44 results about "Hand vein" patented technology

The invention discloses a hand vein pattern developing method based on mathematical morphology operation. Firstly, contrast enhancement is carried out on a hand vein pattern original image obtained through near infrared by the adoption of a histogram equalization method; secondly, high-pass filtering is carried out on the obtained image for denoising; thirdly, the image is processed in a mathematical morphological processing method by the adoption of opening operation to eliminate texture features in the image; fourthly, image reconstruction is carried out in a continuous geodesic dilation method; fifthly, secondary noise brought by the opening operation and the image reconstruction is eliminated by the adoption of a Gaussian mask algorithm, and therefore a clear hand vein pattern image is obtained. The method can achieve image fusion of the image after contrast enhancement and a result image by the adoption of the original image, and clearness of the hand vein pattern image is further improved.

The invention relates to a collecting and displaying device for hand vein images, which consists of a near infrared image collecting module, a near infrared lighting module, an image processing module and a visible light projecting and displaying module. A medical device based on an optical instrument is formed by integrating a near infrared reflective image collecting system with a visible light projecting and displaying system effectively. The collecting and displaying device for hand vein images can be widely applied to medical means such as injection, blood drawing and blood transfusion for hand veins of human bodies.

The invention provides an identification method and an identification device on the basis of hand vein images. The identification method includes acquiring a hand vein image of a sample; acquiring an adjacent matrix corresponding to a structural feature graph of the hand vein image of the sample; acquiring graph distances from the structural feature graph of the sample to structural feature graphs of various registered samples according to the adjacent matrix corresponding to the structural feature graph of the sample and adjacent matrixes corresponding to the structural feature graphs of the various registered samples in a database; and acquiring the registered sample with the minimum graph distance among the graph distances from the structural feature graph of the sample to the structural feature graphs of the various registered samples so as to determine the identity of the sample. The identification method and the identification device have the advantages that as the adjacent matrix comprises position information of various key points in the structural feature graph of the hand vein image and information of the distances among the various key points, the uniqueness of the hand vein image can be embodied effectively, and the identification accuracy on the basis of the hand vein image can be improved.

The invention provides a hand vein image enhancement method that includes an overall contrast enhancement and a local detail enhancement. Specifically, the method includes: step 1. using two-parameter relation function to convert a hand vein mode sample from a spatial domain to an ambiguity domain and enhancing the overall contrast of the sample; step 2. using a multiple dimensioned retinex algorithm to enhance the details of the hand vein mode in the ambiguity domain; and step 3. converting the hand vein mode from the ambiguity domain to the spatial domain and forming a result image. The method solves the problems of low contrast, narrow gray value, non-uniform gray value distribution and the like of the hand vein sample, and after improvement, the efficiency of the method conforms to the requirement of a mode identification system.

Provided is a payment authentication system based on the combination of hand veins and multiple fingerprints, comprising a terminal portion, a network transmission portion and a background processing portion, and employing a mode of first registering an account and then performing transaction authentication. In operation of the system, the terminal portion collects user hand veins and multiple fingerprints, and transmits collected data to the background processing portion through the network transmission portion; the background processing portion respectively matches the user hand veins and multiple fingerprints with the user information recorded in the system, and returns information; the network transmission portion transmits the returned information to the terminal portion. The system employs a double authentication mode based on the combination of hand veins and multiple fingerprints to perform account authentication, and can effectively improve the security and correctness of account authentication in a payment process.

The invention discloses an identification method based on hand vein. A hand vein acquisition module realizes the shooting and storage task of hand vein images, an image processing module completes the grey range consistency based on a pixel level and the size unification based on the image size and performs sharpening processing on the acquired vein images with bad quality, and a feature extraction module performs vein feature extraction on the preprocessed vein images by means of the corresponding feature extraction algorithm. The identification method directly processes the hand vein gray image, has the performances of unchanging the size and rotation, and is partially invariant to light change and affine transformation, thereby improving the identification accuracy rate, effectively shortening the identification time, and having great significance on the actual application of hand vein identification technology.

The invention provides an identity recognition device capable of simultaneously capturing human pulse and vein images. The identity recognition device comprises a palm detection table, wherein the palm detection table includes a base and a top connected to the base; a first light source is arranged in the base of the palm detection table and can penetrate out of the upper surface of the base of the palm detection table; a second light source and an image signal acquisition unit are respectively arranged below the top of the palm detection table; and the image signal acquisition unit is used for acquiring transmission light and reflection light formed by the first light source and the second light source through the detected hand and is connected with the signal processing unit. Meanwhile,the invention provides an identity recognition method implemented by adopting the identity recognition device. According to the identity recognition device, the potential safety hazard that vein identification is carried out by using vein photos or 3D molds to forge hand veins of a real person is eliminated, and the robustness of the system is improved; the defect of step-by-step operation in a traditional method is overcome, and the efficiency of the system is improved; and the price is low; popularization and application are easy.

