744 results about "Body images" patented technology

The present invention is a method and system for measuring human response to retail elements, based on the shopper's facial expressions and behaviors. From a facial image sequence, the facial geometry—facial pose and facial feature positions—is estimated to facilitate the recognition of facial expressions, gaze, and demographic categories. The recognized facial expression is translated into an affective state of the shopper and the gaze is translated into the target and the level of interest of the shopper. The body image sequence is processed to identify the shopper's interaction with a given retail element—such as a product, a brand, or a category. The dynamic changes of the affective state and the interest toward the retail element measured from facial image sequence is analyzed in the context of the recognized shopper's interaction with the retail element and the demographic categories, to estimate both the shopper's changes in attitude toward the retail element and the end response—such as a purchase decision or a product rating.

A system and method is presented for virtually fitting clothing, jewelry, hats, or eyewear frames utilizing 3D scans of a user's face and / or body. The system and method include inputting a 3D scan of a user's face and a 3D model of the item into the software. The 3D image of the item to be fitted is placed on the face or body image resulting from the 3D scan and is iteratively moved until collision is detected between the 3D model of the item and the 3D model of the face or body. A recommendation engine can be used to recommend different items to the user based on the virtual fit. Eyewear frames may be recommended based on testing each model to determine if temple pieces are long enough to get over the ear and if flex is too great or too small.

Systems and graphical user interfaces for analyzing body images. In an exemplary embodiment, the present invention provides a graphical user interface having a display coupled to a microprocessing device and a memory device. The graphical user interface has an electronic representation of a first body image and a second body image and an electronic map representing the position of nodules on the first body image and second body image.

A computer generated 3-D model of the human body (avatar) is created by aggregating personal health and medical data of a user. This data may include data derived from the user's electronic medical record. The user's physical characteristics are entered into the software to generate a personalized avatar that resembles him or her. Data regarding the user's medical history and physical characteristics are visualized on the avatar to map the past and present states of the user, and may be modified by a set of health variables for the purpose of projecting a future body image over established time intervals.

The present invention is a system and method for increasing the value of the audio-visual entertainment systems, such as karaoke, by simulating a virtual stage environment and enhancing the user's facial image in a continuous video input, automatically, dynamically and in real-time. The present invention is named Enhanced Virtual Karaoke (EVIKA). The EVIKA system consists of two major modules, the facial image enhancement module and the virtual stage simulation module. The facial image enhancement module augments the user's image using the embedded Facial Enhancement Technology (F.E.T.) in real-time. The virtual stage simulation module constructs a virtual stage in the display by augmenting the environmental image. The EVIKA puts the user's enhanced body image into the dynamic background, which changes according to the user's arbitrary motion. During the entire process, the user can interact with the system and select and interact with the virtual objects on the screen. The capability of real-time execution of the EVIKA system even with complex backgrounds enables the user to experience a whole new live virtual entertainment environment experience, which was not possible before.

The invention discloses a method for locating a vehicle license plate in complex background. The method comprises the following steps: (1). Differentiating a gray scale mean of a fixed-size region and extracting a vehicle body image from a video; (2). preprocessing the vehicle body image such as gradation, gradient information enhancing, binarization and the like; (3). performing mathematical morphology operation on the processed vehicle body image, and performing primary screening by combining structural features of the vehicle license plate to obtain a plurality of candidate vehicle license plate regions; (4). converting the obtained candidate vehicle license plate regions into an HSV color spatial image; (5). adopting a BP neural network to perform color identification on the HSV color spatial candidate vehicle license plate image, and performing color edge detection by computing the mean color distance between two adjacent regions of a certain pixel; (6). judging edge color pair of an edge point, and eliminating the false vehicle license plate edge; and (7). performing final vehicle license plate location by the texture feature of the vehicle license plate. The method is suitable for complex background, and has higher location accuracy rate and higher robustness.

