CN105654057A - Picture auditing system and picture auditing method based on picture contents - Google Patents
Picture auditing system and picture auditing method based on picture contents Download PDFInfo
- Publication number
- CN105654057A CN105654057A CN201511026630.7A CN201511026630A CN105654057A CN 105654057 A CN105654057 A CN 105654057A CN 201511026630 A CN201511026630 A CN 201511026630A CN 105654057 A CN105654057 A CN 105654057A
- Authority
- CN
- China
- Prior art keywords
- picture
- examination
- verification condition
- meets
- detection
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a picture auditing system and a picture auditing method based on picture contents. The system comprises a picture character detection module and a picture image detection module, wherein the picture character detection module is used for carrying out character identification processing on the picture and judging whether picture information meets a first auditing condition or not according to identified character information; and the picture image detection module is used for carrying out character extraction processing on the picture which meets the first auditing condition, and determining whether the picture which meets the first auditing condition meets a second auditing condition or not according to extracted image characteristics. On the basis of the identified character information and the extracted image characteristics, the picture contents are audited, picture auditing efficiency can be improved, picture auditing accuracy can be improved, a probability that the pictures which break the rule appear in a shopping mall is reduced, and commodity display quality and shopping mall reputation are improved.
Description
Technical field
The present invention relates to picture processing field, specifically, relate to a kind of picture examination system based on image content and picture examination method.
Background technology
At home and abroad in e-commerce system, merchandise display is described mainly through the form of picture and word, and wherein picture is the most directly perceived, so commodity picture is particularly important to the effect of descriptive labelling in e-commerce system.
Generally in e-commerce system, trade company all can upload substantial amounts of commodity picture and sold goods are shown. In order to avoid trade company uploads violation picture, it is necessary to the commodity picture that trade company is uploaded is audited. At present, the commodity picture that trade company is uploaded by e-commerce system mostly by manually auditing the mode of commodity picture one by one is audited, and this needs to expend substantial amounts of manpower and time, and can reduce the efficiency of trade company's publishing commodity.
Summary of the invention
Drawbacks described above in view of prior art, embodiment of the present invention provides a kind of picture examination system based on image content and picture examination method, efficiency and the accuracy rate of picture examination can be improved, reduce the probability that violation picture occurs in store, improve the quality of merchandise display and the prestige in store.
Specifically, embodiment of the present invention provides a kind of picture examination system based on image content, comprising:
Image character detection module, for carrying out Text region process and judging whether picture meets the first examination & verification condition according to the Word message identified to picture;
Graphic image detection module, for the picture meeting described first examination & verification condition is carried out feature extraction process, determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
Correspondingly, embodiment of the present invention additionally provides a kind of picture examination method based on image content, comprising:
Picture is carried out Text region process, and judges whether picture meets the first examination & verification condition according to the Word message identified;
The picture meeting described first examination & verification condition is carried out feature extraction process, and determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
Embodiment of the present invention is adopted to have following beneficial effect:
Based on the Word message identified and the pictorial feature extracted, image content is audited, the efficiency of picture examination can not only be improved, the accuracy rate of picture examination can also be improved, reduce the probability that violation picture occurs in store, improve the quality of merchandise display and the prestige in store.
Accompanying drawing explanation
Fig. 1 is an example of the block diagram of a kind of picture examination system based on image content according to embodiments of the present invention;
Fig. 2 illustrates an example of the block diagram of the image character detection module of picture examination system shown in Fig. 1;
Fig. 3 illustrates an example of the block diagram of the graphic image detection module of picture examination system shown in Fig. 1;
Fig. 4 is another example of the block diagram of a kind of picture examination system based on image content according to embodiments of the present invention;
Fig. 5 is the schematic flow sheet of a kind of picture examination method based on image content according to embodiments of the present invention;
Fig. 6 is the schematic flow sheet based on the picture examination method of image content of the another kind according to embodiments of the present invention.
Detailed description of the invention
For the ease of understanding the various aspects of technical solution of the present invention, feature and advantage, below in conjunction with accompanying drawing, the present invention is specifically described. Should be appreciated that following various embodiments are served only for illustrating, not for limiting the scope of the invention.
