CN203786745U - Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system - Google Patents
Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system Download PDFInfo
- Publication number
- CN203786745U CN203786745U CN201420166090.7U CN201420166090U CN203786745U CN 203786745 U CN203786745 U CN 203786745U CN 201420166090 U CN201420166090 U CN 201420166090U CN 203786745 U CN203786745 U CN 203786745U
- Authority
- CN
- China
- Prior art keywords
- door knob
- module
- appearance
- knob shape
- staff image
- 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.)
- Expired - Fee Related
Links
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 230000003287 optical effect Effects 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 23
- 230000008569 process Effects 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 10
- 210000003811 finger Anatomy 0.000 description 5
- 241000905957 Channa melasoma Species 0.000 description 3
- 230000005055 memory storage Effects 0.000 description 3
- 210000001015 abdomen Anatomy 0.000 description 2
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002650 habitual effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 239000012780 transparent material Substances 0.000 description 2
- 244000060701 Kaempferia pandurata Species 0.000 description 1
- 235000016390 Uvaria chamae Nutrition 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000005224 forefinger Anatomy 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The utility model discloses a door-handle-shaped holding posture human hand image acquisition device comprising a door-handle-shaped shell of which the side wall is provided with an image acquisition window, and a light source and a photographing device which are arranged in the door-handle-shaped shell. Light rays emitted by the light source can be reflected into the photographing device by a hand palm to be imaged. The utility model also provides a holding posture human hand image identification system comprising the door-handle-shaped holding posture human hand image acquisition device, a feature extraction module, an identification module and an execution module which are connected in turn. The identification module is also connected with a storage module. Compared with systems in the prior art, user identification operation and door-opening operation are combined by the holding posture human hand image identification system and the identification method thereof, identity identification operation is automatically performed imperceptibly, and the using mode is identical with that of a conventional door handle.
Description
Technical field
The utility model relates to field of image recognition, relates in particular to collection, processing and the identification of holding appearance staff image.
Background technology
Human body biological characteristics recognition technology was risen from the 1980s, in progressively widespread use of 21st century, was not only applied in the traditional field such as access control, identity discriminating, in medical treatment, border control, entertainment field, had also obtained very large development.Use various recognition systems and the method for fingerprint identification technology, iris recognition technology, face recognition technology and palmmprint recognition technology to emerge in an endless stream.
The most basic application of living things feature recognition is exactly access control, and is access control equipment with the longest history with the door of door lock and handle.Existing living things feature recognition equipment some need to hang on the wall or door upper, as iris identification equipment, palmmprint identification equipment, face recognition device and fingerprint identification device; Some need to stand in a limit, as face recognition device, vertical palmmprint identification equipment; Only have fingerprint identification device can be placed near the handle of door, but because fingerprint sensor need to be pointed the upright smooth sensing contact face of finger belly plane, so can not allow user hold door handle with natural posture.
The existing human body biological characteristics recognition technology based on staff, great majority need to stretch staff to set level, and are placed on specialized equipment and gather image to identify, and as palmmprint, identification need to be shakeout relieving palm; Fingerprint recognition need to be pointed finger belly and aim at sensitive face; Finger and articulations digitorum manus are identified and to be needed finger to stretch to keep flat.Only have articulations digitorum manus recognition technology can use the articulations digitorum manus back image under natural torsion state to identify, but this technology is difficult to again control image capture environment, is easily subject to ambient lighting and reflections affect.
The existing human body biological characteristics recognition technology based on staff is the staff under None-identified natural posture all, also cannot be combined with door handle.User needs first hand or finger accurately to be identified in use, re-uses door handle and pushes the door open, and causes identifying operation separated with opening door operation.
Utility model content
The technical matters that the utility model solves be to provide a kind of can be in conjunction with user's identifying operation and opening door operation hold appearance staff image identification system and recognition methods thereof.
The utility model solves the technical scheme that its technical matters adopts:
Door knob shape is held an appearance staff image collecting device, for gathering, holds appearance staff image, comprising: sidewall offers the door knob shape housing of image acquisition window, and is arranged at light source and picture pick-up device in described door knob shape housing; The light that described light source sends can be entered imaging in described picture pick-up device by palmar.