Synthesized body images are generated for a machine learning algorithm of a body joint tracking system. Frames from motion capture sequences are retargeted to several different body types, to leverage the motion capture sequences. To avoid providing redundant or similar frames to the machine learning algorithm, and to provide a compact yet highly variegated set of images, dissimilar frames can be identified using a similarity metric. The similarity metric is used to locate frames which are sufficiently distinct, according to a threshold distance. For realism, noise is added to the depth images based on noise sources which a real world depth camera would often experience. Other random variations can be introduced as well. For example, a degree of randomness can be added to retargeting. For each frame, the depth image and a corresponding classification image, with labeled body parts, are provided. 3-D scene elements can also be provided.

A biometrics authentication device identifies characteristics of the body from captured images of the body and performs individual authentication. The device guides a user, at the time of verification, to the image capture state at the time of registration of biometrics characteristic data. At the time of registration of biometrics characteristic data, body image capture state data is extracted from an image captured by an image capture unit and is registered in a storage unit, and at the time of verification the registered image capture state data is read from the storage unit and is compared with image capture state data extracted at the time of verification, and guidance of the body is provided. Alternatively, an outline of the body at the time of registration, taken from image capture state data at the time of registration, is displayed.

A method uses body images and computer hardware and software to collect and analyze clinical data in patients experiencing pain. Pain location information is obtained by the drawing of an outline of the pain on a paper copy or electronic display of the body image. Composite images are generated representing aggregate data for specified patient groups. The coordinates of common anatomic landmarks on differently designed body images are mapped to each other, permitting integrated analysis of pain data, e.g., pain shape, centroid, meta centroid, from multiple body image designs and display of all pain data on a single body image design. Differences and similarities between groups of patients are displayed visually and numerically, and are used to assign the probability of a given patient belonging to a particular diagnostic group or category of disease severity.

A method of operating a surgical navigation system is disclosed in which a user may easily recognize a depth perception between virtual organ models and a depth relationship between the virtual organ model and a surgical instrument by switching a two-dimensional organ image which is formed through an augmented reality to a virtual organ mode by three-dimensionally rendering the organ image. A method of operating a surgical navigation system comprises identifying an object from a body image captured by a camera, forming the object in a two-dimensional organ image by using an augmented reality, and forming a virtual organ model by three-dimensionally rendering the organ image.

The invention discloses a method and system for matching features of human bodies and MAC (medium access control) addresses. The method comprises the following steps: receiving a video image within a monitoring range, acquiring face images and / or body images, extracting face features or body features, respectively clustering the face features or the body features into face clusters or body clusters, correlating and clustering the face clusters or the body clusters of a same person and acquiring a movement trajectory of each of the human bodies; acquiring MAC records of mobile equipment, storing the MAC records into a MAC diary database and drawing a movement trajectory of the mobile equipment; acquiring and traversing each of the human bodies according to the movement trajectory of each of the human bodies, calculating the times cij of successful matching of each of the human bodies and each of mobile equipment in the movement trajectory and the times of appearance of each of the mobile equipment within the time period of the movement trajectory and acquiring matching rate of each of the human bodies and the equipment according to the a specific value. According to the method and the system, matching is realized by MAC and the face features or the body features, and the identities of the human bodies corresponding to the MAC addresses are acquired by taking the human bodies as mediums, so as to realize the correlation of the identities, the images and the MAC addresses.

A method for segmenting vertebrae in digitized images includes providing a plurality of digitized whole-body images, detecting (91) and segmenting a spinal cord using 3D polynomial spinal model in each of the plurality of images, finding (92) a height of each vertebrae in each image from intensity projections along the spinal cord, and building (93) a parametric model of a vertebrae from the plurality of images. The method further includes providing a new digitized whole-body image including a spinal cord, fitting (94) an ellipse to each vertebrae of the spinal cord to find the major and minor axes, and applying (95) constraints to the major and minor axes in the new image based on the parametric model to segment the vertebrae.