Fig. 1 is an example of the block diagram of a kind of picture examination system based on image content according to embodiments of the present invention. With reference to Fig. 1, picture examination system includes image character detection module 11 and graphic image detection module 12. Wherein, image character detection module 11 for carrying out Text region process and judging whether picture meets the first examination & verification condition according to the Word message identified to picture; Graphic image detection module 12, for the picture meeting described first examination & verification condition is carried out feature extraction process, determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
In the present embodiment, image content includes the word in picture and picture, the Teletext Standard of the first examination & verification condition correspondence picture, and the second examination & verification condition is corresponding to the picture standard of picture.
Adopt the picture examination system that the present embodiment provides, based on the Word message identified and the pictorial feature extracted, image content is audited, the efficiency of picture examination can not only be improved, the accuracy rate of picture examination can also be improved, reduce the probability that violation picture occurs in store, improve the quality of merchandise display and the prestige in store.
Alternatively, in a kind of implementation of the present embodiment, as in figure 2 it is shown, image character detection module 11 includes Text region submodule 111 and the first examination & verification submodule 112. Illustrate separately below.
Text region submodule 111 is for carrying out Text region process to picture, and its result is to identify the Word message comprised in picture. In a kind of example of this implementation, it is possible to first picture is converted into the picture being easier to carry out optical character recognition (OCR) to improve the identification of word, then pass through OCR and analyze the word extracted in picture. In one more specifically example, it is possible to identify Word message in the following manner: the word in the cutting of picture binary conversion treatment, picture, Word Input, same picture merges.
The first examination & verification submodule 112 sensitive word dictionary for presetting according to the Word message inquiry identified, according to whether the Word message identified comprises sensitive word, or, whether the ratio of the sensitive word comprised according to the Word message identified reaches to set threshold value, it is determined that whether picture meets described first examination & verification condition. In a kind of example in this implementation, the suspicious degree of picture character information can be calculated in the following way: assume: the word number identified from picture is M, base identifies n sensitive word, n sensitive word total number of word N, so suspicious degree is N/M, then whether reaches to set threshold value according to suspicious degree and determines whether picture meets the first examination & verification condition.
Alternatively, in a kind of implementation of the present embodiment, as it is shown on figure 3, graphic image detection module 12 includes feature extraction submodule 121 and second instance nucleon module 122, illustrate separately below.
Feature extraction submodule 121 is for carrying out feature extraction process to the picture meeting described first examination & verification condition, and its result is to extract the pictorial feature of picture. Alternatively, in a kind of example of this implementation, in order to detect the indecency picture of yellow in picture, pictorial feature include following any one or multiple: area of skin color of human body area accounting in picture, exposed region and the area ratio of area of skin color of human body, the texture value of exposed region, the excessive situation of color of exposed region, exposed region the ratio of height and the width. Usually as the yellow map of sensitization picture, area of skin color of human body therein accounts for larger proportion, although human body complexion is likely to difference to some extent, but is distributed within the specific limits, and the texture of exposed region is generally smaller, and color is smoother. Additionally, the height-width ratio in some region (such as, pixel value region within the scope of setting regions) can also as human body set feature.
That is, in order to realize in this implementation, can first analyze (such as, adopt big data analysis) feature of picture in sensitization picture (being not limited to yellow picture), then the pictorial feature of the feature of reaction sensitization picture and the pictorial feature span of sensitization picture it is determined to according to analysis result, in this manner it is possible to the relation passed through between pictorial feature and the pictorial feature span of sensitization picture extracted determines whether picture belongs to sensitization picture. As for concrete pictorial feature except the example above; those skilled in the art can expand neatly according to the thought that this implementation provides; pictorial feature span then can manually or determine after equipment analysis, and this all falls within protection scope of the present invention, does not repeat herein.
It should be noted that the present invention mention exposed region, area of skin color of human body all can pass through preset certain parameter area (such as, hue, saturation, intensity etc.) characterize.
Whether second instance nucleon module 122 meets preset value for the pictorial feature extracted according to described feature extraction submodule 121 and judges whether the picture meeting described first examination & verification condition meets described second examination & verification condition. Such as, it is judged that whether the pictorial feature extracted drops within the pictorial feature span of default sensitization picture, if it is, determine that photo current is unsatisfactory for the second examination & verification condition, sensitization picture is belonged to.
Fig. 4 is another example of the block diagram of a kind of picture examination system based on image content according to embodiments of the present invention, with reference to Fig. 4, picture examination system is except including image character detection module 11 and graphic image detection module 12, also include picture preliminary examination module the 13, first memory module 14 and the second memory module 15, specifically described below. Wherein refer to the explanation in example shown in Fig. 1��Fig. 3 about the explanation of image character detection module 11 and graphic image detection module 12, do not repeat herein.
In the present embodiment, picture preliminary examination module 13 for carrying out pre-detection process to picture, and triggers the picture that the detection of described image character detection module is processed by described pre-detection. Wherein, described pre-detection processes whether following any one or the many kinds of parameters that include detection picture meet preset requirement: whether picture format, the file size of picture, the size of picture, picture are pure color picture.Described pre-detection processes for picture is carried out Preliminary screening, and therefore, screening conditions and parameter can be arranged as required flexibly, are not particularly limited herein.
In the present embodiment, the first memory module 14 is for storing the picture meeting described second examination & verification condition; Second memory module 15 is for storing the picture being unsatisfactory for described first examination & verification condition and being unsatisfactory for the picture of described second examination & verification condition. Wherein, the picture of the second memory module 15 storage can by manually auditing further. So, can realize meeting the picture (namely by audit picture) of the second examination & verification condition and being unsatisfactory for the picture of described first examination & verification condition and be unsatisfactory for the described second picture (namely not passing through the picture of examination & verification) auditing condition and store respectively, it is simple to the follow-up process respectively to picture.
Above in association with accompanying drawing, the system embodiment of the present invention is carried out exemplary illustration, below in conjunction with accompanying drawing, the embodiment of the method for the present invention is illustrative. Wherein, about the explanation of related names, term, and the explanation of the concrete processing mode about relevant treatment, refer to the explanation in system embodiment, repeat no more.
Fig. 5 is the schematic flow sheet of a kind of picture examination method based on image content according to embodiments of the present invention, and with reference to Fig. 5, described method includes:
50: word examination & verification processes. Specifically, picture is carried out Text region process, and judges whether picture meets the first examination & verification condition according to the Word message identified.
52: picture examination & verification processes. Specifically, the picture meeting described first examination & verification condition is carried out feature extraction process, and determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
Adopt the picture examination method that the present embodiment provides, based on the Word message identified and the pictorial feature extracted, image content is audited, the efficiency of picture examination can not only be improved, the accuracy rate of picture examination can also be improved, reduce the probability that violation picture occurs in store, improve the quality of merchandise display and the prestige in store.
Alternatively, in a kind of implementation of the present embodiment, processing 50 can be accomplished by: first, picture is carried out Text region process; Afterwards, the sensitive word dictionary preset according to the Word message inquiry identified; Then, according to whether the Word message identified comprises sensitive word, or, whether the ratio of the sensitive word comprised according to the Word message identified reaches to set threshold value, it is determined that whether picture meets described first examination & verification condition.
Alternatively, in a kind of implementation of the present embodiment, processing 52 can be accomplished by: first, and the picture meeting described first examination & verification condition is carried out feature extraction process; Then, whether meet preset value according to the pictorial feature extracted and judge whether the picture meeting described first examination & verification condition meets described second examination & verification condition. Wherein, in the concrete example of one, described pictorial feature include following any one or multiple: area of skin color of human body area accounting in picture, exposed region and the area ratio of area of skin color of human body, the texture value of exposed region, the excessive situation of color of exposed region, exposed region the ratio of height and the width.
Fig. 6 is the schematic flow sheet of a kind of picture examination method based on image content according to embodiments of the present invention, and with reference to Fig. 6, described method includes:
60: picture pre-detection processes.Specifically, picture is carried out pre-detection process, then carry out subsequent treatment 62 for the picture processed by described pre-detection. Wherein, described pre-detection processes whether following any one or the many kinds of parameters that include detection picture meet preset requirement: whether picture format, the file size of picture, the size of picture, picture are pure color picture.
62: word examination & verification processes. Specifically, the picture processed by pre-detection is carried out Text region process, and judges whether picture meets the first examination & verification condition according to the Word message identified.
64: picture examination & verification processes. Specifically, the picture meeting described first examination & verification condition is carried out feature extraction process, and determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
Adopt the picture examination method that the present embodiment provides, process such processing mode by pre-detection process-Text region process-picture examination & verification, it is possible to the efficiency of picture examination is greatly improved.
Alternatively, in a kind of implementation of the present embodiment, after processing 64, meet the picture of described second examination & verification condition in the first memory block storage; It is unsatisfactory for the picture of described first examination & verification condition in the second memory block storage and is unsatisfactory for the picture of described second examination & verification condition. So, by the classification storage to the picture not passing through examination & verification passing through examination & verification, it is simple to follow-up picture processing.
Alternatively, in other embodiments of the invention, can according to the ratio of the sensitive word comprised in the Word message of picture or quantity, picture pictorial feature position in pictorial feature span (such as, pictorial feature span is divided into different grades of scope) recognition result of picture will be divided into the different suspicious degree such as light, middle and high, and store respectively according to different suspicious degree. When needs carry out manual examination and verification, show suspicious picture (that is, be unsatisfactory for the picture of the first examination & verification condition and be unsatisfactory for the picture of the second examination & verification condition) list according to suspicious degree, in order to carry out manual examination and verification.
When adopting method provided by the invention or system to carry out picture examination, a kind of exemplary concrete handling process is as follows:
1. traversal picture directory, processes picture file one by one.
2. analyze the time labelling in picture file name, it may be judged whether for the picture on the same day.
3. analyzing the picture number in picture file name, inquiry data base judges that whether picture number is effective.
4. the form of pair picture, size and detect with or without content, the picture that detection is not passed through carries out follow-up suspicious picture examination and processes, and otherwise enters next step.
5. pair picture file carries out pretreatment, including picture binaryzation, picture cutting, the picture temporary file after processing is carried out picture character extraction, merges the identification word of same picture.
6. pair picture recognition word is analyzed, it is judged that whether the inside has sensitive word, and sensitive word occurrence number is added up, and calculates suspicious degree, has the picture of sensitive word to carry out follow-up suspicious picture examination and processes, otherwise enters next step.
7. pair picture carries out yellow information detection, has the suspicious picture examination of entrance of yellow information. For example, with reference to process 52 above.
8. picture relevant information and recognition result are put in storage, carry out suspicious picture examination process for suspicious picture, for instance, show suspicious picture with tabular form so that manual examination and verification.
Through the above description of the embodiments, those skilled in the art is it can be understood that can realize by the mode of software combined with hardware platform to the present invention. Based on such understanding, what background technology was contributed by technical scheme can embody with the form of software product in whole or in part, this computer software product can be stored in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) perform the method described in some part of each embodiment of the present invention or embodiment.
Skilled person should be appreciated that and disclosed above is only embodiments of the present invention, certainly with this interest field limiting the present invention, according to the equivalent variations that embodiment of the present invention is made, can not still belong to the scope that the claims in the present invention contain.
Claims (14)
1. the picture examination system based on image content, it is characterised in that described system includes:
Image character detection module, for carrying out Text region process and judging whether picture meets the first examination & verification condition according to the Word message identified to picture;
Graphic image detection module, for the picture meeting described first examination & verification condition is carried out feature extraction process, determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
2. the system as claimed in claim 1, it is characterised in that described image character detection module includes:
Text region submodule, for carrying out Text region process to picture;
First examination & verification submodule, for the sensitive word dictionary preset according to the Word message inquiry identified, according to whether the Word message identified comprises sensitive word, or, whether the ratio of the sensitive word comprised according to the Word message identified reaches to set threshold value, it is determined that whether picture meets described first examination & verification condition.
3. the system as claimed in claim 1, it is characterised in that described graphic image detection module includes:
Feature extraction submodule, for carrying out feature extraction process to the picture meeting described first examination & verification condition;
Second instance nucleon module, whether the pictorial feature for extracting according to described feature extraction submodule meets preset value and judges whether the picture meeting described first examination & verification condition meets described second examination & verification condition.
4. the system as described in claim 1 or 3, it is characterised in that described pictorial feature include following any one or multiple:
Area of skin color of human body area accounting in picture, exposed region and the area ratio of area of skin color of human body, the texture value of exposed region, the excessive situation of color of exposed region, exposed region the ratio of height and the width.
5. the system as claimed in claim 1, it is characterised in that described system also includes:
Picture preliminary examination module, for picture carries out pre-detection process, and triggers the picture that the detection of described image character detection module is processed by described pre-detection.
6. system as claimed in claim 5, it is characterised in that described pre-detection processes whether following any one or the many kinds of parameters that include detection picture meet preset requirement:
Whether picture format, the file size of picture, the size of picture, picture are pure color picture.
7. the system as claimed in claim 1, it is characterised in that described system also includes:
First memory module, for storing the picture meeting described second examination & verification condition;
Second memory module, for storing the picture being unsatisfactory for described first examination & verification condition and being unsatisfactory for the picture of described second examination & verification condition.
8. the picture examination method based on image content, it is characterised in that described method includes:
Picture is carried out Text region process, and judges whether picture meets the first examination & verification condition according to the Word message identified;
The picture meeting described first examination & verification condition is carried out feature extraction process, and determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition.
9. method as claimed in claim 8, it is characterised in that picture is carried out Text region process, and judges whether picture meets the first examination & verification condition and include according to the Word message identified:
Picture is carried out Text region process;
According to the sensitive word dictionary that the Word message inquiry identified is preset;
According to whether the Word message identified comprises sensitive word, or, whether the ratio of the sensitive word comprised according to the Word message identified reaches to set threshold value, it is determined that whether picture meets described first examination & verification condition.
10. method as claimed in claim 8, it is characterised in that the picture meeting described first examination & verification condition is carried out feature extraction process, and determines according to the pictorial feature extracted whether the picture meeting described first examination & verification condition meets the second examination & verification condition and include:
The picture meeting described first examination & verification condition is carried out feature extraction process;
Whether meet preset value according to the pictorial feature extracted and judge whether the picture meeting described first examination & verification condition meets described second examination & verification condition.
11. the method as described in claim 8 or 10, it is characterised in that described pictorial feature include following any one or multiple:
Area of skin color of human body area accounting in picture, exposed region and the area ratio of area of skin color of human body, the texture value of exposed region, the excessive situation of color of exposed region, exposed region the ratio of height and the width.
12. method as claimed in claim 8, it is characterised in that described method also includes:
Picture is carried out pre-detection process, and the picture processed by described pre-detection is carried out described Text region process.
13. method as claimed in claim 12, it is characterised in that described pre-detection processes whether following any one or the many kinds of parameters that include detection picture meet preset requirement:
Whether picture format, the file size of picture, the size of picture, picture are pure color picture.
14. method as claimed in claim 8, it is characterised in that described method also includes:
The picture of described second examination & verification condition is met in the first memory block storage;