Preferably, this door knob shape is held appearance staff image collecting device and is also comprised the optical element being arranged in described door knob shape housing; Describedly by the light of palmar, through the guiding of described optical element, entered imaging in picture pick-up device.
Described door knob shape housing be using sidewall as the surfaces of revolution, tail diameter large and less Rotary-table or the class Rotary-table of head diameter, described sidewall whole clearing, to realize image acquisition window function; It is central that described picture pick-up device is arranged at described door knob shape housing head, and a plurality of described light sources are arranged at described door knob shape housing head around described picture pick-up device, and described optical element is the catoptron that is arranged on described door knob shape housing afterbody.
More excellent, described door knob shape housing sidewall is also provided with the reference column that carries out reference location while supplying user's handling.
In addition, the utility model also provide use that above-mentioned door knob shape holds that appearance staff image collecting device holds the image recognition of appearance staff hold appearance staff image identification system:
Hold an appearance staff image identification system, comprising: the door knob shape being linked in sequence is held appearance staff image collecting device, characteristic extracting module, identification module and execution module, and described identification module is also connected with memory module;
Described door knob shape is held appearance staff image collecting device and is sent to described characteristic extracting module for gathering to hold appearance staff image and will hold appearance staff image,
Described characteristic extracting module is used for extracting the characteristic of holding appearance staff image, and characteristic is sent to described identification module,
Described identification module is for by the identification of comparing of the feature templates of characteristic and memory module, and exports recognition result to execution module,
Execution module is according to recognition result executable operations.
Described characteristic extracting module comprises global feature extraction unit and local feature extraction unit;
Described global feature extraction unit is used for extracting the global feature data of holding appearance staff image, and global feature data are sent to described identification module,
Described local feature extraction unit is used for extracting the local feature data of holding appearance staff image, and local feature data are sent to described identification module,
Described identification module first dwindles feature templates scope according to described global feature data, then by local feature and feature templates matching identification.
Described global feature extraction unit comprises right-hand man's taxon and staff resemblance extraction unit;
Described right-hand man's taxon is used for distinguishing that holding appearance staff image is that left-handed or the right hand grip, and right-hand man's information is sent to described identification module,
Described staff resemblance extraction module is used for extracting the staff shape data of holding appearance staff image, and staff shape data is sent to described identification module,
Described identification module first judges that according to described right-hand man information and staff shape data dwindle feature templates scope, then by local feature and feature templates matching identification.
Compared with prior art, door knob shape of the present utility model is held appearance staff image collecting device and is held appearance staff image identification system user's identifying operation is combined with opening door operation, user only needs nature to hold door knob shape of the present utility model to hold appearance staff image collecting device and just can identify, to be identified passing through, user just can continue push-and-pull door knob shape of the present utility model and hold appearance staff image collecting device door is opened, identification operates in unconsciously to be carried out automatically, consistent with conventional door handles use-pattern.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of holding appearance staff image identification system of the present utility model;
Fig. 2 is the structural representation that door knob shape of the present utility model is held appearance staff image collecting device;
Fig. 3 is the side wall construction schematic diagram that door knob shape of the present utility model is held appearance staff image collecting device;
Fig. 4 is the process flow diagram of holding appearance staff image-recognizing method of the present utility model.
Embodiment
Below in conjunction with the drawings and specific embodiments, the utility model is described further.
Of the present utility modelly hold appearance staff image identification system as shown in Figure 1, comprise that the door knob shape being linked in sequence is held appearance staff image collecting device 1, characteristic extracting module 2, identification module 3 and execution module 4, described identification module 3 is also connected with memory module 5, and described execution module 4 is connected with electronic lock 6.In this embodiment, described characteristic extracting module 2 and identification module 3 are virtual modules, specifically can adopt desktop computer or the embedded system of using USB device; Execution module 4 can adopt the single-chip microcomputer of USB mouth communication.In actual use, described characteristic extracting module 2, identification module 3 and execution module 4 can be also the hardware modules that realizes standalone feature.