Systems, methods, and apparatus consistent with the present invention may be used to enable a subject to alter an image of the subject's body based on the subject's self-evaluation of the actual condition of the subject's own body. The subject may be prompted to capture, using an image capture device, an initial body image. The subject may also be prompted to self-evaluate the actual condition of the subject's own body. Based on the subject's response to the self-evaluation prompt, the initial body image may be altered to reflect the self-evaluation of the subject.

Systems and graphical user interfaces for analyzing body images. In an exemplary embodiment, the present invention provides a graphical user interface having a display coupled to a microprocessing device and a memory device. The graphical user interface has an electronic representation of a first body image and a second body image and an electronic map representing the position of nodules on the first body image and second body image.

The invention discloses an estimation method for a dressed body 3D model in single character image. The method comprises the steps of firstly, establishing a 3D model training sample based on a real character, secondarily, studying a varied function between a human body posture, a figure and clothes on the training sample, and calculating an average figure of various real character figures, then selecting a single image containing a dressed body image, enabling a user to select a clothes type and the positions of a plurality of joints, enabling a computer to initialize a three-dimensional posture of the dressed body image according to the positions of the joints and provide the clothes type selected by the user and the average figure for the three-dimensional posture so as to obtain an initial three-dimensional model of the body image, and lastly automatically adjusting the figure and posture of an initialized three-dimensional model according to the outline of the dressed body image to enable the three-dimensional model to conform with the shape of a targeted character. The estimation method for the dressed body 3D model in the single character image only need the single character image to establish the three-dimensional dressed character model and is wide in application range and simple and convenient to operate.

A system and method for verifying the registration of a fluoroscopy image, wherein an artificial landmark array is introduced into a radiation path of a fluoroscopy apparatus, the landmark array being trackable by a computer assisted, medical navigation system. A fluoroscopy recording is produced with the aid of the fluoroscopy apparatus, and a spatial position of the artificial landmark array at the time the fluoroscopy recording is produced is detected and stored. The fluoroscopy recording is registered onto previously acquired body image data of the navigation system using marking points mapped on the fluoroscopy recording, wherein the marking points are maps of markings on the radiation source. Verification is based on a correspondence between an image shadow of the artificial landmark array on the fluoroscopy recording and a position of the landmark array at the time the recording was produced.

The invention discloses a height measuring method and a height measuring device based on body posture identification. The method comprises the following steps of: acquiring a scene image comprising a body posture; automatically identifying the body posture, wherein different height measuring methods are adopted for bodies of different postures; when a human body is in a posture which is difficult for measuring height directly, partitioning different positions constructing the height or arm reach in a body image to obtain the physical lengths of different positions constructing the height or arm reach respectively; and further summarizing and estimating the height of the human body. According to the method and the device, the automatic degree and height measuring efficiency of body height measurement are increased greatly.

The invention relates to a method for monitoring pig growth by utilizing a binocular vision technology, and the method comprises the following procedures that: a system is established and calibrated; a pig body image is obtained; the pig body image is transferred; the pig body image is processed; the height of the pig body and the area of the pig body back are measured; and the weight of the pig body is pre-estimated. The growth of the pig is monitored though the method of the invention, the stress to the growth of the pig can not be caused, the operation is easy, the labor strength is reduced, the efficiency is high, the real time is good, the realization of the automation and the network transfer are beneficial, and the remote monitoring can be realized.

The invention discloses an interactive exercise method and a head-mounted intelligent device. The interactive exercise method comprises the following steps: receiving body exercise data and body image data; analyzing the body exercise data, and establishing a real-time exercise model; integrating the real-time exercise model and a virtual character image, thus generating a three-dimensional exercise virtual character; integrating the three-dimensional exercise virtual character and the body image data, thus generating mixed reality exercise image data; constructing a virtual exercise environment, wherein the virtual exercise environment at least comprises a virtual background environment; integrating the mixed reality exercise image data and the virtual exercise environment, thus generating a virtual exercise scene; outputting the virtual exercise scene. Through the mode, the reduction degree of a real character can be improved, and the beautiful virtual exercise environment can be constructed to provide a more real sense of immersion.