The invention provides electronic equipment with a password and face image or hand vein recognition function. The method comprises the steps that a customer inputs a password in a password input device; a password addressing software or module sends collected password information to a database; comparing recognition is conducted on an address where the customer pre-stores the password and a pre-stored password in the database; a face image collection device collects a customer face image; an image recognition software or module conducts comparing recognition on customer face image information collected by the customer face image collection device and customer face image information pre-stored in the password address in the database or customer identity document face image information pre-stored in the password address in the database; if comparing succeeds, after it is confirmed that the customer password information and the face image information are successfully correlated, the electronic equipment is started; if comparing fails, the electronic equipment cannot be started.

The invention relates to the medical technical field of hand vein image enhancement and segmentation, and discloses a hand vein infrared image enhancement and segmentation method based on AGC and Frangi, and the method comprises the steps: firstly collecting a hand vein image under the irradiation of infrared light, then carrying out the guided filtering of an initial image, and carrying out the sharpening of the edge of the image, the method comprises the following steps: firstly, carrying out image processing on a blood vessel, then stretching the contrast of an image through AGC, then carrying out multi-scale Gaussian filtering noise reduction processing on the processed image, then carrying out blood vessel recognition on the processed image by applying a Frangi algorithm, extracting a tubular blood vessel contour, and finally, carrying out local binarization segmentation and open operation noise reduction on the image in sequence. And a segmented blood vessel shape with an obvious visual effect is obtained. According to the method, the AGC algorithm and the Frangi algorithm are innovatively combined, breakpoints generated after Frangi processing can be effectively reduced through combination of the AGC algorithm and the Frangi algorithm, and therefore the overall image enhancement and segmentation effect is improved.

The invention discloses a hand vein blood vessel depth detection device based on a binocular principle. The device comprises a near-infrared light source module, an image acquisition module, an imageprocessing module and a shell, the near-infrared light source module, the image acquisition module and the image processing module are all supported on the shell, and the hand skin depth and the handvein blood vessel depth can be measured through near-infrared light short-wave band and long-wave band irradiation.

Provided is a payment collection device based on hand veins and multiple finger fingerprints, comprising a keyboard, a display screen, a housing, a handle, a hand vein collection module, a multiple finger fingerprint collection module and a wireless transmit-receive module. The device is generally in a standby state, and starts to work when a user wakes up the device through a key: first, inputting a money amount on the keyboard and displaying data on a display screen; utilizing the hand vein collection module to obtain a hand vein image, and meanwhile utilizing the multiple finger fingerprint collection module to collect fingerprint images of an index finger, a middle finger, a ring finger and a little finger on the handle; then sending the collected vein image, the fingerprint images and the money amount to a background system through the wireless transmit-receive module, and receiving returned operation information; and finally displaying an operation result on the display screen. The device takes full advantage of different hand biological characteristics of the hand veins and the fingerprints, and has the characteristics of higher accuracy, anti-falsification and security compared with a single vein authentication mode.

The invention discloses a hand vein recognition method and device for dual living body verification, and relates to the field of identity verification. The method comprises the steps of obtaining physiological parameters of a to-be-verified hand; performing action feature living body verification when the physiological parameters are greater than a first preset threshold value; calculating the palm similarity and the hand back similarity after living body verification succeeds; and if both the palm similarity and the hand back similarity are greater than a second preset threshold, indicating that the hand vein recognition succeeds. According to the invention, dual living body verification is carried out in a manner of combining action characteristics and physiological parameter detection;the palm vein image and the hand back vein image are respectively extracted for vein recognition, the reliability is improved through dual living body verification and dual vein recognition of the palm vein image and the hand back vein image, and the method and device are particularly suitable for occasions with very high reliability requirements.

The invention discloses a numerical control detonator dissection machine tool and a dissection method thereof. The machine tool comprises a numerical control machine body, and a dissection machine body fixedly mounted on the side surface; the numerical control machine body is integrated with the dissection machine body; a digital system is positioned in the digital machine body, and is provided with a key area and a display area; the side surface of the numerical control machine body is electrically connected with an electronic hand vein through an electric wire; a slide rail is fixedly mounted in the dissection machine body, and a Z axle is in the direction of the slide rail; a slide sleeve slidingly sleeves the slide rail; a first chassis is fixedly mounted at one end of the slide rail;and the bottom of the first chassis is fixedly connected with the bottom of an inner cavity of the dissection machine body. A tool bit is adjusted to move on the Z axle and an X axle through a first motor and a second motor by the electronic hand vein; the position of the tool bit is adjusted to correspond to the positions of fixed detonators; then, a rotating motor is started to rotate the detonators; a cutter is controlled to dissect the detonators during moving on the X axle, so that the operation is simple and convenient; and the manual touch of the detonators is not needed during dissecting, so that the safety is guaranteed.