Of the present utility modelly hold the door knob shape that appearance staff image identification system uses and hold appearance staff image collecting device 1 as shown in Figure 2, comprising: door knob shape housing 11, light source 12, picture pick-up device 13 and catoptron 14.Described door knob shape housing 11 be using sidewall 111 as the surfaces of revolution, afterbody 112 diameters large and less Rotary-table or the class Rotary-table of head 113 diameters, sidewall 111 whole clearings, to realize image acquisition window function; Described picture pick-up device 13 is arranged at described door knob shape housing 11 head 113 central authorities, and a plurality of described light sources 12 are arranged at described door knob shape housing head 113 around described picture pick-up device 13, and described catoptron 14 is arranged on described door knob shape housing 11 afterbodys 112.
The sidewall 111 of door knob shape shell 11 adopts transparent material to make, and is preferably the smooth acrylic material of transmittance >90%, and this smooth acrylic material adopts and repeatedly burnishes and fabricates step by step to guarantee that surface of contact is smooth transparent.Understandable, described sidewall 111 also can adopt other non-transparent material to make, and only need on described sidewall 111, offer transparent image acquisition window.
Light source 12 preferably adopts LED white light source.Understandable, described light source 12 can also adopt the light source of other types, also can be set to other positions of door knob shape shell 11 inside, as long as can provide enough illuminations for holding appearance staff image acquisition.
The camera lens of picture pick-up device 13 preferably adopts the common or pinhole lens of <10mm focal length.Picture pick-up device 13 can adopt analogue camera and USB capture card according to different application demand, or digital CCD/CMOS camera of USB interface, or with the wireless CCD/CMOS camera that USB wireless adapter pairing is used, maybe can use the Ethernet camera of POE.
Catoptron 14 preferably adopts full spectral reflectance mirror, full spectral coverage reflectivity >95%.Understandable, described catoptron 14 also can need to adopt other optical elements according to actual optical path change.
Refer to the dotted arrow in Fig. 2, when this door knob shape is held appearance staff image collecting device 1 and is held appearance staff image image acquisition, the light that described light source 12 sends is by palmar, describedly by the light of palmar, through the guiding of described optical element 14, entered imaging in picture pick-up device 13, complete the collection of holding appearance staff image.Optical element 14 has played the effect that extends light path, has greatly dwindled the volume of door knob shape housing 11.
More excellent, refer to Fig. 3, the left and right sides of described door knob shape housing 11 sidewall 111 bottoms is respectively equipped with reference column 15, and user, when holding door knob shape housing 11, is clipped in the forefinger of left hand or the right hand and middle finger root to realize reference location by reference column 15.
Of the present utility modelly hold the appearance staff image-recognizing method flow process of holding that appearance staff image identification system uses and refer to Fig. 4, comprise the following steps:
S1. (flow process 400-403) door knob shape is held 1 collection of appearance staff image collecting device and is held appearance staff image;
S2. described in 2 extractions of (flow process 404-417) characteristic extracting module, hold the characteristic in appearance staff image;
S3. (flow process 418-421) identification module 3 is by the feature templates identification of comparing of storage in described characteristic and memory storage 5;
S4. (flow process 422-423) if comparison the match is successful, execution module 4 unlocking electronic door locks; If it fails to match in comparison, execution module 4 keeps electronic lock to close.
Wherein, described characteristic extracting module 2 comprises right-hand man's taxon, staff resemblance extraction unit and local feature extraction unit, and described step S2 comprises the step of following executed in parallel:
S2-1-1. (flow process 404-407) right-hand man taxon will be held appearance staff image and will be converted to gray level image, extract and hold the effective image of central area, both sides in appearance staff image and make difference to distinguish right-hand man, obtain right-hand man and distinguish result;
S2-1-2. (flow process 408-412) staff resemblance extraction unit polar coordinates launch to hold appearance staff image, along radial direction projection, hold appearance staff image, and projection calculate staff length with this described in binaryzation, obtains staff length data;
S2-2. (flow process 413-417) local feature extraction unit, to holding appearance staff image cutting square block of cells, is used multi-direction Gabor filter filtering to process, and uses LBP encode and combine each block coding, obtains local feature coded data.
The reason that described step S2-1-1 can carry out is the setting of reference column 15, if reference column 15 is not set, must adopts so more complicated algorithm to carry out right-hand man and distinguish, makes to differentiate that increase computing time.
Described step S3 comprises the following steps:
S3-1-1. (flow process 418) identification module 4 distinguishes that according to described right-hand man result dwindles described feature templates scope,
S3-1-2. (flow process 419) identification module 4 further dwindles described feature templates scope according to described staff level data.