The invention discloses an access control system and a method based on face recognition. The access control system comprises a first trigger module, a second trigger module, a first image processing module, a second image processing module and a facial feature comparing module, wherein a first image collecting module can collect a wholly-body image of personnel in a first trigger area; a second image collecting module can collect a face image of personnel in a second trigger area, process the whole-body image and correct parameters; compared with all prestored outline information, all prestored face images in a correcting area can be screened out, and the prestored face images are matched and fused with the collected face image; the facial feature comparing module can control an access control system to unlock according to a matching degree of the face image; meanwhile, the access control system can sense that personnel enter and exit through a sensing module, so that advertisements can be broadcasted and interrupted in real time; the access control system disclosed by the invention can quickly and accurately perform image recognition, so that access control system response time delay is reduced, advertisement exchange is accurately achieved, a work efficiency of the access control system is improved, and convenience is brought to property management.

The camera system is constituted by the camera main body and the interchangeable lens which is removably attachable to the camera main body. The camera main body has an imaging unit, a main body shake detector, a main body image blur corrector, and a body microcomputer configured to control the imaging unit, the shake detector, and the image blur corrector. The interchangeable lens has a shake detector, an image blur corrector, and a lens microcomputer configured to control the shake detector and the image blur corrector. The body microcomputer selects either the main body or lens shake detector, activates the selected shake detector, and stops the other shake detector.

The invention relates to a visual false body image processing device and the method, belonging to the field of biological engineering. In the invention, an image collecting module is a CMOS digital image sensor which converts the obtained image information into digital mode; a wireless transmission module is responsible for the communication of the image collecting module and the image processing module, then transmits the image information collected by the image collecting module to the image processing module; the image processing module has an image information precorrection to the obtained image to improve the image quality, having image information simplifying, strengthening or coding treatment to transform the obtained image information into the pulse encouraging mode accepted by the visual system to provide for an internal stimulation module, and providing the function of self regulation for users. The method is showed as follows: firstly executing image pretreatment, then through an image complexity judgment, the image is divided into three kinds and the corresponding treatment procedure is adopted. The invention resolves the prior disadvantage to be applied in all types of visual false body.

Delivery of health information to a patient suffering from a chronic condition is personalized by displaying the health information directly on a customized image of a body. The patient's medical record, standards of care for the condition, prescribed treatments, and patient input are applied to a generalized health model of a disease to generate a personalized health model of the patient. The personalized health model comprises an HTML file encoding an image map of a body. The body image illustrates the health condition of the individual patient. Preferably, data is collected from health provider sources and stored in a database on a server at a service provider site. The data is processed at the server, and is displayed in the patient's home using a TV connected to a multimedia processor. The multimedia processor connects the television set to a communications network such as the Internet. Applications include preventive care of chronic diseases such as diabetes and asthma.

The invention discloses an abnormal vehicle license plate recognition method and a system. the method comprises the following steps: 10, an image of an abnormal vehicle license plate is captured; 20, the image of the abnormal vehicle license plate is pre-treated to obtain a filter image; 30, a vehicle body image is detected in the filter image; 40, the abnormal vehicle license plate is positioned in the vehicle body image; 50, characters of the abnormal vehicle license plate are segmented in the vehicle license plate region; and 60, a Chinese character classifier, an alphabet classifier and a mixed number and alphabetclassifier are arranged respectively so as to recognize the characters of the abnormal vehicle license plate, and the following operation is carried out on each classifier. Thus, the vehicle license plate can be recognized in the abnormal condition, and the vehicle license plate recognition precision is high.