It is unsatisfactory for the picture of described first examination & verification condition in the second memory block storage and is unsatisfactory for the picture of described second examination & verification condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511026630.7A CN105654057A (en) | 2015-12-31 | 2015-12-31 | Picture auditing system and picture auditing method based on picture contents |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511026630.7A CN105654057A (en) | 2015-12-31 | 2015-12-31 | Picture auditing system and picture auditing method based on picture contents |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105654057A true CN105654057A (en) | 2016-06-08 |
Family
ID=56490923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511026630.7A Pending CN105654057A (en) | 2015-12-31 | 2015-12-31 | Picture auditing system and picture auditing method based on picture contents |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105654057A (en) |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106331695A (en) * | 2016-08-24 | 2017-01-11 | 合肥数酷信息技术有限公司 | Video and audio-based detection and data analysis system |
CN106446803A (en) * | 2016-09-07 | 2017-02-22 | 北京小米移动软件有限公司 | Live content recognition processing method, device and equipment |
CN107194394A (en) * | 2016-09-29 | 2017-09-22 | 北京神州泰岳信息安全技术有限公司 | Remotely access monitoring method and relevant apparatus |
CN107729924A (en) * | 2017-09-25 | 2018-02-23 | 平安科技(深圳)有限公司 | Picture review probability interval generation method and picture review decision method |
CN107832925A (en) * | 2017-10-20 | 2018-03-23 | 阿里巴巴集团控股有限公司 | Internet content risk evaluating method, device and server |
CN107896335A (en) * | 2017-12-06 | 2018-04-10 | 任明和 | Video detection and ranking method based on big data technology |
CN107944022A (en) * | 2017-12-11 | 2018-04-20 | 努比亚技术有限公司 | Picture classification method, mobile terminal and computer-readable recording medium |
CN108171774A (en) * | 2017-12-26 | 2018-06-15 | 上海展扬通信技术有限公司 | A kind of post card making method and relevant device |
CN108388410A (en) * | 2018-02-09 | 2018-08-10 | 浙江印歌网络科技有限公司 | Copy method and device |
CN108765785A (en) * | 2018-04-02 | 2018-11-06 | 广州供电局有限公司 | A kind of long-distance video automatic teller machine VTM self-service terminal systems |
CN109002842A (en) * | 2018-06-27 | 2018-12-14 | 北京字节跳动网络技术有限公司 | Image-recognizing method and device |
CN109409362A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | The detection of picture sensitive word and localization method and device based on tesseract engine |
CN110097329A (en) * | 2019-03-16 | 2019-08-06 | 平安科技(深圳)有限公司 | Signal auditing method, device, equipment and computer readable storage medium |
CN110399361A (en) * | 2019-07-31 | 2019-11-01 | 腾讯科技(深圳)有限公司 | A kind of method and information processing unit of information processing |
CN110414929A (en) * | 2019-07-10 | 2019-11-05 | 广州市巴图鲁信息科技有限公司 | A kind of automobile parts picture intelligent checks method |
CN110473263A (en) * | 2018-05-09 | 2019-11-19 | 北京京东尚科信息技术有限公司 | The checking method of picture, device and system |
CN110503084A (en) * | 2018-05-18 | 2019-11-26 | 广州腾讯科技有限公司 | Character area recognition methods and device in a kind of image |
CN110766340A (en) * | 2019-10-31 | 2020-02-07 | 支付宝(杭州)信息技术有限公司 | Business auditing method, device and equipment |
CN110879963A (en) * | 2019-09-18 | 2020-03-13 | 北京印刷学院 | Sensitive expression package detection method and device and electronic equipment |
CN110956123A (en) * | 2019-11-27 | 2020-04-03 | 中移(杭州)信息技术有限公司 | Rich media content auditing method and device, server and storage medium |
CN110992446A (en) * | 2019-12-04 | 2020-04-10 | 杭州三体视讯科技有限公司 | Picture auditing method |
CN111292530A (en) * | 2020-02-04 | 2020-06-16 | 浙江大华技术股份有限公司 | Method, device, server and storage medium for processing violation pictures |
CN111385602A (en) * | 2018-12-29 | 2020-07-07 | 广州市百果园信息技术有限公司 | Video auditing method, medium and computer equipment based on multi-level and multi-model |
CN111767493A (en) * | 2020-07-07 | 2020-10-13 | 杭州安恒信息技术股份有限公司 | Method, device, equipment and storage medium for displaying content data of website |
CN111860659A (en) * | 2020-07-24 | 2020-10-30 | 上海德易车信息科技有限公司 | Picture auditing method and device, electronic equipment and readable storage medium |
CN111882371A (en) * | 2019-04-15 | 2020-11-03 | 阿里巴巴集团控股有限公司 | Content information processing method, image-text content processing method, computer device, and medium |
CN111984881A (en) * | 2019-05-21 | 2020-11-24 | 北京沃东天骏信息技术有限公司 | Prompting method, prompting device, terminal, server and storage medium |
CN112131376A (en) * | 2019-06-24 | 2020-12-25 | 北京华雨天成文化传播有限公司 | Auditing method and device |
CN112348615A (en) * | 2020-03-24 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method and device for auditing information |
CN112700207A (en) * | 2020-12-11 | 2021-04-23 | 五八到家有限公司 | Resume information processing method, device and storage medium |
CN109284732B (en) * | 2018-10-15 | 2021-04-30 | 西安艾润物联网技术服务有限责任公司 | Picture reporting method and related device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1396533A (en) * | 2001-07-16 | 2003-02-12 | 友立资讯股份有限公司 | Sexy file judging system and method |
CN1761205A (en) * | 2005-11-18 | 2006-04-19 | 郑州金惠计算机系统工程有限公司 | System for detecting eroticism and unhealthy images on network based on content |
CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
-
2015
- 2015-12-31 CN CN201511026630.7A patent/CN105654057A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1396533A (en) * | 2001-07-16 | 2003-02-12 | 友立资讯股份有限公司 | Sexy file judging system and method |
CN1761205A (en) * | 2005-11-18 | 2006-04-19 | 郑州金惠计算机系统工程有限公司 | System for detecting eroticism and unhealthy images on network based on content |
CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
Non-Patent Citations (1)
Title |
---|
丛健: "不良信息过滤技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106331695B (en) * | 2016-08-24 | 2018-08-07 | 合肥数酷信息技术有限公司 | One kind is based on video/audio detection and data analysis system |
CN106331695A (en) * | 2016-08-24 | 2017-01-11 | 合肥数酷信息技术有限公司 | Video and audio-based detection and data analysis system |
CN106446803A (en) * | 2016-09-07 | 2017-02-22 | 北京小米移动软件有限公司 | Live content recognition processing method, device and equipment |
CN107194394A (en) * | 2016-09-29 | 2017-09-22 | 北京神州泰岳信息安全技术有限公司 | Remotely access monitoring method and relevant apparatus |
CN107729924A (en) * | 2017-09-25 | 2018-02-23 | 平安科技(深圳)有限公司 | Picture review probability interval generation method and picture review decision method |
CN107832925A (en) * | 2017-10-20 | 2018-03-23 | 阿里巴巴集团控股有限公司 | Internet content risk evaluating method, device and server |
CN107896335B (en) * | 2017-12-06 | 2019-12-31 | 重庆智韬信息技术中心 | Video detection and rating method based on big data technology |
CN107896335A (en) * | 2017-12-06 | 2018-04-10 | 任明和 | Video detection and ranking method based on big data technology |
CN107944022A (en) * | 2017-12-11 | 2018-04-20 | 努比亚技术有限公司 | Picture classification method, mobile terminal and computer-readable recording medium |
CN108171774A (en) * | 2017-12-26 | 2018-06-15 | 上海展扬通信技术有限公司 | A kind of post card making method and relevant device |
CN108388410A (en) * | 2018-02-09 | 2018-08-10 | 浙江印歌网络科技有限公司 | Copy method and device |
CN108765785A (en) * | 2018-04-02 | 2018-11-06 | 广州供电局有限公司 | A kind of long-distance video automatic teller machine VTM self-service terminal systems |
CN110473263A (en) * | 2018-05-09 | 2019-11-19 | 北京京东尚科信息技术有限公司 | The checking method of picture, device and system |
CN110503084A (en) * | 2018-05-18 | 2019-11-26 | 广州腾讯科技有限公司 | Character area recognition methods and device in a kind of image |
CN110503084B (en) * | 2018-05-18 | 2024-03-01 | 广州腾讯科技有限公司 | Method and device for identifying text region in image |
CN109002842A (en) * | 2018-06-27 | 2018-12-14 | 北京字节跳动网络技术有限公司 | Image-recognizing method and device |
CN109409362A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | The detection of picture sensitive word and localization method and device based on tesseract engine |
CN109284732B (en) * | 2018-10-15 | 2021-04-30 | 西安艾润物联网技术服务有限责任公司 | Picture reporting method and related device |
CN111385602A (en) * | 2018-12-29 | 2020-07-07 | 广州市百果园信息技术有限公司 | Video auditing method, medium and computer equipment based on multi-level and multi-model |
CN111385602B (en) * | 2018-12-29 | 2022-08-09 | 广州市百果园信息技术有限公司 | Video auditing method, medium and computer equipment based on multi-level and multi-model |
CN110097329A (en) * | 2019-03-16 | 2019-08-06 | 平安科技(深圳)有限公司 | Signal auditing method, device, equipment and computer readable storage medium |
CN110097329B (en) * | 2019-03-16 | 2023-11-14 | 平安科技(深圳)有限公司 | Information auditing method, device, equipment and computer readable storage medium |
CN111882371A (en) * | 2019-04-15 | 2020-11-03 | 阿里巴巴集团控股有限公司 | Content information processing method, image-text content processing method, computer device, and medium |
CN111984881A (en) * | 2019-05-21 | 2020-11-24 | 北京沃东天骏信息技术有限公司 | Prompting method, prompting device, terminal, server and storage medium |