S3-2. (flow process 420-421) identification module 4 calculates respectively and calculates respectively the mahalanobis distance of all feature templates within the scope of local feature coded data and feature templates and judge one by one whether mahalanobis distance is less than threshold value, if mahalanobis distance is less than threshold value, the match is successful, if mahalanobis distance is greater than threshold value, it fails to match.
The appearance staff image identification system of holding of the present utility model is obtained more than 98% discrimination in the batch experiment of 6000 parts of feature templates of 200 people, and the discriminating time is less than 1 second, obtains better effects.
Understandable, step 2-1-1, step 2-1-2, step S3-1-1 and step S3-1-2 are used of the present utility modelly to hold the step that appearance staff image identification system must carry out, but step 2-1-1, step 2-1-2, step S3-1-1 and step S3-1-2 can shorten discriminating computing time greatly; Described step S2-1-2 also can be used the method for other collection staff resemblance data to replace; Described step 2-2 can other prior aries carry out image pre-service, also can adopt the habitual additive method of prior art to encode; Described step 3-2 also can adopt other habitual recognition methodss of this area identification of comparing.
The acquisition of the feature templates in memory module 5 of holding appearance staff image identification system of the present utility model comprises the following steps:
C1. user's typing user profile;
C2. door knob shape is held 1 collection of appearance staff image collecting device and is held appearance staff image;
C3. described in characteristic extracting module 2 extractions, hold the feature templates in appearance staff image;
C4. identification module 3 is stored to described user profile and feature templates in memory storage 5.
Understandable, in obtaining the process of described feature templates, described characteristic extracting module 2 can also be extracted right-hand man simultaneously and distinguish result and staff length data, and by described identification module 3, user profile, right-hand man is distinguished to result, staff length data and feature templates are stored in memory storage 5; In the process that obtains described feature templates, can also comprise the described feature templates of checking, the step of storing a plurality of described feature templates, be all the conventional techniques means of this area, do not repeat them here.
The foregoing is only preferred embodiment of the present utility model, be not limited to the utility model, for a person skilled in the art, the utility model can have various modifications and variations.Protection domain of the present utility model is as the criterion with claims; all within spirit of the present utility model and principle; any modification that claims technical scheme required for protection is made, be equal to replacement, improvement etc., within all should being included in protection domain of the present utility model.
Claims (7)
1. door knob shape is held an appearance staff image collecting device, for gathering, holds appearance staff image, it is characterized in that, comprising: sidewall offers the door knob shape housing of image acquisition window, and is arranged at light source and picture pick-up device in described door knob shape housing; The light that described light source sends can be entered imaging in described picture pick-up device by palmar.
2. door knob shape according to claim 1 is held appearance staff image collecting device, it is characterized in that: also comprise the optical element being arranged in described door knob shape housing; Describedly by the light of palmar, through the guiding of described optical element, entered imaging in picture pick-up device.
3. door knob shape according to claim 2 is held appearance staff image collecting device, it is characterized in that: described door knob shape housing be using sidewall as the surfaces of revolution, tail diameter large and less Rotary-table or the class Rotary-table of head diameter, described sidewall whole clearing, to realize image acquisition window function; It is central that described picture pick-up device is arranged at described door knob shape housing head, and a plurality of described light sources are arranged at described door knob shape housing head around described picture pick-up device, and described optical element is the catoptron that is arranged on described door knob shape housing afterbody.
4. door knob shape according to claim 3 is held appearance staff image collecting device, it is characterized in that: the reference column that carries out reference location when described door knob shape housing sidewall is also provided with for user's handling.
5. hold an appearance staff image identification system, it is characterized in that, comprising: the door knob shape being linked in sequence is held appearance staff image collecting device, characteristic extracting module, identification module and execution module, and described identification module is also connected with memory module;
Described door knob shape is held appearance staff image collecting device and is sent to described characteristic extracting module for gathering to hold appearance staff image and will hold appearance staff image,
Described characteristic extracting module is used for extracting the characteristic of holding appearance staff image, and characteristic is sent to described identification module,
Described identification module is for by the identification of comparing of the feature templates of characteristic and memory module, and exports recognition result to execution module,
Execution module is according to recognition result executable operations;
Described door knob shape is held appearance staff image collecting device and is selected the door knob shape described in claim 1-4 any one to hold appearance staff image collecting device.