The invention provides an intelligent pest situation monitoring method and an intelligent pest situation monitoring device, and relates to the technical field of pest situation monitoring. The intelligent pest situation monitoring method includes the steps of capturing pests, collecting pest images, transmitting the pest images, processing the pest images and establishing a pest warning model. Thepests are captured by traps, the pest bodies are photographed by cameras to obtain pest body images, the pest body images are transferred to an image processing module of a pest situation observationand prediction device for identification, statistics and analysis. The intelligent pest situation monitoring method can accurately grasp the species, number and growth status of the pests, can effectively cope with and control the pests, has a high degree of automation and a high degree of intelligence, integrates pest monitoring and controlling into one, and has a good pest control effect. The invention also provides the intelligent pest situation monitoring device. The device comprises a box, the cameras, an electric brush, a controller, the image processing module and the traps, the monitoring is timely and effective, and the identification result is accurate.

The invention relates to the technical field of aquatic product index measurement and particularly relates to an automatic measuring device and method for fish type morphological parameters. The automatic measuring device comprises a computer, a framework main body (1), a live fish flow guide groove (2) which is obliquely formed on the framework main body (1) and a photographing device which is arranged at the lower end of the live fish flow guide groove (2) and is used for photographing a fish body image; the bottom of the live fish flow guide groove (2) is a transparent platform; the photographing device comprises a bracket (4) arranged on the framework main body (1) and an industrial camera (5) which is in sliding connection with the bracket (4); the industrial camera is in signal connection with the computer; the computer comprises a parameter setting module, a calibration module, an image acquisition module, a fish body size automatic extracting module and a fish body size manual measuring module which are in signal connection in sequence. With the adoption of the device and the method, the fish type morphological parameters can be rapidly acquired in a lossless mode.

The invention provides a recurrent neural network attention model-based pedestrian attribute recognition network and technology. The pedestrian attribute recognition network comprises a first convolutional neural network, a recurrent neural network and a second convolutional neural network, wherein the first convolutional neural network is used for extracting a whole body image feature of a pedestrian by taking an original body image of the pedestrian as an input; the recurrent neural network is used for outputting an attention heat map of an attribute group concerned at the current moment andlocally highlighted pedestrian features by taking the whole body image feature of the pedestrian as a first input and taking an attention heat map of an attribute group concerned at the last moment as a second input; and the second convolutional neural network is used for outputting an attribute prediction probability of the currently concerned group by taking the locally highlighted pedestrian feature as an input. According to the network and technology, a recurrent neural network attention model is utilized to mine an association relationship of pedestrian attribute area space positions soas to highlight positions of areas corresponding to attributes in images, so that higher pedestrian attribute recognition precision is realized.

The invention discloses a photograph preview method for an electronic device, a graphical user interface, and an electronic device, and by the method the body image of the person being photographed isadjusted during the photograph preview or the video preview process, so that the body shape represented by the adjusted body image is more beautifully shaped than the actual body shape of the photographed person. Body beautifying comprises beautifying body proportions (such as stretching the legs, widening the shoulders, etc.), and adjusting the body's fatness and thinness (such as slimming waist, slimming legs, flattening stomach, tightening buttocks or plumping up certain parts of body, etc.). The photograph preview method for an electronic device, the graphical user interface, and the electronic device enable the user to beautify the photographed person during the camera preview process, which is simple to operate, and high in effect.

The invention discloses a cone-beam computed tomography image and X-ray image registration method; the method uses a regression model based on a mixing residual error convolution nerve network to build associations between two-dimension X-ray images and three dimensional cone-beam CT image non-rigid deformation parameters, and uses a mixing residual error convolution nerve network and deformation parameter iteration optimization method to realize reliable online two-dimension three dimensional image registration; the method comprises the following steps: extracting to obtain an image channel; training the regression model based on the mixing residual error convolution nerve network; carrying out two-dimension three dimensional non-rigid registration based on regression; iterating and optimizing deformation parameters; obtaining a final body image determined by the deformation parameters, and thus realizing two-dimension three dimensional image registration based on iteration regression. The method can realize reliable online two-dimension three dimensional image registration, can be applied to oral cavity clinics, and can evaluate treatments and analyze craniofacial growth according to two-dimension three dimensional image registrations.