CN112131376A (en) * | 2019-06-24 | 2020-12-25 | 北京华雨天成文化传播有限公司 | Auditing method and device |
CN110414929A (en) * | 2019-07-10 | 2019-11-05 | 广州市巴图鲁信息科技有限公司 | A kind of automobile parts picture intelligent checks method |
CN110399361A (en) * | 2019-07-31 | 2019-11-01 | 腾讯科技(深圳)有限公司 | A kind of method and information processing unit of information processing |
CN110879963A (en) * | 2019-09-18 | 2020-03-13 | 北京印刷学院 | Sensitive expression package detection method and device and electronic equipment |
CN110879963B (en) * | 2019-09-18 | 2023-09-05 | 北京印刷学院 | Sensitive expression package detection method and device and electronic equipment |
CN110766340A (en) * | 2019-10-31 | 2020-02-07 | 支付宝(杭州)信息技术有限公司 | Business auditing method, device and equipment |
CN110956123B (en) * | 2019-11-27 | 2024-02-27 | 中移(杭州)信息技术有限公司 | Method, device, server and storage medium for auditing rich media content |
CN110956123A (en) * | 2019-11-27 | 2020-04-03 | 中移(杭州)信息技术有限公司 | Rich media content auditing method and device, server and storage medium |
CN110992446A (en) * | 2019-12-04 | 2020-04-10 | 杭州三体视讯科技有限公司 | Picture auditing method |
CN111292530A (en) * | 2020-02-04 | 2020-06-16 | 浙江大华技术股份有限公司 | Method, device, server and storage medium for processing violation pictures |
CN112348615A (en) * | 2020-03-24 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method and device for auditing information |
CN112348615B (en) * | 2020-03-24 | 2024-06-18 | 北京沃东天骏信息技术有限公司 | Method and device for auditing information |
CN111767493A (en) * | 2020-07-07 | 2020-10-13 | 杭州安恒信息技术股份有限公司 | Method, device, equipment and storage medium for displaying content data of website |
CN111860659A (en) * | 2020-07-24 | 2020-10-30 | 上海德易车信息科技有限公司 | Picture auditing method and device, electronic equipment and readable storage medium |
CN112700207A (en) * | 2020-12-11 | 2021-04-23 | 五八到家有限公司 | Resume information processing method, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105654057A (en) | Picture auditing system and picture auditing method based on picture contents | |
CN107067006B (en) | Verification code identification method and system serving for data acquisition | |
CN110348439B (en) | Method, computer readable medium and system for automatically identifying price tags | |
CN112906463A (en) | Image-based fire detection method, device, equipment and storage medium | |
CA2656425A1 (en) | Recognizing text in images | |
CN107896335B (en) | Video detection and rating method based on big data technology | |
KR100907172B1 (en) | System and Method for Multi-stage Filtering of Malicious Videos in Video Distribution Environment | |
CN112487848A (en) | Character recognition method and terminal equipment | |
CN103440494A (en) | Horrible image identification method and system based on visual significance analyses | |
CN114170482A (en) | Model training method, device, equipment and medium | |
CN111461101A (en) | Method, device and equipment for identifying work clothes mark and storage medium | |
CN110895811A (en) | Image tampering detection method and device | |
CN109166012B (en) | Method and device for classifying users in travel reservation class and pushing information | |
CN112925905B (en) | Method, device, electronic equipment and storage medium for extracting video subtitles | |
CN110889470A (en) | Method and apparatus for processing image | |
CN111402027B (en) | Identity recognition method, commodity loan auditing method, device and terminal equipment | |
CN113766308A (en) | Video cover recommendation method and device, computer equipment and storage medium | |
CN114817518B (en) | License handling method, system and medium based on big data archive identification | |
CN113888760B (en) | Method, device, equipment and medium for monitoring violation information based on software application | |
CN108287817B (en) | Information processing method and device | |
CN112818984B (en) | Title generation method, device, electronic equipment and storage medium | |
KR20160112256A (en) | Image analysis apparatus using cluster system and method using the same | |
US7899255B2 (en) | Method for recognizing and indexing digital media | |
CN116383427B (en) | Picture batch analysis method, system and medium based on intelligent wearable device | |
CN116563869B (en) | Page image word processing method and device, terminal equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160608 |
|
RJ01 | Rejection of invention patent application after publication |