44results about How to "Facilitate image recognition" patented technology

Game interface tracks the position of one or more game controllers in 3-dimensional space using hybrid video capture and ultrasonic tracking system. The captured video information is used to identify a horizontal and vertical position for each controller within a capture area. The ultrasonic tracking system analyzes sound communications to determine the distances between the game system and each controller and to determine the distances among the controllers. The distances are then analyzed by the game interface to calculate the depths within the capture area for each controller.

The invention provides a container as well as a lighting control method thereof, and a computer readable storage medium. The container comprises a cabinet body, a door body, a camera device, a first lighting module, a second lighting module and a controller, wherein the door body is arranged at an opening of the cabinet body in a retractable way; the camera device is arranged on the cabinet body;the first lighting module is arranged on the cabinet body and is used for providing light for the interior of the cabinet body; the second lighting module is arranged on the cabinet body and is used for providing light for the camera device; the controller is connected with the first lighting module and the second lighting module; the controller is used for controlling the working states of the first lighting module and the second lighting module according to the opening and closing states of the door body. According to the container provided by the invention, the working states of the first lighting module and the second lighting module are controlled by means of the controller according to the opening and closing states of the door body, so that the service lives of the first lighting module and the second lighting module are effectively prolonged under the premise that the information such as the commodities and the price tags is displayed in a highlighted way so as to stimulate consumption.

Ultrasound image recognition systems and methods, and artificial intelligence training networks for such systems and methods, are provided. An ultrasound data information system includes an ultrasound image recognition training network that is configured to receive ultrasound training images and to develop ultrasound image knowledge based on the received ultrasound training images. An ultrasound imaging device acquires ultrasound images of a patient, and the device includes an ultrasound image recognition module. The ultrasound image recognition module is configured to receive the ultrasound image knowledge, receive the acquired ultrasound images from the ultrasound imaging device, and determine, based on the ultrasound image knowledge, whether the received ultrasound images represent a clinically desirable view of an organ or whether the clinically desirable views indicate normal function or a particular pathology. The received ultrasound images are transmitted to the ultrasound image recognition training network for further training and development of updated ultrasound image knowledge.

The invention discloses a multifunctional intelligent blind guiding method. The multifunctional intelligent blind guiding method comprises the following steps of receiving a voice command, and navigating; obtaining image data of an obstacle; carrying out recognition processing on digital image data, judging that threat is formed by the obstacle if the recognized obstacle is a static body, generating an ultrasonic ranging control command, and generating and outputting voice alarm information or vibration prompt information according to a ranging result if the ranging result is within a preset alarm range; and generating an ultrasonic ranging control command if the recognized obstacle is a dynamic body, carrying out threat anticipation calculation according to a ranging result, and generating and outputting voice alarm information or vibration prompt information if the obstacle is within a preset alarm range. The invention also discloses a multifunctional intelligent blind guiding device and a processor. According to the multifunctional intelligent blind guiding method, the multifunctional intelligent blind guiding device and the processor, which are disclosed by the invention, the blind guiding service can be more safely, conveniently and reliably provided for the blind, the blind is prevented from walking more distance and meeting the obstacle, and thus the blind can quickly and safely arrive at the destination.

The invention discloses a face image dimension reducing method based on local correlation preserving. The method comprises the following steps of: expressing a face image by using multi-dimensional vectors, acquiring k neighbors of each vector according to the norm of two difference vectors, and calculating normalization weight of the k neighbors of each vector according to a radial basis function; calculating a difference vector of each vector and the sum of the weights of the k neighbors of each vector, acquiring a matrix by multiplying transposition of each difference vector by each difference vector, and adding the matrixes corresponding all the vectors to acquire a local correlation preserving matrix; and calculating characteristic values and characteristic vectors of the local correlation preserving matrix, and selecting the characteristic vectors corresponding to partial large characteristic values as basic vectors to form a projection matrix, and thus realizing dimension reduction. The dimension reduced face image well preserves local data association, the method is beneficial to image identification, and the classification effect after characteristics are extracted by the method is superior to those of primal component analysis (PCA) and locality preserving projection (LPP); and calculation complexity is reduced, and a relation among the new method, the PCA and the LPP is disclosed.

The invention relates to the technical field of image processing, and discloses an image processing method and system to improve the accuracy and efficiency of image restoration processing. The method of the present invention includes: constructing a convolutional neural network model to realize color spot recognition of facial images and marking the corresponding color spot areas; collecting images of people with a camera located in the middle of the face, identifying the corresponding facial areas, and calling the The convolutional neural network model judges whether the corresponding facial image has color spots, and if so, marks the corresponding color spot area for the user to further confirm whether it is an area to be repaired; in the image processing coordinate system, preferably through the symmetrical area transplant and repair the color to ensure that the repaired color is consistent with the original color; when the conditions do not match, the pixel value corresponding to the adjacent grid that does not have a color mutation is screened out for color repair to ensure that the repaired color is consistent with the surrounding Pair with smooth and natural.

An image processing method generally includes: obtaining a vanishing point on a curve surface in a two-dimension image; extracting all the straight line segments between a top contour line and a bottom contour line of the curve surface by the vanishing point; removing a perspective distortion to get parallel straight line segments; obtaining the lengths of the straight line segments, obtaining the true width of each of the straight line segments in a three-dimension space and the depth increment of the straight line segments according to the lengths; obtaining the expanded width of each straight line segment according to the true width and the depth increment; obtaining the total expanded width of the curve surface to transform it into a flat surface; transforming image contents on the curve surface onto the flat surface. The method can be applied when scanning an open book.

The invention discloses a book inventory robot based on visual SLAM, and relates to the technical field of mechanical engineering. The invention includes a base, a surface of the base is provided with an installation groove, the inner surface of the installation groove is fixedly connected with a mobile positioning device, a surface of the base is fixedly connected with a protective cover, the inner surface of the protective cover is fixedly connected with a lifting encoder, and the shaft of the lifting encoder One end is fixedly connected with a transmission tooth, the axis of the transmission gear is connected with the base in rotation, one surface of the base is fixedly connected with a guide column, the side of the guide column is slidably connected with a lifting seat, and the side of the lifting seat is rotatably connected with a collar. The invention respectively records the displacement, elevation and rotation information of the robot through the mobile positioning device, the lifting encoder and the rotary encoder, so that each positioning and mapping is an independent individual, which avoids the error accumulation caused by the matching of the depth map before and after the visual SLAM technology, and improves the The accuracy of positioning is beneficial for the robot to perform image recognition.