Embodiments of the invention provide an information collection method and apparatus, a remote controller and an identity recognition method and apparatus. The information collection method comprises the steps of collecting palm vein information; and processing the palm vein information, and extracting palm vein feature information, wherein the palm vein feature information is used for identity recognition. By adopting the scheme, the identity recognition is performed by utilizing the palm vein feature information; the use is extremely convenient; and the palm vein feature information is basedon finger vein living body features, so that the security is extremely high.

The invention discloses a convenient and adjustable hand vein infusion fixer which is characterized in that a hand back fixing band is disposed on the bat body of a bat-shaped body, a wrist fixing band is disposed on the handle body of the bat-shaped body, the bat-shaped body is provided with a waterproof layer, the hand back fixing band is fixedly connected with the bat body through a connecting device, the wrist fixing band is fixedly connected to one side of the bat body, the hand back fixing band and the wrist fixing band are the fluffy faces of nylon loop fasteners, nylon loop fastener hooked faces are respectively disposed on the back of the pat body and on the back of the handle body, and the connecting device is an elastic connecting line. The convenient and adjustable hand vein infusion fixer has the advantages that the fixer is easy in material acquiring, low in manufacturing cost, convenient to use and applicable to infusion of hospitals and communities, and the positions of the hand back fixing band can be adjusted up and down according to the size of the hand of a patient.

The invention discloses an intelligent terminal operation management method and device and an intelligent terminal. The intelligent terminal operation management method comprises the following steps of: acquiring hand vein pattern information of the current user; and triggering the intelligent terminal to enter a preset operation mode corresponding to the currently acquired hand vein pattern information on the basis of the acquired hand vein pattern information of the current user. According to the method disclosed by the invention, the users can enter different operation modes of the intelligent terminal more conveniently.

The invention discloses a federal learning-based finger vein and palm vein recognition method and system and a computer readable storage medium. The method comprises the following steps of obtaining a hand vein image; carrying out federated learning training on the mobilenetV2 detection model by utilizing the public data set; the model parameters of the convolution part of the trained vein detection model mobilenetV2 are uploaded to a center party; the central party performs federal learning aggregation to obtain a plurality of aggregation models; performing fine tuning on the obtained aggregation model in a local data set to obtain a trained mobileNetV2 detection model; inputting the hand vein image into a trained mobileNetV2 detection model to extract a feature vector; and calculating the similarity between the extracted feature vector and a vein feature vector of a registered person in a preset database, and if the similarity is greater than a preset threshold, determining that the current hand vein image belongs to the registered person, and successfully identifying. According to the invention, the risk of privacy data leakage is reduced; and meanwhile, the problem of non-independent identically distributed data sets is solved.

The invention relates to an acquisition system and an acquisition method for a novel biometrics identification method. The system utilizes low-cost devices to acquire texture images of hand veins, reasonably designs a light path, and adopts a method combining transmission and reflection near-infrared light sources to realize three imagining modes: a transmission mode, a reflection mode and a mixedmode, thereby obtaining comprehensively considered hand vein images. Three times of filtering denoising treatment is used for smoothening the hand vein images, and finally output hand vein images canachieve the segmentation effect. The acquisition system can use a cheap non-professional camera due to reasonable light source design and an effective denoising treatment method, thereby greatly reducing the system cost.

The utility model relates to a portable dorsal hand vein observation instrument. The instrument consists of observation window, lens barrel, zoom knob, focus adjustment knob, top lighting module, housing, base with power supply, top light source switch, bottom light source switch, and bottom light source. The instrument of the invention utilizes the magnification characteristic of the microscope, enables medical personnel to observe clear veins on the back of the hand, facilitates venipuncture, improves the accuracy of venipuncture, and has a simple structure and low cost.

The embodiment of the invention discloses a file processing method and device, electronic equipment and a storage medium. The method comprises the steps that when a file access request is received, hand vein features corresponding to a target subject are obtained, and if the hand vein features are consistent with stored vein features associated with a target vehicle, a to-be-matched icon password corresponding to the stored vein features is called; and if the to-be-verified icon password corresponding to the trigger operation is consistent with the to-be-matched icon password, determining that a target file corresponding to the file access request is successfully decrypted, and displaying the target file. The problem that the data is easy to leak due to the fact that the encryption coefficient is low when the data is encrypted and decrypted based on the single finger vein feature in the prior art is solved, the difficulty coefficient of data decryption is increased, and the effect of guaranteeing the data security is achieved.