6. the appearance staff image identification system of holding according to claim 5, is characterized in that: described characteristic extracting module comprises global feature extraction unit and local feature extraction unit;
Described global feature extraction unit is used for extracting the global feature data of holding appearance staff image, and global feature data are sent to described identification module,
Described local feature extraction unit is used for extracting the local feature data of holding appearance staff image, and local feature data are sent to described identification module,
Described identification module first dwindles feature templates scope according to described global feature data, then by local feature and feature templates matching identification.
7. the appearance staff image identification system of holding according to claim 6, is characterized in that: described global feature extraction unit comprises right-hand man's taxon and staff resemblance extraction unit;
Described right-hand man's taxon is used for distinguishing that holding appearance staff image is that left-handed or the right hand grip, and right-hand man's information is sent to described identification module,
Described staff resemblance extraction module is used for extracting the staff shape data of holding appearance staff image, and staff shape data is sent to described identification module,
Described identification module first judges that according to described right-hand man information and staff shape data dwindle feature templates scope, then by local feature and feature templates matching identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420166090.7U CN203786745U (en) | 2014-04-08 | 2014-04-08 | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420166090.7U CN203786745U (en) | 2014-04-08 | 2014-04-08 | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN203786745U true CN203786745U (en) | 2014-08-20 |
Family
ID=51322906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420166090.7U Expired - Fee Related CN203786745U (en) | 2014-04-08 | 2014-04-08 | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN203786745U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008864A (en) * | 2019-03-22 | 2019-07-12 | 清华大学深圳研究生院 | A kind of miniature manpower identification equipment and recognition methods |
-
2014
- 2014-04-08 CN CN201420166090.7U patent/CN203786745U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008864A (en) * | 2019-03-22 | 2019-07-12 | 清华大学深圳研究生院 | A kind of miniature manpower identification equipment and recognition methods |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A robust iris segmentation scheme based on improved U-net | |
| Cross et al. | Thermographic imaging of the subcutaneous vascular network of the back of the hand for biometric identification | |
| Sun et al. | Iris image classification based on hierarchical visual codebook | |
| Vijayan et al. | Twins 3D face recognition challenge | |
| Sun et al. | Ordinal feature selection for iris and palmprint recognition | |
| CN105787442B (en) | A kind of wearable auxiliary system and its application method of the view-based access control model interaction towards disturbance people | |
| KR20160101973A (en) | System and method for identifying faces in unconstrained media | |
| WO2013087026A1 (en) | Locating method and locating device for iris | |
| WO2013051019A1 (en) | Evolved biometric system with enhanced feature and method for the same | |
| CN101464945A (en) | Identification characteristic identification method based on finger back arthrosis veins | |
| CN112232163A (en) | Fingerprint acquisition method and device, fingerprint comparison method and device, and equipment | |
| CN104898971B (en) | A kind of mouse pointer control method and system based on Visual Trace Technology | |
| CN110781778B (en) | Access control method and device, storage medium and home system | |
| CN203786745U (en) | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system | |
| Benziane et al. | Dorsal hand vein identification based on binary particle swarm optimization | |
| CN104978551B (en) | Grip position manpower image identification system and its recognition methods | |
| US11768926B2 (en) | Method of textured contact lens detection | |
| Li et al. | Iris recognition on mobile devices using near-infrared images | |
| Shirke et al. | Iris Recognition Using Visible Wavelength Light Source and Near Infrared Light Source Image Database: A Short Survey□ | |
| CN112232152A (en) | Non-contact fingerprint identification method and device, terminal and storage medium | |
| Jampour et al. | Extract and classification of iris images by fractal dimension and efficient color of iris | |
| Song et al. | A survey of visible iris recognition | |
| Rafik et al. | A Model Of A Biometric Recognition System Based On The Hough Transform Of Libor Masek and 1-D Log-Gabor Filter | |
| Sun et al. | Research on palm vein recognition algorithm based on improved convolutional neural network | |
| Narmatha et al. | A new approach for iris image identification using modified contour segmentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140820 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |