses an automatic book searching system of a household bookshelf based on image and character recognition, comprising a high-definition camera, a chip processor, a database, an input device and an output device, wherein:
the high-definition camera is connected with the chip processor and is used for shooting a high-definition picture of the bookshelf facing the spine outwards and transmitting the shot picture to the chip processor, so that subsequent processing is facilitated;
the chip processor is connected with the high-definition camera and the database and is used for carrying out image segmentation and character extraction on the pictures transmitted by the high-definition camera so as to obtain book names with position information and transmitting the book name information to the database;
the database is connected with the chip processor and is used for storing the book name information extracted by the chip processor, so that the book position information can be conveniently inquired subsequently;
the input equipment is connected with the database and is used for inputting the name of the book to be searched by a user;
the output equipment is connected with the database and used for displaying the book name and the position information of the book.
Further, the chip processor is used for obtaining the image edge by applying a Canny edge detection algorithm, completing the segmentation of the book spine by using an LSD (least squares) straight line detection algorithm, sequentially numbering the segmented images by using a recursive marking algorithm, extracting characters of the segmented images by using a CRNN (recursive mean square distribution) and CTC (central control unit) algorithm, and finally sequentially sending the extracted character information into a database for storage.
Preferably, the chip processor adopts TMS320DM642 and other series chip processors.
Preferably, the high-definition camera adopts a CMOS high-definition camera.
Preferably, the database is a MYSQL database.
Preferably, the output device is a display screen.
Example two
As shown in fig. 3, the invention further discloses an automatic book searching method for a household bookshelf based on image and character recognition, which uses the automatic book searching system to search a book, and comprises the following steps:
step 1: the high-definition camera shoots a high-definition picture from the bookshelf with the spine facing outwards, and the shot picture is sent to the chip processor for processing;
step 2: obtaining the image edge by applying a Canny edge detection algorithm, and completing the segmentation of the book spine by using an LSD (least squares) straight line detection algorithm; in this step, the image segmentation is completed based on the spine boundary line existing in the form of a straight line in the obtained photograph.
Further, the step 2 specifically comprises the following steps:
step 21: carrying out noise reduction processing on the image by Gaussian filtering;
step 22: calculating the magnitude and direction of the gradient by using the finite difference of the first-order partial derivatives;
step 23: carrying out non-maximum suppression on the gradient amplitude;
step 24: edges are detected and continued using a dual threshold algorithm.
And step 3: sequentially numbering the segmented images by using a recursive marking algorithm;
and 4, step 4: performing character extraction on the segmented image by using a deep learning CRNN algorithm and a CTC algorithm; the CRNN algorithm realizes character detection by CNN and RNN algorithms, and the CTC algorithm realizes character recognition.
Further, step 4 specifically includes the following steps:
step 41: CNN is RNN extraction characteristics;
step 42: the RNN converts the characteristic sequence output by the CNN into output;
step 43: CTC is a translation layer, and a final prediction result is obtained.
And 5: the extracted character information is sequentially sent to a database for storage, and the stored content comprises the book name and the position information of the book;
step 6: the user inputs the title from the input device, the book-finding system returns the position information of the book on the bookshelf and displays the title and the position information of the book on the output device (display screen).
In the embodiment, the automatic book searching system of the household bookshelf based on image and character recognition only needs to enable the spine of the book to face outwards when the book is placed; the images are taken by shooting, after the images are processed by a series of chip processors such as TMS320DM642 and the like, the results are stored in a MYSQL database, the position of a book can be displayed on a display screen by inputting the book name, and image segmentation, book position positioning, book name and character recognition and book name query can be rapidly realized. The method has the advantages of high flexibility, high real-time performance, low cost and accurate and rapid positioning.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. The utility model provides an automatic book system that seeks of domestic bookshelf based on image and word discernment which characterized in that, includes high definition digtal camera, chip processor, database, input device and output device, wherein:
the high-definition camera is connected with the chip processor and is used for shooting a high-definition picture of the bookshelf facing the spine outwards and transmitting the shot picture to the chip processor;
the chip processor is connected with the high-definition camera and the database and is used for carrying out image segmentation and character extraction on the pictures transmitted by the high-definition camera so as to obtain book names with position information and transmitting the book name information to the database;
the database is connected with the chip processor and is used for storing the book name information extracted by the chip processor;
the input equipment is connected with the database and is used for inputting the name of the book to be searched by a user;
the output equipment is connected with the database and used for displaying the book name and the position information of the book.
2. The system of claim 1, wherein the chip processor is configured to obtain an image edge by using a Canny edge detection algorithm, complete the segmentation of a book spine by using an LSD line detection algorithm, sequentially number the segmented images by using a recursive labeling algorithm, extract characters from the segmented images by using a CRNN + CTC algorithm, and sequentially send the extracted character information to the database for storage.
3. The system as claimed in claim 1 or 2, wherein the chip processor is a chip processor of TMS320DM642 series.
4. The system according to claim 1, wherein the high-definition camera is a CMOS high-definition camera.
5. The system of claim 1, wherein the database is a MYSQL database.
6. The system according to claim 1, wherein the output device is a display screen.
7. An automatic book searching method for a household bookshelf based on image and character recognition, which is characterized in that the automatic book searching system of any one of claims 1-6 is used for searching books, and comprises the following steps:
step 1: the high-definition camera shoots a high-definition picture from the bookshelf with the spine facing outwards, and the shot picture is sent to the chip processor for processing;
step 2: obtaining the image edge by applying a Canny edge detection algorithm, and completing the segmentation of the book spine by using an LSD (least squares) straight line detection algorithm;
and step 3: sequentially numbering the segmented images by using a recursive marking algorithm;
and 4, step 4: performing character extraction on the segmented image by using a deep learning CRNN algorithm and a CTC algorithm;
and 5: sequentially sending the extracted character information into a database for storage;
step 6: the user inputs the name of the book from the input device, and the book searching system returns the position information of the book on the bookshelf and displays the position information on the output device.
8. The automatic book searching method for the household bookshelf based on the image and character recognition as claimed in claim 7, wherein the step 2 specifically comprises the following steps:
step 21: carrying out noise reduction processing on the image by Gaussian filtering;
step 22: calculating the magnitude and direction of the gradient by using the finite difference of the first-order partial derivatives;
step 23: carrying out non-maximum suppression on the gradient amplitude;
step 24: edges are detected and continued using a dual threshold algorithm.
9. The automatic book searching method for the household bookshelf based on the image and character recognition as claimed in claim 7, wherein the step 4 specifically comprises the following steps:
step 41: CNN is RNN extraction characteristics;
step 42: the RNN converts the characteristic sequence output by the CNN into output;
step 43: CTC is a translation layer, and a final prediction result is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110278642.8A CN112990216A (en) | 2021-03-16 | 2021-03-16 | Automatic book searching system and method for household bookshelf based on image and character recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110278642.8A CN112990216A (en) | 2021-03-16 | 2021-03-16 | Automatic book searching system and method for household bookshelf based on image and character recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990216A true CN112990216A (en) | 2021-06-18 |
Family
ID=76335753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110278642.8A Pending CN112990216A (en) | 2021-03-16 | 2021-03-16 | Automatic book searching system and method for household bookshelf based on image and character recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990216A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241374A (en) * | 2018-06-07 | 2019-01-18 | 广东数相智能科技有限公司 | A kind of book information library update method and books in libraries localization method |
| US20190074028A1 (en) * | 2017-09-01 | 2019-03-07 | Newton Howard | Real-time vocal features extraction for automated emotional or mental state assessment |
| CN111475613A (en) * | 2020-03-06 | 2020-07-31 | 深圳壹账通智能科技有限公司 | Case classification method and device, computer equipment and storage medium |
-
2021
- 2021-03-16 CN CN202110278642.8A patent/CN112990216A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190074028A1 (en) * | 2017-09-01 | 2019-03-07 | Newton Howard | Real-time vocal features extraction for automated emotional or mental state assessment |
| CN109241374A (en) * | 2018-06-07 | 2019-01-18 | 广东数相智能科技有限公司 | A kind of book information library update method and books in libraries localization method |
| CN111475613A (en) * | 2020-03-06 | 2020-07-31 | 深圳壹账通智能科技有限公司 | Case classification method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2608261C2 (en) | Automatic tag generation based on image content | |
| JP6397144B2 (en) | Business discovery from images | |
| GB2607749A (en) | Fine-grained visual recognition in mobile augmented reality | |
| CN110503076B (en) | Video classification method, device, equipment and medium based on artificial intelligence | |
| CN110427859A (en) | A kind of method for detecting human face, device, electronic equipment and storage medium | |
| CN106033435A (en) | Article identification method and apparatus, and indoor map generation method and apparatus | |
| CN102436590A (en) | Real-time tracking method based on on-line learning and tracking system thereof | |
| CN109558792B (en) | Method and system for detecting internet logo content based on samples and features | |
| CN103428537A (en) | Video processing method and video processing device | |
| CN106295514A (en) | A kind of method and device of image recognition exercise question display answer | |
| CN102375987A (en) | Image processing device and image feature vector extracting and image matching method | |
| CN107644105A (en) | Question searching method and device | |
| CN106529375A (en) | Mobile terminal and object feature identification method for image of mobile terminal | |
| WO2020199512A1 (en) | Question information collection method and system | |
| CN103838840A (en) | Address list search method based on image correlation pattern | |
| CN111079777B (en) | Page positioning-based click-to-read method and electronic equipment | |
| CN112990216A (en) | Automatic book searching system and method for household bookshelf based on image and character recognition | |
| CN112287790A (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN111008295A (en) | Page retrieval method and device, electronic equipment and storage medium | |
| CN115937492A (en) | Transformer equipment infrared image identification method based on feature identification | |
| CN111753715B (en) | Method and device for shooting test questions in click-to-read scene, electronic equipment and storage medium | |
| CN112507941A (en) | Cross-vision field pedestrian re-identification method and device for mine AI video analysis | |
| CN112307158A (en) | Information retrieval method, device, equipment and medium | |
| CN110647844A (en) | Shooting and identifying method for articles for children | |
| CN109447087A (en) | A kind of oil smoke image dynamic area extracting method, identifying system and kitchen ventilator |
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 |